Numenta Live Streams, 5 Jul 2019

Previous Meeting Next Meeting

⏯

youtube image

►

From YouTube: BHTMS: Describing the Minicolumn Competition

Description

I will be reviewing the current prose for the Spatial Pooling page and continuing to write about the minicolumn competition and active duty cycles.

A

Okay, so I think I think I'm streaming.

A

A

Okay, I'm trying again.

A

We are not receiving video data at a fast enough rate.

A

A

So your connection is faster. Consider using a lower bit rate. I think I need to change my bit rate, so just bear with me for a moment: I'm gonna, so I'm gonna. This is the first time I've used this method, I'm, not sure what happens when I broadcast out an alert.

A

Okay, samurai folks, um I think I can change us. Okay, I'm gonna. Try this again still trying this.

A

All right, it's anybody there, just working I, can't tell if it's working yet it says I'm streaming. Let me check the. Let me check something.

A

Says live now, yeah.

B

Yeah, it looks like I'm there.

A

It's ok, great, ok,.

A

So here we are, this is um I'm Matt Taylor. Thanks for joining me, we're going to continue building HTM systems, we'll be talking about the mini column, competition. Today, please excuse any technical difficulties we may be having I may be. Having because certainly the YouTube live thing is totally new to me. Twitch was a lot easier, so I've got a lot a few things to learn here, so hopefully not a big deal.

A

So let me first move to I've got a lot of new tools so.

A

Here's what we're gonna be talking about today.

B

Well: here's where we've.

A

Been where we're going last time we talked about all these things down to the mini column, competition, so I'm gonna, you know, click review over this stuff and we might but we're not gonna, go back and try and rewrite any of it. I know I like it here me as well over here, um I'm.

B

Not gonna, try and rewrite any of this stuff.

A

But we're gonna focus on the mini column, competition describing that and then maybe get into learning and duty cycles. The duty cycles isn't complete: we've only done active duty cycles. We haven't done overlap duty cycles, yet, which will be both will be necessary, I believe to implement boosting I'm, not quite sure about overlap, duty cycles, I I, know I investigated them a couple years ago, but I'm not certain. Why they're used it's probably, and it's probably for reversing- seems to be the reason, but.

B

There's some interesting visualizations.

A

We can do with the overlap duty cycles and you know similar to the active duty cycle. It's a anyway we're not going to do any coding today or creating diagrams we're just going to try and do pros, but like last time, if we run into situation where we need to update a diagram, I'm, not afraid to go into the code and update it. So this is where we're, where we've gotten to so far and we're going to work on this competition first off and so we'll start. There.

A

Alright, I'm also going to turn on discord voice chat. So you can see me on discord. Sorry hear me on discord.

A

If you don't know the way to get to discord, voice chat, let me copy the link and put it into chat. Alright. So let me let me know who's there. We got five people watching. It looks like so thanks for for joining in we're gonna get right to some technical stuff, and let me know if there's any issues can. Can everyone hear me I just want to make sure that I'm coming through? If someone could say something in chat, if you're watching on the YouTube page, the chat channels like right near by the video and.

A

Otherwise, you can also get on discord and that link that I just posted in chat, and let me know there, there's a live streaming channel or just get into voice chat.

A

Hopefully everything is going well because it's hard for me to tell my control room is much different here than it was on in a twitch. So, let's see I think I can see yeah, okay right. So let's go to the screen. I've got the server running if you've been following along with me, you know what you're, what you're looking.

B

A

If not, there's a github project that you can follow along with this is all the code I'm pushing is being pushed into this project, which you can see right there. Even if you can't see the chat down there, it's called building HTM systems, and this is currently what it looks like. This is the spatial pooling page. This is going to be an interactive tutorial on how to create a spatial Pooler, why it exists, what it's doing, how it's doing it and how it relates to the neurobiology of the neocortex.

A

So we've already talked about many columns, I'm not going to review this stuff. We've got placeholders here for certain things like this is a diagram that doesn't exist yet I'd love to make that happen, but I haven't gotten there. Yet this is the data that we're that's being displayed or being encoded an input into the spatial Pooler, and this is the encoding split up into its parts or all together. Here's the potential pools diagram. Given a mini column, each one has a different potential pool and you can tweak this and change it.

A

We're going to keep it at 85 percent. I've got a little code in here Oh. Actually before we go move on to the mini column, competition we are going to. We are missing something in permanence --is, so we have a description here where we're introducing the term synapses the first time we've talked about synapses in this document as scalar permanence values, that's how we model synapses, but we have not talked about how initial permanence azar created what we barely talked about, how additional permanence is created. We haven't talked about the mechanism we're using.

A

So that's what this distribution here is. This is a normal distribution around a center point, and so that's that's how we want to set up the synapse permanence is we want to choose a center point which I've chosen point five, which we can move around if we want and moves the distribution like so so we have I have some code. That's doing this, given a center point, it will create.

A

It will create this connection. Distribution for each mini column, as you can see, each mini column has a slightly that's randomized, so they all have different initial permanent settings, the more mini columns we get. The more sort of normal this distribution gets so, for example, I should be able to go into our code here and I.

A

Think I have like a size in the state here, the SP size, or do I I might not, but we should be able to control the size of the spatial Pooler. Here's where we're creating it mini column count so I have that set up as a just a global page. Variable I should probably pull that out into a state at some point, but but I won't, but I do want to show you that when I increase this, if we increase this, we probably want to increase the winners, but I'm not going to worry about that.

A

We should see this distribution. Oh wait, wait! It's uh it's! Actually the input size that matters not the minute, so you see the the number of many columns increased here. That's not actually what I wanted to do. What I want to do was increase the size of the input, so I can do that by by increasing the the end values of our encoders here.

A

So, for example, I'll just show I'll just increase the scalar encoder by a factor of 10, and we should be able to see that distribution change in order to do this correctly I'm going to have. This is a little bit of a code. Smell I'm gonna have to go into the combined encoder because it also has is initializing its own encoder, but I'm not too worried about the code smell at the moment. So this should store it. So now our our input space is much bigger.

A

As you can see, the combined encoding is much larger because the scalar space is taking the scalar value is taking up a much larger space- hello Falco. Hopefully you can hear me so I'm, just showing this we're going to talk about permanence --is and the initial distribution of connection permanence Azure, synapse permanence is, and you can see how much more normal. This is when we have a bigger input. Space makes processing. Time goes way.

B

A

We create when we increase the size of the input space, so we we don't want to get too crazy about this, but I could also you know we could double this again and just show you this will slow things down quite a bit, but now we've got a nice normal distribution right around that center point. So I want to show how we're doing this distribution we're using something called a random Bates distribution which and I'll show and I'll talk about.

A

Why we're doing that and we'll write about it to a bit we're sort of outsourcing that so, let's, let's revert this back to what we had before and just make sure that we.

B

Didn't break anything.

A

So we should still basically get the same thing. It's just the distribution isn't quite so smooth. But that's what happens when you have a smaller sample size when you're doing random distributions.

A

So I'm stating here for these diagrams, the connections are initially just establishing a normal distribution around a center point, but I'm not saying how I'm sort of saying why? Because it ensures that synapses are prime to either connect or disconnect quickly when learning, because they're close to the connection threshold. So let's look into some of this code and in the permanence 'iz and this this is actually going to be within.

A

B

A

So let me get that. Let me open that.

A

Open up a version or local version of simple HTML sure I have the most recent copy of it and I. Don't what is have some local changes? I.

A

Was trying to get this all nice, so you guys could actually see it somewhat it's. uh What are my local changes here now I just added some comments, I'm sure I can actually do this. Look at this here too.

A

Let's look at it here because it'll be a lot easier, see.

A

So oh I just added some comments in the tests.

A

I added a test, a whole test here, so man, I'm, I'm, really bad at writing code and my my desktop computer and then not pushing it and then writing the same code in my laptop computer.

A

So what do we have here?

A

We have an assertion so from head. This is what's most recent and head. What have I done? That's different assert, so I've got I've created this expected value, and this is actually the newer thing. This is what I want I think right, so I'm I was just assuring the min and Max were right. So I remember doing this in two places. Now one way it was a little cleaner than the other. Actually let me before I do that the.

A

Yeah we want the well I'm with the locals change the one where I put it into an expected I think that's cleaner. So that's what we want and then here it's I, just added an extra test to make sure that the overlap arrays were matched which seems acceptable to me. Now that we've done that we should, we should run tests again.

A

And make sure nothing that these tests don't run mm-hmm and they they do they just take a little while and then we'll go. Look at our permanent sis code as if I had more than one mind. No I, just am very forgetful. I mean I, have I, think I have less than one mind: I'm super forgetful. Okay. So let's, let's change? What else do we have changed?

A

That's these changes.

A

These are staged to be pushed.

A

Okay, so let me all right right, I was in the middle of a merge. I forgot, so let me merge that okay and then we should be good, get push upstream master I'm, not going to bother with a pull request here.

A

Let's make this a little bigger, so you can see it so we'll leave it at that now we should be back in a good state. Okay, so initial permanence is right. Here are so we've got get permanence --is, but that doesn't mean that we've created them. Yet so here's here's one of the things we need to talk about is this random baits function, the random baits function, I'm using a d3.js version.

A

Random baits here is the code, so I am essentially going to link to it.

A

Random baits right here and I could I could also link to a Bates distribution, but what it? What the Bates distribution allows us to do is specify a density essentially or a a spread for the for the function so that we can control the peak how flat or how peaked this is.

A

So so I think what we'll do in the pros of the spatial polar we don't I, don't know why. I'm looking in permanence ha's pools by the coding spatial, fooling, ok, let's go down to permanence is where we were writing.

A

A

Connections are initially established in a normal distribution around a center point for the initial permanence is the connection threshold should be near the distribution center.

A

This ensures that synapses are primed to either connect or disk and I quickly, sharing a more and sharing more entropy in the initial state of the system. So I should say something here about the Bates distribution. I'm, not I, don't think I want to make a big deal about it like I, don't want to give it its own header heading or anything, because this is just one way to do it. This is not even the way nupoc.

A

Does this I don't even know how nupoc does it I think nupic doesn't use a a distribution it just sort of randomly it does. The important thing is that most of the connections are close to this is the connection threshold and nupoc I believe they're sort of random you know, is the base distribution, something that resembles the biology I'm, not I'm. Not it makes sense that the that there would be a normal distribution I would think around this connection threshold. This is we have to think about. This is just being a starting point.

A

We're sort of bypassing I.

A

Would I would probably say we don't really know but I think it's a clean way to do it, and in that we have to start somewhere in biology.

A

You start as a as a newborn being bright, a newborn mind that learns nothing, or that knows nothing really and has to learn everything. That's not where we want to start from I think we want to.

A

We want to try and start initialize a system that has and we're sort of pretending that it's sort of these, these dendrites axons, whatever have have grown a bit so I'm, not I'm, not so, really sure how I'm not totally sure but I, don't think it matters too much as long as as long as this is this, these connection, these permanence --is are mostly close to the connection threshold, meaning they're they're close to being connected, but we want some of them to be connected already randomly and some of them not to be connected, so we're going to Center them around the connection threshold and create a distribution around them.

A

That's the that's the important thing yeah and if the research comes out we can change it, but but even if it does I'm not sure it's important as long as like. If this were just random random, we could I mean yeah. If this were, if this were just, if we just randomly had all them around 85% of them close to the threshold, it would work the fact that we have this hill.

A

You know this peak, it's not that important, but it's something something Alex Lavin told me: it was probably the best way to do it and he recently commented on the forum about it too. When I mentioned him, so that's what we're gonna use, we're gonna use this Bates distribution, so I'm just gonna, say one. There are many ways.

A

Let's, let's start with that, there are many many ways we might establish: initial permanence 'iz permanence --is, but the I think I've already said that should be near the initial permanence, as the connection threshold should be near the distribution center, but the the important the important.

A

I, don't know, but the important thing I'm not really writing this very well with the the important thing to is to establish most of the permanence is close to the connection threshold.

A

Yeah, most of close to the connect connection, threshold and I've sort of explained that Y above we will use a bait and I'm going to put this link this baits distribution. This is where I can link to Wikipedia a Bates distribution.

A

Okay, which won't allow us which allows the flexibility to choose.

A

Well, if just let's say I wish, which gives us a variable to change the what's, the word I want the intensity of the curve. Let's say at the end of the distribution curve, as you increase the.

A

What do we call it here?

A

What did I call it?

A

The sense know the connection threshold. Oh I, don't even think I have it hooked up. Do I.

A

Connection distribution yeah: this is it's called connection. Distribution.

A

Yeah connection distribution, so as we change and and the what they call this in Bates is independent variables, as you increase the number of independent variables in the Bates equation. Is that the right? That's just a distribution bution, the peak of the curve becomes more prominent, say that and see this in action by changing this value. Here just want to see if this works, because we increase increase this the peak yeah, the higher we get the peak year.

A

It is if we go down to like 6, it's gonna be flat real flat, then we're gonna have the two. It's almost completely flat. One is 0 is like a flat line: oh I, don't even let it go to 0, so hello, lollie, May, nice, to see you as you can see. You show up a chat right here. You guys watching be I'd, be really happy if you, if you gave this video a thumbs up and certainly subscribe. If you subscribe, something will happen on this on the video, your name and lights.

A

So I got that idea from twitch so hit that subscribe button. If you haven't subscribed and I'm pretty sure something like will pop up on the video, a brain, a brain will come brains will come. Ok, so I'm changing I'm gonna put this back to 20 I! Think for today. Oh, that's, really tight, see how ha I see how crazy it is. Isn't it called kurtosis, kurtosis I, don't know kurtosis I've, never heard of that term probability. Theory the measure of tailored miss, oh yeah, that makes sense of a probability.

A

Distribution kurtosis thanks I appreciate that I learned something today. This is why I like live-streaming, because I learned things from the audience kurtosis.

A

So a similar the concepts of skewness, so kurtosis, that's a good thing. Maybe I should maybe I could link to this. If this makes sense, kurtosis of an univariate normal distribution is three cool. Ok, so, like that's great and I, don't think it's set anywhere in here. Yeah.

B

A

Kurtosis awesome so generalize to do so short tail is three.

B

There it works thanks.

A

Mel X for subscribing. Oh, it actually mentions you and Chan I appreciate that whoops whoops whoops whoops, okay. So what I'm really want this to be is 25 the kurtosis.

A

They cut in the bait, stick I'm, not sure this is exactly the same, because in baits they call an independent variable. Maybe I don't want to introduce a new term in this document.

A

Maybe I will I, don't know I like it's good to have a reference. I could also I could also just put see. Also, let's do that in parentheses, see also a href kurtosis.

A

Kurtosis, that's great I, love learning something new see, also kurtosis, okay, okay, so that's how we're establishing our distribution, one of the things I want to show is the actual code to do this. So I scoot it down so the code and create permanence is is right here in the spatial, polar and simple HTM.

A

So we do this. Oh this yeah! This is right. We do this one time up front when the SP is constructed, then that's those are our initial permanence --is from there. We will never do this again unless a new spatial Pooler is constructed, so this has just done once and then those permanence is changed if learning is turned on, if learning is not turned on, they don't change they're, just that's where they're at all the time.

A

So maybe we should say something about that too.

A

Yeah connections are initially established, a normal distribution around a center point. Okay I'll just emphasize this by writing it in in in the next paragraph.

A

So I already said connection established, so we're gonna put some code next and then we'll show the distribution, diagram, I. Think that makes sense. So I'm going to write one more paragraph to explain that this is done when the SP is created, we're going to write the code that is executed when the SP is created and then we'll show the distribution diagram.

A

A

Yeah so I want to cook so code block initial permanence is initial. Permanence values are established once when the spatial Pooler- let's, let's capitalize this, who cooler is initialized.

A

These values will only change if learning is enabled and again more on this later.

A

Below is the logic to use the logic below the logic below uses the D d3.js? Let's, let's like this, a trap, d3 g, JS, j s, bates.

A

What did I call it? Random bates, random bates function, so let's go out. I got this linked here: random Bates function.

A

But let's do this random base.

A

Function: a to establish thresholds, not thresholds, let's just say the values: okay,.

B

A

Then let me put the link in alright, so logic well uses a d3 so now, let's add the code and I'm gonna copy, ok, so here's here's a code example we're going to have to create the code example in another file and keeping the code examples in a different file, and so we will throw this in here. This is going to be code example. Two code example, two establishing initial, let's say: MIT and we'll leave mini column, mini column, initial permanence values using a random Bates distribution.

A

Okay code example to go for the code index at whoops code index at one and now let's go find that that is. Where is our code? Examples.

B

Not in components.

A

A

Hold on I gotta find out where I got them from code. Examples. Example: spatial point: okay: here it is wow that was a place. It was just dense, okay, so we want another code. Example: I might change the way this works, but this is working for me now we're just going to create code example, two we're going to create a string literal and put the code example there and just index it so it'll just be the second one, and now we got to go grab the code example from the actual spatial puller.

A

So all of these code examples are what's running behind the page, so that's something I'm I'm really trying to adhere to so, for example, this this is it get the permanent first. You need the potential pool and- and I will explain this because there's there's a tricky bit to this, and it's that the arrays, the indices of the these arrays, the Rays of the permanence, is the originally permanence array for each mini column matches its potential pool.

A

So you can't depend on using the index of the mini column to access its permanence value, because the permanence values are matched to the potential pools same problem with the potential pools. The potential pool is an array of indices of mini column indices, and so this these permanence is match that they don't they don't logically just count up and they don't match one to one with each mini column, because that's a bit of a waste of space.

A

If you've got a small potential pool, you don't want to store lots and lots of it's basically permanence --is that don't exist. There's there are no permanence is unless that is a part of the index, is a part of the potential pool. Okay. So let's, let's try this and just put this here and then clean this up, so I think we can I think we'll keep this get potential pools. Let's just leave, we won't use this we'll just say get potential pools.

A

This is a code example, so for each.

A

The baits function. Let me look at this again. If I go to this baits function right, we're we're essentially establishing it using a parameter to the SP. That is, that establishes what that crew ptosis value is got a new word. I love having a new word to use so I, don't think I'm going to highlight this I'm just going to essentially say call this baits, we'll call it random baits.

A

So we're gonna call the random baits and this Center value is I think well. Well, we won't talk about that either. All that does is allow us to.

A

A

Move the center of the just, maybe I, should put it in. We want to be able to move the center of the distribution.

A

So if I move the connection threshold up, I might also want to move the center of the distribution up with it, because we want the center of the distribution to be at the in the center of the at the connection threshold.

A

So maybe I will leave that and we'll call this distribution center, because I think that's what I called it. Yeah connection no center of distribution here: okay, establish a mini colonist initial permanence values, permanence values here permanence values using a random Bates distribution. So that's our code example. This is weird that the my diagram is a little bit off, but that's okay! Well, we'll deal with that later.

A

Okay, so get potential pools. So the thing I want to note about this is what I've talked about earlier. Is that this method of creating the permanence --is aligns to the potential pool for each mini column? It's not. It doesn't give you an array back that matches that has space for every single mini column or every single input cell. Excuse me we're talking about one mini column and how it maps to the input.

A

So this function is not going to give you an array that that aligns to the entire input it's only going to align to the potential pool that of this mini column. To that input, which saves space in the long run, it makes the code a bit more complicated, I guess but I think that's. Okay, so I need to explain I, think I, explained random baits and get potential pools. We've already got the code for up here, so assuming that this is how we're getting potential pools.

A

What I do need to explain is the distribution center minus 1/2, and that's because the default distribution center is at the midpoint at 1/2. So if we move it- and you know it's I'm hesitating about this now again- I'm- not sure that I want to explain this I, don't think it needs to be explained.

A

Maybe not, let's see we'll see when we come back, we'll see how confusing it is and if the permanence is over 1. This is just a ceiling and a floor. Basically, oh I guess I can use the JavaScript functions ceiling and floor instead of this.

A

No, no, no, no.

B

This is ok, yeah.

A

This is ok, I'm gonna leave like this. It's simple this way right Falco. You could add that not each input connects to each mini column, just like the brain right.

B

A

Well, not each yeah yeah. That's that's! That's a good way. To put it it's a line to put the potential pools array.

A

Alright, let's try and write some something to that effect.

A

Hey, oh yeah I just noticed the Dmitri guy, who just told me about kurtosis, joined our discord. Thanks for joining and Dimitri, you can join voice chat if you'd like I. Have it open?

A

Let's see: randome, okay, so I I, misspelled, random, random, random.

A

Or where is that random.

A

They're, just random and a base and that didn't that code didn't actually doesn't actually look like code. Does it.

A

Yeah I've got a lot of misspellings everywhere. That's that's! Okay, that stuff will be fixed at some point, ran oh I, guess it is. Okay, that's how it is code. I just was hoping. This was formatted properly. Okay, next paragraph move on to the next paragraph.

A

We've got our code example, okay, and then we want to sort of further explain this. A bit.

A

Okay, the array returned by this function.

A

A

Let's see this function returns an array for each mini column, an array of permanence --is of permanence values for each mini column. Each array.

A

Defines how connected that mini column is toward the input space? These arrays are are not.

A

How did you put it that it does not is not fully? These arrays are not fully, are not indexed or not um do not cover the complete input space. Let's say that these are raised, do not cover the entire input space, but only the mini columns, potential pool and other words do not expect to index these arrays by input space index.

A

A

In order, let's say in order to find the input, indus indices for each permanence index, let's say in input index for each permanence value permanence value.

A

You must go through the potential pool for the the gross through the you must inspect. Let's say you must inspect the many columns potential pool.

A

Which matches the you think I'm over complicating it? This was something that confused David when we were writing this code, so I thought I would be explicit about it. I don't think David's on line because we're not doing real coding today, he jumps in when we're doing coding, not prose so I. Don't know that he's on line, but.

A

Well, if it's over is maybe there's a simpler way, I can say it. I mean the the simple the the crux of it. Is you can't index this by by using the length of the input space you have to go through the potential pool array in order to find the input index for each premise, value must inspected many columns, pinch pool I mean I, don't maybe I can just leave it.

A

Maybe I can just not do the. In other words, maybe that's good enough. I.

A

Can just say to get a permanence about values.

A

Input space so.

A

You must access the many columns.

A

Potential pull something like that.

A

So much Texas not making it clear, yeah well, we'll come we'll come back, look I, said always come back and try and simplify getting something. Ours is good. Okay, so we have this. Oh I should also mention. There's actually I might just put this in the let's just put code comments in for this.

A

Why, today, why did I close that there's my examples? Oh, this is not the right one. Okay, so.

B

Let's just write code examples.

A

Code, examples here and sure this is a permanence must be.

A

Between zero and one simple, right and and I can even say, permanence, arrays, permanence, hermit perma as arrays mash. The potential fool.

A

A

How does that sound.

A

Okay, so we'll leave that there alright, so I'm, not gonna talk about learning yet I'm gonna, take all these values and just kind of move them down. I.

A

Don't know where somewhere down here now we're going to talk about the mini comp, competition, okay, so I need some pros right under the mini con competition to explain what it is, and this is where we'll talk about K winners and introduce the idea of K winners. Maybe K winners, maybe there's a Wikipedia page about it. Yeah winner-take-all, that's what they call it: winter take-off or K winners, winner-take-all.

A

Kay winners takeoff in many practical cases, there's only there's not only a single neuron, which becomes the only active one, but there are exactly K neurons which become active for a fixed number of K yeah. That's exactly we're talking about winner-take-all networks, okay, so competitive learning. This is our n n concept, but.

B

A

We're it's the same thing in special point: okay, K winners take all will say it's.

B

At some point well,.

A

We'll talk about that for now. Let's try and get some pros going for this, not here, but up here many column, competition right here.

A

What happened? I switched files? Oh my okay,.

A

So this is sort of like the crucial part. I. Think of the Kate is just a variable. That's just the variable they use for account. So it's just like the top K. It's just a mad thing. You know.

A

The main thing I want to I want to get across here. What is the? What I want like a one, two sentence, summary of the mini column, competition, so I'm, just gonna like throw out some word salad here, I guess and try it and make sense of it. The important thing is.

A

These mini columns compete to represent the semantics of the input. Okay, many columns.

A

And should I, don't do I have to say I could just say for you for each input many columns come compete to represent the semantics of the input they do. This.

A

By comparing their overlap, scores did I talk about that, yet overlap yeah, no, no, no I haven't talked about overlap. Okay, so I have to thump overlap. I haven't talked about overlap at all, okay, so this may be.

A

This may be another diagram.

A

Because one of the things we might want to show yeah, this may be, and it may be. Maybe I can just do this by splitting up this mini column, competition diagram didn't by comparing their overlap, scores. What I'd love to show here is.

A

For each mini column, if I select, the mini, complement so I'm not sure the winners. Yet so I'll come up with a version of this diagram that doesn't show the winners, but it shows a count of each you and- and this is where a pause is really useful. So, let's, let's, let's also add a pause, I think I have a pause. I have a pause command somewhere a UI element.

A

Where did it go data player, toggle learner where where's the pause, where's the pause.

A

Our today where's my pause button I have a pause, diagrams input here it is player no yeah.

B

Yeah Claire.

A

Data player, that's all of those the state of player, yeah, yeah data player, okay, so this will pause the input.

A

So I'm gonna add that right here as I start talking about mmm many columns.

A

I'm, just gonna put it here for now, because I want to be able to pause it. So it's pause. Okay, so now we're paused.

A

Okay, so before I continue writing this I think I'm gonna update the diagram a bit I'm going to create a version of the mini column, competition that does not show the key winners. Yet it only shows the.

A

Connections that it like emphasizes basically all these connections, these blue dots- it just shows the blue dots. I think this is fine on the right. Maybe we can.

A

Yeah I might update this a bit I sort of want these circles to be maybe I'll make the circle lines dotted. Okay, so I am gonna, go into the diagram a bit. I'm gonna make a version of this that doesn't show the the winners yet okay, so I think I can do that.

A

So let's make this figure four one.

A

And we're going to call this overall Oh overlap, let's call it meaty, column overlap, mini column, overlap.

A

You call them overlap and yeah so, and this competition will keep down here. We might actually have a another one. So what I'm gonna do here is tell it show competition, false and then on this one will say: show competition true and now we'll go into the mini. Comic competition I want to get in there and we'll have a new option: I'm not going to store it. So where is our update function here? We go update, render inputs debase, render competition so in the competition.

A

B

A

Oh okay, so I so I've got this I thought I had. What I really should have here is a completely different renderer that renders just the boxes of the winning many columns in this case I'm not doing that I'm doing them all at once and I'm deciding on the for whether I'm gonna.

A

No that's not right, stroke, where's.

B

The overlaps happening overlap.

A

This is in the mini columns hold on a second. Let me, let me inspect this. Someone I want to dig into this and see what exactly I'm doing here, not that one, let's pause: okay, right here, inspect.

A

Phyllis Oh stroke black stroke with 1.5 yeah, so it's the stroke width is that the only thing a stroke black and stroke with yeah.

B

A

Winner, so that's right, so, okay, so if winners includes so now so really all I have to do is is say. If so, I'm gonna pull out a constant here. Constant show competition.

A

Was this dot prop so competition and we'll just add that to the condition, if show competition and- and then this one same thing, if show competition and winners includes, let me put the extra prints here so now. They should not show up okay, good, not crazy, about this, but I can refactor this later. I'll put it to do fix me. We've refactor out winners into another.

A

Another group, basically, would be another group.

A

Same-Same career, alright, okay, so we're not showing the competition anymore.

A

We're just showing and now I want to I want to go to the circles and I want to make them even less prominent and I'm going to do that by changing these stroke.

A

But still equals none filled. Why my client is fill. This really should be stroke.

A

What is the SBG stroke dotted stroke array, there's something simpler than that? Even.

A

Thought there was something you can simpler than that, maybe not okay, so we can do that we'll do it and we'll just do array it's whatever stroke array, it's from all right, so I'm gonna make them all the same. So we're not going to have a dynamic or a stroke array. It's gonna be two or just I, think that'll work yeah there we go so let's make it even smaller, even one, maybe one two and the stroke width should be pretty small.

A

A

I just want to see where this looks like.

A

This is the actual width and that's pretty small, that's too small, so maybe just maybe one and let's do instead of one. Let's do one four and then they'll be even harder to see you.

A

If you could define what overlap is and pros, and then you know what you want to display in diagram, I'm sort of going to the bat the backwards way, I.

A

Want to show I want to show the overlap and then decide what to write about, because I want to have a count up here. That's one of the things I'm missing is account. This looks awful hold on. This looks bad, maybe one two, that's okay, I guess, Oh. What I don't like is on the full circles.

A

Sorry I'm gonna have to make this dynamic.

A

So I'm gonna have no width if no width.

A

I'm gonna use I'm gonna steal this fill and I'm going to.

A

So stroke with so we're say, with equals default is be zero. Okay, and if it's, if we're connected, then with is gonna, be one.

A

It whoops the opposite of that stroke, there's one if it's yeah the opposite of that. You like the way I, represent the winners and horizontal bar diagrams in HTML videos.

A

Yeah. That's a good point.

A

That's a good point.

A

It could certainly we could certainly do that. We could certainly do that.

A

A

But let's do that's a good point, so we could define what the overlap. What overlap is essentially by by pausing this am I allowing them deposit, select a mini column and then dynamically show what the overlap score is for that mini column somewhere by Counting. You know one, two, three, four: five: six: seven, eight nine ten, eleven twelve thirty! Forty two days ago, Saturday June 1920 its twenty four that one.

A

Yeah, so I want to display that somewhere when you click a mini column, it shows you the overlap, Square and then what's the I mean the heat map is showing.

A

Yeah, that's that's exactly what I'm planning on doing I'm gonna take I'm gonna, just I'm gonna tell them what to do and I'm gonna embed the pause button in there and say press this. Press pause for the data now go click a mini column and then notice the overlap score. The pops up, we're gonna, put the overlap score right in the middle here. So let's, let's do that right now. Let's add the overlap score, so we're gonna say: if, if we're not showing the competition will show the overlap score and then the next one.

A

There's it would be great to have maybe we'll do that in like another diagram down at the bottom: okay, I'm sort of brainstorming about the new diagram that I want, but you're right. That was a good, a good presentation, sort of the stacked you could see what I'd like to be able to do is associate like this mini column. If we, let's say we have a diagram, so I have to think about this a bit because I have limited screen real estate here. I'm I can't make these any wider than this, because I know.

A

There's there's just issues with I want this to be easily embeddable I want it to display on mobile, you know, and so I need to keep these the same width. So whatever I add needs to be this width, so I'm thinking I'll put something under it much in the same way that I put this under the others and I can show that stacked diagram that you said horizontally instead of vertically right, I. Think.

B

That would I think I could.

A

We could make sense of that, or maybe maybe not we're going to play with that, but we'll think about that as we go along, but I do think that's a great idea. We should have that something like that, so you can tell exactly what's going on here. That was a good. That was a good illustration.

A

B

So for right now, let's get this.

A

Let's get the overlap, the overlap number displayed.

A

This selection look, look bad, but I'll deal with that later. I want to display the overlap score right here and we'll do it for both of them. I, don't think that'll be too bad. Okay, so back to the mini column, competition I will create another function, so we've got render input, render potential pools, render connections.

A

Right render connections under mini columns under competition.

A

Okay, input space, so this is going to be outside of this entirely. This dot render overlap score, so I don't have this yet so so we're gonna do this, based on the selected mini column that we're just going to essentially.

A

Render a number on the screen so.

A

Selected mini column should be in here somewhere right, select a mini column, no, no yeah. It should be prop, so we got so. Here's where we get so I need to get the potential pool for the selected mini column, and that will give me the the permanence --is so I need this, for the permanence is okay, so that so there's going to be a pools first and then perms, okay, so const pools equals that constant terms, equal pools.

A

No, no! No! No! That's not yeah.

B

A

I'm confused this dot, props dot permanence is I, don't need to get the pools, I, don't know, I, don't care all I need is the permanence is and I'm just going to do a count. Okay, so Holocaust overlap equals zero and then we're just going to loop over this or each firm, and all we do is if, if firm, is greater than this props connection, threshold overlap, plus plus so now we have the overlap, and now we need to put it somewhere. So.

A

It's sort of between these two, so I'll just put it here. It's going to be a text box.

A

Let's last name overlap label, I'll, just call it overlap, and then we can just simply say take a look at this root. Select this dot root, select the text.

A

I'll put it up here.

A

Overlap text overlap so we're just getting it out of the DOM and then we'll say overlap text text. Is it text text overlap, I'm, not sure this is going to work SVG text this might break.

A

That's, certainly not going to be in the right place at this point, because I haven't placed it anywhere.

A

A

Like d3.js text.

A

Text set text, text, value, change, text, value, something like that text element I know it's something simple: I always have to look this type of stuff up for all you need is to set the inner HTML all right, so so I thought it was just text. I thought you just called text and of any element and it would set the it wasn't. It might be. Html.

A

Either way this is not going to be in the right place, so so, let's let me inspect this and look for it find text.

A

Now, that's finding all these other text bits and the ten should pull this out. I want I.

A

Put them in between these two, so it should be easy to find it's in between mini columns there. This text overlap, 0, 0, 0 0, so it's being set, but it's always set to 0 and it's not really being explained in the right place, but we're gonna put it. Let's set it, let's translate it over.

A

ha White-Space:Nowrap display:block, it should be black it doesn't. It doesn't look like it's showing anything pause, pause pause. This.

A

Yeah, it's not showing it's not showing up. Why is it not showing up it may.

B

Be underneath no.

A

It's not underneath.

A

I am just oh I know why it's I always forget about this text is, is anchored at the bottom left, so I have to move it down. Let me just move it to the right place. I.

A

Can do it here? Let's do it programmatically.

A

A suit of the translation, in which case I, will steal a translation that I have for the competition.

A

Don't I have a translation, that's late there. It is okay, add er er.

A

So get this text will translate it we're gonna, move it down, we'll move it to half and we'll move it down like another half I think the same thing we'll see where, where it lands.

A

Oh okay, fourth whoops wrong one, this one! Fourth, hello, mark brown, alright, so there it is, but I don't know, but I still need to like subtract. I, don't know 40 this.

B

A

To be all sort of custom, look wrong. One I keep I, keep doing my translation on the wrong thing. Let's, let's do that.

A

This should be here.

B

A

Why do I keep putting out in the wrong place.

B

A

Right I just want to display the overlaps core work. Work work before we Sh before we talk about key winners. I want to make sure that it's clear what an overlap score is what we're talking about a mini column, so I'm sort of isolating that part of this diagram, but right now it's not working, which is probably just something simple, I'm missing, I, don't think it'll be hard! Oh it's!

A

This is this bit, so so, let's see what what's wrong with our premises, something's wrong right here, perhaps permanence is for each oh yeah. I forgot I have to go into it.

A

Yeah, so each these are all so I need to get the permanence --is of the selected mini column. This stop props dot, selected mini column. So that's that's. It I.

A

Think, that's all that's wrong for.

A

Each of undefined- oh, it's not select any column, it's selected. Why did it do that? Oh I had a function called select, mini column, I think overlap is read-only. Why would you do that? Of course? It's not. It shouldn't be. Okay, let's see that score change there. We go.

A

That's not right, 71, no I, don't think so.

A

I, don't think so it should be like around 20 or so so. This is way too high. It's probably just an indexing problem. 76.

B

A

This has got to be just an indexing problem.

A

So I'm getting the permanence --is of the selected mini column and for each permanence it's going to be something right here.

A

B

A

Okay, this permanence and the connection threshold. ah That's right! There's no connection threshold. Oh it's I've got to pull this out. So, let's, let's pull this out of this function, scope and set it up right here.

A

Action threshold equals now we'll have now. We don't have to worry about this, but this works better know. What doesn't it really.

A

Where's my function at render overlap, scores above select many columns, but it's not not in this.

B

A

Connection threshold is 0.5 if the permanence is over 0.5 increased the overlap.

B

A

This should increase the overlap. We should have a cup of one. This.

B

A

That looks right. Maybe something didn't get updated properly. No, that's wrong! That's definitely wrong! Is it because I'm not resetting? Oh.

A

This is active duty cycles. That's why I keep screwing this up. Okay, okay,.

A

So start here start here: hey no way how they want so overlap is zero. We go through our permanence --is. How many permanence is do we have for this 128.

A

And they're all right around 0.5.

A

There's one for every way: this isn't this isn't respecting the potential pool.

A

A

I may add this to the watch to watch.

A

Look up 10, you add two watches. Okay, I did wear my watches now not navigator.

A

There there it is okay, there's my watch, so these are my parents's and there's 128 of them, which is it shouldn't, be 128 shouldn't be under 28. It should be less than 128, because that's the potential pool is 85% of 128. The permanence is are what I'm getting from these should all be. There are different sizes.

A

Okay, the selected mini column is what 191 no 190 yeah 191.

A

A

Okay, that seems right.

A

Okay, hold on all I need to do is go to where I'm, rendering the connections and make sure that I'm I'm using the same logic, because obviously I've got something wrong in my head: here's rendering connections where's the data coming from we're calling this stop. Props permanence is selected mini column, we're getting selected mini column from the stuff processor mini column, which is right.

A

Okay, so that's our data on which we draw circles and we are deciding oh, the winners, the winners, no no.

A

If connection threshold and encoding pools- okay, what's this bit I forgot about this? Oh.

A

Right the input bit has to be on the input bit has to be on so I'm, not I'm, not calculating that so I'm just displaying everywhere that there's a possible connection. So this isn't an overlap, I'm not doing the actual overlap. Calculation I'm, just counting all the, but all that all of the the connections that are above the connection threshold I obviously have to also use the encoding.

A

Let's split this down, so I can go down here where I was working. I obviously have to use the encoding okay and and make the decision whether it's on or not and I have to get the pools damn I do it. I do have to get the pools. That's, okay, all right! So we're gonna get the pools.

A

We're gonna need the encoding we're going into the pools.

A

We're going to need to select a mini column.

A

A

All right, selected, mini column and coding potential pools for the selected mini column, and now we can add this bit, which is what we really need to do to decide whether we're going to count it as an overlap, say if the permanence is greater than the connection threshold and the input bit is on that should be it I. Don't know why that was so confusing for me. That's basically the calculation we're doing eyes not defined rights, because I'm not I.

A

A

That's better! That's what I want to see. So if we pause the these should be high 21. This should be 7 1, 2, 3, 4, 5, 6, 7, good 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, good; okay, it's just literally deep yeah, okay, so that's so we're showing the overlap score here.

A

Now and I'll make this look nicer later, I think, but essentially maybe I should okay yeah, let's write. Let's continue! Writing the prose we'll get there all right, close this guy back to the prose back to away from the mini column, competition. Where were we right? Is they do this by comparing their overlap, scores to emphasize that it's a new term.

A

A

Overlaps 4 denotes the how strongly how strongly a mini a mini column matches the input denotes how strongly a mini column matches the current input just learnt digging into yeah.

B

A

Well, the that's that yeah! That's exactly what what I'm planning on doing work.

A

And it's funny because in my head that's I mean it makes total sense I, just in the code, I disconnected and didn't realize. Oh obviously, I have to it's not just the potential connections. It's the ones that overlap the current input. It's right there in the code, an overlap, score denotes how strongly mini column matches the current input and the diagram below.

A

Let's, let's I'm gonna I'm gonna ask them to pause the data press. The pause button pause button loop and inspect the diagram below by selecting many columns in the Left chart.

A

Some reading over your shoulder we'll have to get that same hand-holding.

A

Well, let's see where I go with this and you tell me if I'm, if I don't, if I don't go the direction, you think I should go. Oh, oh I! Don't want that to break up like that I'm gonna fix that it should be easy and components, input play player.

A

Okay, so I don't want this to be a div I want it to be a span I.

A

Hope that works- oh, my god, whoops come on come on now. I think this is probably because my CSS is.

A

Looking for a div player.

A

Present because you can't give a span of width, this is not what I wanted.

A

Span class player yeah, so so these SPG buttons, oh crap,.

B

A

Okay, I'm, not gonna I'm, not gonna, I'm, not gonna mess with this I'm gonna put it back because apparently this is dependent. These polygon points are dependent on being inside of a block component.

A

So I'm gonna leave this and I'll just make a note to try and fix this.

A

Well, it'll be pretty obvious. I think that it's not what we want rust is pause, button and inspect the diagram below by selecting it. Many columns in the Left chart pause pause, select as you select different columns, the let's I'll say the the redder.

A

Many columns have more overlap with the current input value and the green many columns as you.

B

A

Around the space notice, the overlap score again, emphasis overlap, overlap, score.

A

Changing this is the value of the current.

A

Permanence --is permanence --is permit notices.

A

That I want to say connections. These are the connected. Synapses I've already explained that these this is the value of this is the number so the number of connected synapses, okay, which means permanence, is above the connection threshold, which has been explained for previously, that's yeah, that's what I'm doing I'm, explaining the overlap score. Definitely, that was the point of this whole thing is to explain the overlap. Score is the number of connected connected synapses that overlap the current input.

A

The current overlap, the on bits in the input space at this time, step.

A

So you click through the account that you can verify this score. I'm at you can verify. This score is correct by counting the number of solid blue circles in the input space notice, they are all on top of the a gray input box which represents an on bit.

A

Okay, yeah overlaps, a verb in American English I mean to overlap. Something is to be on top of it or to like, if, like a Venn diagram, when you have two circles, they're overlapping.

A

You know with there's an overlap where the circles are both covering the same space if it's a common term in English overlap like if you put two blankets on top of a bed where they both covered the same space would be where they overlap.

A

Okay, this is the number notice the overlap, score, changing and I'm gonna bet, I'm, gonna, better denote this score, I'm gonna label on it in the diagram. This is the number of connected synapses that overlap the on bits, change that overlap the on bits.

A

Connect the synapses that overlap the on bits.

A

On this, in the input space at this time step, you can verify the scores correct deposit again, you can verify the score is correct. By counting the number of solid blue circles in the input space notice, they are all on top of a a gray input box, which represents an on bit.

A

A

So connected synapses that do not overlap the current input are not counted in the overlap score, obviously right, but I think it's okay to restate this I want to I really want to fix this. So I can embed this. This pause button inside of the text I'm not sure, if that's possible, with with it being an SVG but I, wouldn't be against changing it.

A

A

Okay, so now the next thing to explain is that these, these overlap scores are what we compare to decide which columns represent the data.

A

You know I left the current infrared, not counted connected synapses that do not overlap the empty circles. The empties, you know the empty circles did not overlap. Okay, you're just saying put Lefty current input empty circles that make sense are not counted in the overlap, score.

A

A

A

Alright, so that so the this next diagram, I'm gonna defer because I do like the idea of showing a stack, a ranking.

A

So that would be the creation of another diagram, so I might put a placeholder in for that stack, ranking and then the ideally, as you select one of these, the mini columns in the stack ranking that becomes the selected mini column and all the other ones update. So you can tell you, can associate this one at the top of the stack. Is this mini column?

A

So that's a that's exciting to do that diagram up, I'm, looking forward to making that, but let's put a stub in for that before this one there's going to be a stub, and this is going to be figure forth, wait that was figure where.

A

For one right, this is gonna be for three.

A

This is right. That's the one I want to keep, and so we're going to put a stub here. It's gonna be for two and we're gonna call this stack rank or something like that.

A

It's not going to be a mini column, competition. All this stuff, I'm, just gonna, pick that out and say diagram, stub, I.

A

A

And ports diagram diagram stuff from opponents diagrams diagram, stove.

A

Okay, there we go permanence is medical competition, diagram stub, that okay minute call them, and then let's down here, I, don't know what this is gonna be like, but I definitely know, there's gonna be a selected mini column coming out of it to.

A

Stack ranking of mini columns by overlaps, poor! That's what that's! What that's gonna be.

A

Why did I call this minute? Column stack, rank overlap, it's supposed to just be called stack rank. Okay, so assuming that that exists, we need to introduce it.

A

Here is another view of the many columns they columns, ordered ordered by their overlap, scores those with the those with higher overlap, scores are and instead of being up and down. This is going to be left and right, I think so we'll say closer to the left. So let's do, let's do left and then go down. We'll have the the highest ones are the highest ones at the left, left left of the diagram and.

A

Yeah um left of the diagram during the the mini column, yeah I, should be clear when we get the diagram competition.

A

During the competition say, a state competition, many columns with the highest overlap scores should represent the.

A

The the input data or this time step so just to say brickwork- should represent the input data to choose the winners of the competition competition.

A

Fireworks, we simply.

A

A

Simply choose we three choose how many.

A

I'm trying to say Kay, you know we decide. Kay I've talked about Kay I'm talking about K winners, yet yeah it'd be fifth of July man. The fireworks were nuts last night near my house. There's these giant signs everywhere. That say no fireworks thousand dollar fine for fireworks and there must have been 50 people shooting off fireworks and nobody cared okay. So to choose the winners of the competition we sent, we must decide, we decide how many.

A

Let's just say, we decide how many many columns we want to represent the data and simply cut off chit and simply choose that amount.

A

How do I decide how many many columns we want to represent the data and I mean what I want to say? Is we just like cut off the stack at that point and I? Don't maybe it's simply? Maybe that's what we do. What we do we cut out, their remaining mini cut, cut the stack at that point, and this should be clear from the diagram, because we'll have first of all, we'll have a K, and so that's um we'll be able to have a K and we can move it back and forth.

A

So add that in.

A

I'll just I'll say in machine learning terms. This is called a.

A

K winners take all operation and I'll link that to or was it winner-take-all here we go, K winners take all operation.

A

Let's link it to aah.

A

Caylor's take all operation.

A

We can easily control the sparsity of this new representation by changing okay, okay, so so there's also something that we want to change. We've got winter count here.

A

And I'm not using it for anything, but we should introduce something that changes this winter count and make it a state so that it can be changed. So, let's.

B

Do that real, quick.

A

We're gonna make it a number value and we'll call it k winter count or something like that.

A

We'll put it here.

A

So, let's call this K winter account number value, k, winners, low, let's at least at least, have to have I, don't know, 10 I, don't know, let's okay, 1 and we'll make the high I mean it can't be bigger than the imp account. I, don't even know what that is. So, let's just make it a hundred I, don't know and we'll step it at 1, which we don't need to do anything for. We might change this at some point and we'll call this K winner account.

A

That's the state, so the set state.

A

Okay, we're countin value; okay, so first of all, I'm going to change this to K winner account and now I'm going to add it to the state here, put it under permanence. Okay, we're count.

A

20 get rid of this that everywhere we have K. Whenever can't we have to put, we have to use the state, this state dot.

A

There's another one: that's already got it, that's it okay! So now we should be able to use this key winner count to change. This is where I love react.

A

So now we can add this easily control a sparse patient by changing K. Try changing.

A

Okay, here, okay Twitter account.

A

See if it works, try changing K here. Did you do? Yes, it does? No it doesn't. It's not working. I know why I think.

A

So when we're creating this mini column, competition I think it might be. Oh this state that winners- that's we've already got winners.

A

How are we getting this.

A

Winners, undefined winners: how are we getting winners? How are we setting that? Oh, no, that's! That's the actual winners, not the key winner count. That's the actual winners.

A

So how are we specifying to the mini column, competition.

A

In the right place, yeah overlaps winners: oh we're we're we're calculating the winners.

A

Or calling compete so when we create the SP initialized spatial polar sized input count extra threshold winter count, winter count there. It is state kate, winter count.

A

Oh I think I know why. Okay so I have to have a in in the component. Did update I'm not always initializing the spatial Pooler I'm only initializing the spatial puller. If the connection threshold changes I, don't think I I, don't think I need to reinitialize a spatial polar if K changes. All I really need to do is update the option so so.

A

Winners come so before, so, if there's no SP, I'll, initialize otherwise, I'll say this: SP ops, dot, K, Twitter, County!

A

Let's go look at this bishop puller and see how its deciding how many winners.

A

Calculate overlap, there's the winners, winter count; okay, it's just winter count, so I should be able to this is this is a little bit inappropriate, intimacy fix me and appropriate intimacy.

A

This SP, the ops winter count, equals the state dot.

A

K winter count but I think it'll work.

A

I can't tell is it working? Is there only 7? Is there one if I do this is or one yeah? Okay? So that's working great all right, so we can change the K winners. Good good.

A

So now we only have eight and they're the very highest the highest of the highest overlaps, but there's a tiebreaking problem here we haven't really talked about tiebreaking yet, but there is a problem with tiebreaking here, but I'm not going to get into that. Quite yet, we'll probably talk about tiebreaking well, I mean we have to at some point I think it's probably probably important enough right now, it's doing basically random tiebreaking, so I'm, not gonna, mention it all right. Here's another view of the many columns ordered by their overlapped scores.

A

Those with higher overlap scores are at the left of the diagram during the competition main column, so the highest overlap. Scores should represent the input data to choose the winners of the competition. We decide how many many columns we want to represent the data and cut the stack at that point in machine learning terms. This is called a K where's take all operation. We can easily control the sparsity of the new representation by changing a K all right, okay, guys I'm gonna wrap it up.

A

Now it's almost three o'clock and my throat started hurt from talking. So, let's start a review of this code and see what we've done and where we're at so first of all, I, don't know why this image is here. So, let's take it out. I know why I know why it's there I just shouldn't, be there I see you've mark brown so on our spatial pooler's page we've added a diagram. Stub we've extracted winter count from a global page variable into a state page variable.

A

We've also added some inappropriate intimacy with our spatial polar by setting it's winter. It's a winter count without a setter.

A

This is still the winter count. We added a number scrubber to change the Kate winter count, and then we added some some pros here. A code example for permanent establishing mini column, permanence values, yeah permits values, and then we started on the mini con competition and broke it out into several different diagrams, one of which we haven't created yet so before we do before we go on. Let's go and create a ticket for this, oh Jesus, on every what I want to do. I accidentally opened every tab in there.

A

Okay, so looking at our projects, excuse me figure. Captions right pros is what I'm doing still have to do. Those don't split connections on proneness diagram, initially, I made a fix that okay, but let's add this so create new new diagram to show stack, ranking of many many columns by overlaps or all right and I'm gonna turn us directly into an issue or it's an issue stage that it's an important thing to do, and.

A

Let's add the right labels, this will be an enhancement, it's gonna be a d3.

A

Okay, so I got that rid of this. This, for these links got these links taken care of okay back here: okay, mini-com competition, firetruck, sorry, I missed it.

A

We add a new function called render overlap score and we changed some of the circle. Strokes I changed the name of this one because it wasn't right and then we changed the circle stroking.

A

We added a an option to show competition or not, and then our actual renderer overlap score.

A

This is a bit inefficient because we're calculating these overlap, scores twice, we're doing it here and render overlap score and we're doing it in in the mini columns. But so I could add a fix me for that to.

A

Inefficient because we're already count you waiting overlaps.

A

Elsewhere at that, and that's where the text element is for the overlap that looks good to me and then we added a new code example that all looks good, okay, filling out many column, competition prose and adjusting diagrams I. Don't really care that we're over the limit pushing it.

A

And here we go not simple. Htm get push up stream master.

A

Already, oh spaceboy playing soon, you know I'll, try it Amaro yeah I'll! Do it tomorrow, I'll be on twitch tomorrow, on my other account we'll do a little guitar practice, I've been doing chord, progressions, and so maybe we'll do some chord progressions the stuff. Okay, oh, if you think of a better way to explain the K winners. This is all a draft really and I'm totally open to suggestions.

A

Tour de France starts from your town. Are you gonna go watch it that sounds fun. Do you want to see my new toy? This I got like the extra-large stream deck. Look at all my icons, so that's fun, I, just I just started setting it up. It's a whole lot. Better cuz I was kept I kept flipping in between screens to do things, and now I can do everything on one screen. So that's nice, so.

B

A

I am going to have an excellent weekend. I hope all of you have an excellent weekend. I could play the piano with that. I absolutely could I could set up each each button to play a different tone. It wouldn't be very efficient, but I've got this.

A

Nothing came out sounding okay that doesn't work. It's easy to easy to I still.

B

Have many more buttons I can add.

A

So we'll see we'll see what happens, but the important thing is done. Important thing: it's definitely the cow sound and once I get the sounds hooked up so I the chat bot. As you know, it doesn't work at all. It's not hooked up at all. It's a totally different API than twitch, but I found the tutorials to get it. I know. I can get it working and have it do everything that it did before and I will add a cow sound. So you can do you know: bang sound cow anytime.

A

You want falco, you can make the cow sound I'd be like Christmas every day, thanks for joining everybody, if you're watching, please like the video and subscribe to the channel I, would greatly appreciate that and I will be back with a live stream. Monday research meeting livestream on Monday in the meantime, I'm going to be working on thumbnails.

A

So you look at the week the YouTube channel lots of lots of new fancy, thumbnails I'm, going to keep working on that, because if people like to click on nice-looking thumbnails for sure alright I'm going to press this button on the stream, deck and I and if it works, the stream is going to stop so we'll see and I'll, channel and and everything will be done so take care. Everybody have a great weekend.