A solo bit on NEAT, POET, and MAP-Elites — evolutionary algorithms that grow neural networks and their wiring, not just weights. Aqeel walks through a weekend experiment where simple creatures evolve to recognise images they themselves produce, and how symmetry and low-energy constraints start to look uncannily like life.

Watch the full episode below — also on the podcast feed wherever you listen.

In this bite

The facts

  • Solo walkthrough of NEAT, POET, and MAP-Elites — algorithms that evolve network topology, not just weights.
  • A weekend experiment lets evolved creatures recognise images their own DNA sequences produce.
  • Browser-based swarm compute via WebAssembly and PartyKit — anyone can help evolve the population.
  • Symmetry and low-energy constraints in a three-dimensional setup begin resembling biological form.
  • Lines from Stanley, Clune, and Risi connect decentralised evolution to ongoing work on Meos.

Between the facts

NEAT-family algorithms meet a long-deferred weekend after shipping Meos to the app stores. The self-recognition task turns a research toy into something stranger: brains that must read pictures of their own making. Distributed volunteers in browsers carry a population search that would once have stayed on a lab cluster.

Beyond the facts

Simple rules for wiring, energy, and symmetry start to resemble the shapes biology favours. A trace of identity persists inside artefacts that are partly constructed, partly discovered — a motif that echoes beyond the simulation.

Why you should listen

The bit follows how a standing research interest surfaces in product choices and a live experiment you can join. Hearing it in Aqeel's voice carries the technical walkthrough and the quiet reason the project exists at all.

Transcript

Auto-generated from captions — likely errors. Timestamps seek the embedded player.

My weekend project cost me two and a half thousand dollars of opus 4 .8 credits

So one of my weekend projects i haven't done one in a while because i've been so focused On building meos that has been my weekend and weekday and late night project uh but since we Launched of the app stores, I was really excited to finally have time to work on an algorithm I've had a romantic obsession with ever since I got exposed to AI.

And that was NEAT, which is using evolutionary algorithms to not only change the Weights of a neural network, but also the way that it connects together.

It uses genetic algorithms, so it defines a DNA sequence per neural network and then with that you Test it out in a simulated environment and then you see which ones are the fittest and then Breed a new population based on the one before that there are extensions to this algorithm and I Kept following it by the way the work is all biologically inspired by and the pioneers are Kenneth O.

Stanley Jeff Kloon is another one that i am really inspired by with his works where he extended It to include the algorithm called poet poet then is about being able to make the environment which You test it in also evolve at the same style size um same way as the algorithm evolving So you have ways of knowing how to get to the place you want to get and then Further work sebastian risi i think was their name that worked on MAP-Elites and this turned into

A really great nature paper of robots that heal themselves so you get like a hexapod robot and These algorithms are really good unlike they're not really used for training llms or ai but they're really Good for robotic gait so you can imagine a hexapod needs to know how to move its legs.

And instead of keeping the algorithm that knows how to move its legs in the perfect living situation, You then put it in environments where or you measure particular evolved genomes of these brains where the Leg itself, one of the legs might not be touching but it's still moving now this is useful To keep and you keep it like multi -dimensional parameterization of this so that in the field suppose That like hexapod's leg got like taken off then that way it still is able to change its

Brain really quickly without retraining so these are that's the algorithm that i was really excited about and I never had chances to play with it. I also had, I've always, like, I guess, in this course, the meos, and you can see it All in meos, I have an obsession with decentralization and utilization of, I suppose, volunteer compute.

And because this is a population search algorithm, it is able to be embarrassingly parallel and decentralized. So utilizing the web browser in Cloudflare Party kit I then and WebAssembly I was then able To develop a neural evolution artificial life experiment where anyone can go to it to this website you Can go onto your phone onto this website and it connects you to the cloud the swarm compute And you're helping evolve neural network life forms that are doing one thing which i think is this Is where it became a weekend project not a bit of an art where they're trying to understand

Their true self so as i said earlier the neural networks image or like what defines the neural Networks architecture can be done as a sequence, a DNA sequence.

That then produces a pattern. That pattern gets through an algorithm that turns into the brain. The inputs then for that brain, or we can think of like what we put as the eyeballs, What we put as the input into that thing to test it, is that I give it the Image that produced itself.

So it's like right now I'm looking at a preview of myself. My brain is seeing a picture of me and the task then that we tested on is that Given that input of seeing the produced image can that neural network reproduce the sequence that developed that Image

And uh this again like the genesis um random seed to start this entire algorithm i used the Sequence and And yet a trace of the true self exists within the false.

This is a ridiculously hard problem Because it is solving a few things. It has to know how to make a sequence, that's one. So that's sort of like a LLM sort of deal.

So I've decided to extend a lot of the work that was usually done in neural evolution and Bring in some of the more recurrent neural network stuff like Karpathy, Andrzej Karpathy really made famous with Their original blog post on the, what was it called?

The unreasonable effectiveness of recurrent neural networks.

So it's going back to all that stuff and then bringing in a bit of what we know Now today of AI. So this is the repo, you can go check it out.

It's MIT, I think, it's probably, or whatever. I have a whole heap of research in here, the documentation. You can see the literature review on the white paper as well.

But I also have, as I said, it's all WebAssembly and runs in the browser. So as soon as you go to the GitHub Pages site, this is actually the app and it's Loading now.

So what this is happening here are all of the neural networks that are a different type of Niche of behavior. So if this was the hexapod, it would be like a human being.

Let's say it's like the percentage that this neural network keeps its left leg on the ground versus The right leg on the ground.

So if you and then the challenge in that case might be who moves the fastest. That's like kind of what this MAP-Elites here is doing. So in this case, we are doing it by symmetry versus complexity to the actual neural network.

The neural network itself, it's super glaring, let me close this.

Can you open the window? Yeah, There we go.

Cool. So the neural network sequence, the original sequence is there. That neural network sequence creates this convolutional pattern producing network That takes X, Y, Z. It's actually X1, X2, Y1, Y2, blah, blah, blah.

So that makes a connectivity matrix that will be in three dimensions. Those patterns that it produces are these images here. That's the 3D image. So that neural network DNA sequence produces an image Like this.

And then you use another algorithm. This comes from actually the ES -hypnete, Evolved Substrate Hypnete extension. That's the two -dimensional version. So different parts of density determines the nodes.

That's the actual brain itself.

So the input then to this neural network takes this image as a sequence and it actually has Attention to be able to determine what part is most interesting and then tries to produce a sequential Output.

To produce a sequence is already hard enough to be able to learn but the real hard thing, As I guess the only people that be understanding this by now would know is when to stop Producing the actual sequence.

That's effectively a halting problem. That's obviously incredibly hard so it has to know by looking at the image of itself the length Of its very own DNA sequence in which is over here.

You can see how often it glimpsed at the actual thing and thought before it actually wrote the Neural The sequence out and this one you can see it has produced five nodes 18 connections out of It should have done 19 connections i've also implemented Hebbian learning and neuroplasticity as well as neuromodulation This is also really cool stuff or proper biologically inspired neural network things Hebbian learning and associative Learning allows you to do learning at runtime.

So it's sort of like attention in a way or recurrence in a way. It is also how we operate a lot more and a big part of meos.

You can really see what I really enjoyed about doing this project was you can really, I could Really see the thread

Of these things that I found interesting as a researcher the things that I was attracted to as A researcher and even though I didn't go into AI research and I decided to go into AI Business I guess and consulting originally when it kind of boomed and if I went into AI research I probably would be a lot more better a lot more well off this is I can see How these things have inspired my actions in building meos or the things that I've held on to

And that real poetic ending to all of this is the reason why I decided to make this Neural network and artificial life experiment try produce an image of itself again goes to that genesis and Yet a trace of the true self exists within the false Just as so many of these research Ideas and thoughts of mine, they exist within meos, they exist within this website you can go to, And importantly, they exist within MI.

Add the biological nature of these simple rules of we've got this three dimensionality and then a pattern Producing. So this is the currently best performing brain that we have evolved so far.

Again, please go to the website and you can help us evolve more. Over here on the left, you can see these two input neurons and then it goes to the Output neurons on the back.

And then one that this reminded me of, by looking at this, was the very well known and Established fact in neuroscience that our eyeballs evolved into our brain.

The fact that we just started as eyeballs and that sensor alone then turned into this brain. You can see that here. You can see those two eyeballs at the front.

You can see them. There they are. There's two little eyeballs at the front. Goes into a big fat piece of neurons connected together and then to an output which I guess Would be the spine this is just one of them you can take a look at other different Shapes here let's take a look at this shape there's a kind of cool shape as well you Can always see there's like oh input neurons they're the sensors they're like eyeballs two eyeballs those are The two eyeballs that are looking at this image that i gave this simple mathematical problem and because

I followed the rules of exactly how we make this in the physical world doing it in 3d Three dimensions Getting symmetry is a thing to do with energy converse conservation as well trying to keep things low Energy, it started making things that look like life.