DevoWorm Lab Meetings, 24 Feb 2020

Previous Meeting Next Meeting

⏯

youtube image

►

From YouTube: DevoWorm (2020, Meeting 7): Morphozoic, Morphognosis, and Cellular Automata

Description

DevoWorm meeting: February 24, 2020. Attendees: Richard Gordon, Vinay Varma, Devansh Batra, Thomas Portegys, Ujjwal Singh, Bradly Alicea, Yash Patel, and Jesse Parent

A

B

B

B

Wait for a few more people here.

B

Wait another minute or so.

B

Okay, welcome to the meeting today hope everyone had a good week. I was talking to Richard before the meeting and he said he just finished his the paper that he presented last week. So I don't know if he wants me to distribute it to the group at some point, but so will still be discussing that you know in subsequent meetings, maybe at the end of this meeting.

B

If anyone had any questions or comments, they're thinking about from that presentation, thanks again for the presentation last week this week, we're gonna turn to Tom Portage's who's been a member of the group for many years and he's gonna present on his his he's doing a lot of simulations with cellular, automata and bio-inspired modeling, and so before we get to that. I wanted to share our paper. I, don't know! Maybe time we'll talk about this paper in the in the hello.

B

It's a paper, a new paper on growing cellular automata. So let me share my screen. This just came out recently in.

B

A journal called the still and for those who aren't familiar with the still it's a machine learning journal. That's you know at the present things not PDF format, but they present them in this interactive format. So it's an actual journal where people publish these interactive pieces. So let's, let's talk about this for a couple minutes, so this is a paper called growing neural cellular automata, it's called the subtitle is differentiable models of morphogenesis, and so this this Journal distill is actually a machine learning journals.

B

So this is a little bit different than what they usually publish. They usually publish things in more mainstream machine learning, but this is a morphogen morphic, genetic approach to complexity and the authors here. A couple of authors like eleven is the last author on this paper and he's actually well known in the developmental biology and morphogenesis community. So this is the paper I'll put a link to it in the chat.

B

Ok, yeah, if I'm says distill is cool this. It is ok, so that's the link, and so this is the paper. So it starts off with this animation. So the way this works is that you can write. Let's start over, you can set the speed. You can set your faint your target shape, so you can start, maybe with a a gecko here or a lizard.

B

You can start with a smiley face, a human eyeball, a fish, a Christmas tree, a pretzel I mean they're, trying to be cute, but they're also trying to cover a lot of different shapes. Well. Why don't we settle on this butterfly, so you can settle on this target morphology and the idea is that you're gonna take this cluster of pixels and you're gonna run a simulation that forms this morphology, and so, if we go back, we reset it and it's starting to grow at a very slow speed.

B

We can speed it up a little bit more. So it's a half speed and you get this butterfly and it's kind of pixelated, but you can see the process here. So let's turn over butterfly from a little cluster of pixels, so there are different types of also there different types of models growing.

B

B

And regenerating and so they're described down here, these different types of experiments but they're all basically very similar in terms of their outcomes.

B

C

One that's what.

B

C

B

C

Do if you don't do too much.

B

Yeah, so that's that's the regenerating regenerating actually has like where you can cut it, and then it reforms. So what? How does this do? How does this work? So this is actually you can try this in a collab notebook for those of you are interested in that. So if you want to download the notebook, it gives you the code and everything. So how does it work and then they'd so in the paper they get into like how this works?

B

So you get a description of what you know morphogenesis and that it's an example of self-organization, so they're using cells as the building blocks of these bodies and they're using rules and those rules are very similar to what you find in a cellular automata and they walk through the model here. So here's the model where they have a number of different steps in the model. They actually is a pretty advanced model and it's actually more than just a cellular automata.

B

There's a lot of machine learning involved in this as well a lot of encoding and decoding of things, and so that's I mean I'm not going to go over that right. Now, but you can read about that, and then they have a way to determine the cell state. They have your cellular automata rules and yeah. They kind of walk through that, and then they have their different experiments that they profile in this article, so learning to grow experiment.

B

One experiment, two is what persists exists and then experiment, 3 is learning to regenerate, and so they kind of walk through all of this yeah. Oh there's an experiment for rotating the perceptive field, so each of these cells, I, guess, are perceiving things in their environment and they're, responding to it. So Michael evan has actually written a lot about decision-making in cells and so he's interested in that area. It's they kind of fit feeds into this work as well, so related work.

B

He talks about PD es which are partial differential equations and their role in this process, now all networks and self-organization and swarm robotics. So this is again. This is probably going to be of interest to a lot of people in this group. I would go through it and maybe if someone wants in those times gonna talk about in this talk, maybe someone could present it on its own because it probably deserves that kind of attention.

B

But I just want to point that article out and so it that sets up kind of like tom's talk so tom. If you're ready, can you share your screen.

C

Okay, so thanks for presenting it rather I was gonna mention a little detail, but that's great, but that is still venue looks really cool I. Think I'm gonna probably submit my simulation to that and see how it goes. Yeah, so he's got some. You know put something more than.

C

Okay, so what is hopefully just disability overview of a couple projects.

A

On with more from more facility which gradually.

C

You know addiction, Stevie Brule gave you up as Chloe your kind of few years ago and.

A

It's a morphogenesis model.

C

I'm not gonna, go I've got a couple demos with it and no one needs you gonna, be here, but I'm not gonna. Do everyone in these slides, so I'm just gonna kind of go over view level so and then, with some demos. So everybody sees okay.

A

C

It's it's a longer wise. You know that sort of player of what you just saw there, where you have various objects, kind of growing into other shapes. So what this does? Is it a set of rules? If basically, the way it works is you can enhance of the pinyin morphogenesis process and more facade, watches that and henna developed some of their comic-con rules and using those rules it can actually recruit the more colorful genesis process and you can you can you can even feed.

D

Those rules into a neural network or control network in a chimera, so you can have a nice compact, fast version.

C

Of it, which is also very nice for like dealing with noise- and things like that, so we wanted something it's at comic-con.

A

But it also embodies its computational feasible.

C

What you don't want any of it, is without our comic-con and get this explosion of bits. If you try to capture too much, maybe good information, so morph razajin way to deal with that. Basically aggregates stuff, that's following spadix, so let me go to the picture. Your pelvis is better.

C

What would cheer okay?

C

They don't have an interior picture. Okay,.

C

So go back up here, so here's the cell has a stage. This is standard shower time about stuff it amid senses.

A

Reacts to signals signals carrier.

C

Information about stating into excel and appealed as the confluence of signals, since I set up in the dark spot over the years so.

C

You wanna get a picture, this okay, here's a picture so like you might.

E

Have change that looks like this on.

C

A graded and it has different cells in different states and the way this works is you have a basically a pyramid of expanding in space neighborhoods, so you can have an immediate one which is like the morning, rod which is 3, 2 3, and then that would then have a bunch of a few neighborhoods in a neighborhood. But it's actually pretty good trading. Exactly it's just bigger, and this is the aggregation speeds. You don't actually get this effeminate Oriole explode from using the kind of a histogram cell type.

C

Each one of the cells has a different state, so you can educate those at definitive, histogram or as I'm in the oven, now adays the concept of a centroid back here in each of these sectors. Here of a bigger, larger.

C

Life seeking stacking anyone see, it is kind of clear it. So basically, never context so I saw has as well like can have an over pair larger context and what they love it to do is determine what to do so.

C

That context is called the.

C

More full mistake and the southern thing more fun, I think in a meta mark as part of a metaphor and Marvin a state tells the minimum what what is the action of the cell, so these cell could do like change state essentially and here's what you can do with the I told you could do like a machine, their network.

C

So what you can do is: okay, you put ER in the neighborhood of a cell and then you and then you output, the action which is to whip the cell, how the cell to change day- and this turns out to be very angry because these rules can get in each other's roles.

C

So let me do a little demo at this point. I think that's the best thing to do which a lady, okay.

C

So a couple things you can do is.

C

Okay, let's data, as you saw with the 1500 stove, you can have a repair sort of functionality. Let's see if I can do with more for no more bizarre along the same line.

C

Since this is this, sort of atheists are now infamous vision of images.

C

Called the lena picture which people Playboy, which is now not fully correct, but we then wait, but so what.

A

You got here is kind.

C

Of like a edge detection, sketch of the image and Martha's art is taught that given in this sketch, usually to some degree, so let's see what it does pretty good. Okay,.

C

So it took the edges, it is the starting stage and each one of those cells said Oh. What should I do? Look at my neighbors and over time it develops. If you kind of see a picture here, it developed it actually created. The imaged I have another one, which is a terrine.

C

There's a thing, is you know the lute or any famous reaction diffusion equations. So, let's see what they apply to create patterns.

C

He is only gonna, take swell sprinting away.

C

And I could get the thing going on my computer, you know country okay, so what this does is it takes?

C

The transmission diffusion takes an arbitrarily random bunch of pixels or cell States, and if you apply the ration, diffusion and certain parameters, if you change the parity to get the patterns, but so this is one of the primary centers.

C

Seriously, the cells start changing states.

C

You have started coalescing.

C

This is a so-called muttering spot pad.

C

If you've ever seen this, but you can have lots of the competitors strikes all finished up all from a pair of ladies differential equations. So.

C

The cells are primitive, call the singing. Oh.

C

F

So what you're actually seeing here.

C

I wonder how this looked a little cracker than it? Should it okay, so this is actually the work was bizarre after it has learned how to do Eagle upper pattern by watching the Turing reaction. You diffusion equations that work, and you can see, comes up with the sort of it will come and get better and better, although it could get even more better if I play with it tomorrow, you can.

A

See him two dots.

C

Here are going to us, so it's learning it.

A

Has learned to generate the.

C

The Spotted Pig, so, let's see if I, can actually show you the real toy piggy to learn from.

C

That will be this one, so here again we scared a bunch of.

C

Yourself, a nice initial information, because it's from totally.

C

C

You see the episode watch this and then it did its own thing. It's learned rules to build this all these igniter. Ok, so here are the Leopards passed.

C

Okay and that's that's.

A

All I want to show you for demos, resort.

C

So, let's see juice, we've also done a couple of things like the paper has.

C

How many life cell regeneration evolution of very, very rudimentary calculation sequence, which is an embryo? Is this I'm sure you know more about this and I'm, not a biologist and are they are machine learning person, but I have interested in computational biology? So it's like the cancellation is where this, where you have a embryo in it like is this.

C

It is this portion of the beginnings of to just attract it's actually one. It could also over those a.

C

Which is something you have when in brains are developing like energy talk together, so they can talk to each other and just saw turns reaction, division, morphogenesis, so the primaries in your life. It can watch a any wife doing its thing.

C

It's a toda painting, so that comment I'm forming opens and it figures to do all these interesting things and it can watch those and figure out what the rules are. So can you create that it can? Regenerate cells is just kind of a beginning sort of do.

C

You need you saw this with the Lina picture. You can learn to generate a whole image from like her rough sketches relation. We have shown what it wants, what to do in many festivals visit the escalation super simple. This thing it starts out of the square which is in I think this cream. Each one does and oh we're finding we're neuron will send out exons to target Redis, and if you wanted to do that again and okay, so that's pretty much what I want to say about MorphOS? Oh, so that's the technique that it uses.

C

So, let's go back to the. Let me show you up all the projects, so they would kind of hamper this.

C

The next one is a plumber fish. So this was a little moving.

C

This is a puffer fish, but there's a certain kind of official lives off the coast of Japan and people found it to do these amazing buildings. Amazing nests, which looks like this thing so slow critter. Does this nest.

A

C

A

Floor and that's the mail of dunces.

C

And it had all these it's kind of a moon shape and at a central area which is very fine and ground, so in there and natural things this is just the bee's knees. It's the most amazing can be seen so I thought. So this.

A

Versus Projekt RED sort of angle.

C

This is I, wanted an animal behavior and not just more code notices. The most.

A

Bizarre, if you thought it's.

C

A

Like something that's.

C

Sort of static- it's dynamic, that's on space, but animals do things in time, so this behavior is Federer goes over time. It changes in the the fish is changing location and it's moving on and time and so I developed this kind of a dated sister called muffled noises, I like to come up with names. It's.

A

A little bit of a sense.

C

More venosus me tease the shape of knob and I'd call it the shape of nitrogen spaces. Higher and I chose not only time but also space, because, as you might be wary mammals, well, someone could a lot of animals. Mittens are one of them. I, don't know a lot of other animals besides animals, but we have these special structures and their brains called root cells and there's other ones called play. Cells which are specifically wired to do spatial geometry processing, so her name is Randall navigate.

C

Then I take a gauge of the physics of the world that has a tool or cleaning geometry. If you're to be a German on a flat surface and use that, as you know, so it's his stuff, that's wired, to view a lot to leverage the fact that world the world is a special place as well as temporal place, because most now, no letters. No it's just the temple essentially Alesi at your current normal looks that I'm interested in it. So here's ten a picture does see any brain. Behavior again.

C

Penguin episode, they're taught fools from the behavior, because I watched you behavior half an inch on those rules of Illinois.

A

Can you come up with the producers of the area.

A

That is a cone at.

C

All because it's.

A

Painted, like a light, calm sort.

C

Of thing, we're thinking in the past can be far away bargain far away so yeah against the dirt up on the top of the cone. We have things are very recent or present right now help Colonel president and Venice.

C

It's gonna be way more.

C

Extended also in space they can be so this provides a kind of context for controlling behavior and, once again, when I did some penetrate to avoid the commentary. Origin, which is the aggregation trick, has gotta be some other.

A

C

Which an exploring using multiple.

A

Centroids but I haven't done that yeah at.

C

Some point I well so here's the a couple equations that describe how many these meteorites are constructed in space and time. So you can see another picture. You just use this other account in here. Here's a three by three and there's two days.

C

So you and histogram or a centroid other that's feature so that they haven't been there chunk of space-time and okay, don't say thing plug, listen to it now in our open nor minute thanks, you get you concisely, because you get to the fuzzy, be ability to get noticed. So, let's go on to a demo of this next.

C

This is a nest: okay and I when I submitted this for publication. Someone else, just just before that said, submitted a very, very nice puffer fish nest. I mean makes a really cool like and I'm, just like the real one, and so so that's not a.

A

Very nice well I'm not really trying to actually.

C

Build a nation that I'm trying to study the behavior or something that does something interesting and his nest building is entertaining. But the.

A

One that was really nice is actually encoded.

C

So I'm not interested in there I'm interested in some kind of generalized learning here so I shouldn't get further, but eventually got a colorful tepee.

C

Okay, I'll watch the pufferfish good thing.

C

So there was a negative.

A

Beta media nest more.

C

Ferocious watches the fish bill says, and then he built up these rules and.

A

C

It during order to execute the rules, so let's see what it does. Okay, so this red triangle in the middle is the fish and the fish can actually see the elevations. So this.

A

Fish actually wants to kind of scrape off the elevations.

C

That get them all looking like that wrong nest, so you see these three cells in front of it. It's to the elevation 644 unnaturally, that's.

A

Actually, what it's looking at and then it's responding.

C

With just a serger sitting here for dinner, it also uses the previous response and turns out it's actually good to know your previous response.

A

Is to determine your next responses.

C

So, let's have it kind of step along here and we'll. Let it go a little bit so now see.

A

What it's doing now is kind of plowing.

C

Up flatten out the area he, and so both plows out this nice little central area, which is square because it's as you know, grid and that's essentially sort of you'll see it kind of looking like a geisha on a little factor here.

C

But it is the it is.

A

To keep track of all its context like where it is when.

C

A

C

And that should more pronounced Asafa today.

C

Okay, it kinda looks like.

C

This is not the no luck this is, they didn't have to be a beginner to deployment. This is fairly gentle. Oh no! No.

C

Okay, then we'll.

G

Just let me finish it.

C

F

Second ago, better, okay,.

C

All right, so it means something it looks headless. The mess head is Kanab.

A

We sort of circular thingy so.

C

That's my version of the nest on a cellular, Tata.

C

Okay, so I did that last year and this year, I'm working on something called.

C

Again, more for notices using another now this is really interesting. Behavior and I'm, not saying I'm, actually telling you anybody about how about me beats work, but a honeybee he's actually did this thing where they, yes, I, can show ya.

C

Okay, other time did you think my reader.

C

Honeybees amazing behavior, where they go out and they buy, you know, gather the nectar and pollen and I. Don't know I'm. Just saying I, don't know, I just simplifying things. Okay, so they'll find nectar.

A

C

Flowers and they'll bring back alive and if they know so once they know where nectar is, they need is danced.

A

C

Hide called the Llano dance and the dance has two components, so it tells the other bees which direction the nectar is, and it's.

A

Relative to the Sun and.

C

I'm not doing this on because we don't have a sign in our toilet on fire. So it's just going to do today, making mental lamb, which is more than any bees, actually do smaller than anything, but it also does so. The direction is of its the ants, those which direction the beef should go and then the length of this central wiggle-waggle. Thank you cuz, you know her go and then the bees go fly off and.

A

C

You know, hopefully by my nectar and they're, doing back Alice. It does another dance but I'm interested in just the one kind of behavior. So let's look at a little video here, which is me talking about other thing works.

C

Okay, so what you're gonna see so we're gonna B's, here's a diving little well! Let me show another video.

A

A

A

C

C

This task is very hard for a conventional, normal heart to do unless it's given him elicits. You know the potentially so much to start like compromises so, for example, like a very popular recurrent Network, which called long short-term memory, but if you try to get a long trip in memory to serve dead reckoning navigation, to figure out to keep track where the hive is so when it does blunder on an exterior, it immediately gets lost, I mean lsdm that were clearly really really powerful, but they can handle this very well and I.

C

Had my researcher, she seems to point my tractor and I've actually run this I saw his brother, Cody I had felt this, and indeed he gets the case. So you need some kind of help you need. Some kind of animals have the same where they actually have some emotions, more determination of space, and that's what you need to, because this beauty and just a general note this is kind of where I'm at is animals.

C

Do these kind of things that you know we just don't seem to explode at well, another just animate, so thoughtful that they did. Is fascinating even is. It is just stomped artificial, neural networks, as they come out of a box to.

A

C

We need to do we're kind of animal behavior, because you know we have all these things felt. It was yeah. You know amped up to do the ink level so hey. Oh, she is do more animal behavior, okay, so the honeybee is the moving paper in just finished a basis point.

C

It's quite an alternative, so it's basically kinda like the puffer fish with this other stuff going on. Okay and you think it's probably you get up and you got all my webpage.

C

You can find this stuff here. Putting the video.

C

C

B

Well, thank you for that. That's very good and I'm sure we have a lot of questions about what you've been doing and I I, especially like the comment about the neural networks being in you know, unable to do certain things that you know we people talk about like there's this debate about how neural networks are like the brain or not like the brain or how its you know, able to generate intelligent behavior.

B

But you know these are like very specific things that these models are being trained to do so, like you know, people talk about like how artificial intelligence can play jeopardy and win, but it's a very specific type of task that they're doing, and you know, there's a lot more to behavior than just like you know. A narrow set of you know, like maybe an expert system type of croch or some sort of like you know, a pattern.

B

Recognition approach, so I think that you're bringing that out quite well in terms of like how that you know what the shortcomings are of conventional techniques.

A

Of surprises constantly or any good things that we did, you know where they are available.

C

I mean I was given soda in general, so and you know, as you said, conventional.

E

Others, like their planning, you go, we.

C

Don't have like the Gerda notice in.

E

Berea place.

C

But you're like oh my gosh, your burger, you know basically eat better run.

F

C

A

So they're super powerful in the very narrow, very.

C

Silos yeah, but I need.

A

To get there we're gonna, actually a really short I, don't know: I code, artificial, general intelligence.

C

A

Animal, a general closets first.

C

We had all animals and us rebels, we have all this flexible behavior, which is deal with the world. So that's that's kind of my.

C

B

So I had a couple questions in the chat or a couple observations in the chance. So, okay.

C

B

I think this was Gordon. This was about the growing cellular automata. He said it contrasts with the cybernetic embryo, so I know people here probably I've heard a little bit about the cybernetic embryo, but this is a series of two papers that stone has written with one with Richard and one with myself and Tom. We talked about like cybernetics and how that kind of you know that kind of approach can you know, explain something about morphogenesis in the embryo.

H

In the cybernetic area approach is that the everyday does not have a Code, Red, okay and a global sense. What it does is it sets up that a system which has a specific goal, and then, when that goal is achieved, it includes the construction of two more cybernetic systems. So you end up with a tree of cybernetic systems which results on embryo and that's very different from any scheme which had like four women to sort 11th strikes being directed.

H

Where the final state is already relaxed to say, she's.

G

H

That's the way that works is.

F

H

The egg has its mind somehow an idea, but it's supposed to be and it keeps checking its own shape against it, but it hasn't it's lining to a flex. There I think. That's quite fallacious view cells.

H

That's way more bizarre, actually.

B

A

C

Final state, it just has a bunch of rules, is rules and better than the thing.

H

To extract the syllables yeah, that's right.

E

H

The the rules are very localized and insensitive. Each each system has its only goal point which accomplishes, but at the end, the goal that includes the construction of the next cybernetic system, and so in fact, marvelously constructs as paragraphs, so you get a by figure, could keep you treated under data systems?

H

That's different from having a little deal where you try.

H

So it's kind of a hybrid, very localized rules know that you know in civics, but.

H

H

H

F

Unfolds it kind of.

H

Will start first when you get some proliferation to get more than one set? Okay, so you get a few at least know. Maybe couples or whatever you got a pilot cells. No happiness! Is you get a pair of ways we've gone over the organist. We call it to accentuate those ways propagates through the cells to a subset of the cells and change the so students subtype when the wave is done.

H

It also sets up the conditions for the initiation within that group of cells of two new ways divided the territory into so the cells undergo another slip of differentiation.

H

Okay, so you're, okay and then it's all over and so we're also waiting. So so you've got lots of social workers.

H

So, that's, that's! That's the general idea. This is each each group of cells is defined by a highway that goes through it and sets and Paraguay's. Then it's no subset. So you bunch of nested subsets of cells and in this step the cells become different cars.

H

If the, if the process does produce a bio mordant such as body said you have to but doesn't have because they're more successful, but this will be better. It's analogous in some sense evolution Tongass to walking at table.

H

The Sun must fall off the wire, but if you get all the way across the food supply worries and the lenses were the ones that got the tricks were little locals feedback. They possibly get all the way across the wire.

H

So it's full of local feedbacks, but not not much, maybe Sun, but there's not much little feet right. Yeah.

C

H

So so it's it's a it's a lot of explanation. Simulator.

H

Okay, yeah, okay, you listening to have access just send in your email address will give you access to.

H

H

Muffin fish: this looks: we could sell it as eccentric by that time. I know a dozen yes, okay, now I was thinking while you're showing that well. Why not, then try to modify the puffer shape model and see.

F

If you can fix.

H

Very eccentric, icon matters yeah, and what would be more and more bizarre thing.

F

Yeah but yeah I can be.

F

H

Patterns of made, what makes you do something it's so dispersed yeah, but that's crystalline silica right, obviously isn't the same, but there's something that can be similar. The other parents are definitely yes, oh, so you might.

A

H

To imitate those patterns, so we had a a chapter in the book and this is coming out. Diatomic matters, a tiny pellets, maybe I'll send that to you, it's known as a person she's a much better mathematician. I am so it's a little bit steep on the myth, but the might seem that way. Actually take your simulation for the puffer fish and started acting in centric diatoms yeah.

H

The multiple layers, the set of shaken pattern as you go up radius.

F

Exactly what happens yeah.

H

C

Depending on the language, when you're talking about this cognitive, every I wasn't like once you come up with this these. This is this locally local rules, where we want to call it between them. There's a producers of him had ever produced crap. You.

F

F

Homeobox, you know rules.

H

Dissimulation see what reduces.

C

Yeah, you know whatever viable. You know in.

F

C

B

Happen, how can you jump from one viable corn to another draft 504.

C

Without killing, without telling everyone.

G

H

Yes, we thought that's the.

H

Probably Richard Phillips mixture and monsters the whether evolution, pcs, but.

F

In gradual form or big.

E

E

H

The he's very good Genesis was time, but people did not like, and these mythic tyranny is gradualist which which people have to keep, and anybody know certain jokes.

D

H

If you look at the one picture in Origin of Species and how he describes it, you'll see that we was completely aware that the evolution occurred. Many levels of sudden.

B

Thanks yeah thanks for comments. Okay,.

G

B

So does anyone else have any questions before we wrap it up we're almost at the top of the hour here.

B

Like I said, I can send papers out, or tom has a link there.

C

B

And so this is a very interesting topic. Yeah thanks for the presentations, so will we might revisit this in subsequent weeks? I've people are interested in talking about it further, please, you know, chat message me or Tom. We can talk about some other issues related to this I. Think it's a good thing to follow. Up on next week we have I, think Jesse's been and a half his he's, gonna record his presentation on the free energy principle and we're gonna present it next week, sort of on video.

D

Yeah girl, first and the.

B

Theory of the brain or something so Jesse's willing to wait into that you're gonna, pretty good presentation, looks pretty good, so doing that, and so, but otherwise have a good week. Remember we still have spots open for presentations, so people are interested in presenting yeah wait right in please. Let me know otherwise of a good week.

C

B