Neuroevolution of augmenting topologies (NEAT algorithm)
en.wikipedia.org
Neuroevolution of augmenting topologies (NEAT algorithm)
1–10 of 34 posts
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#2I post a link to NEAT here about once a week.
The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs)
Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks.
Its easier to learn and implement than back propagation, the speciation is the most complex but awesome feature. It develops multiple solutions, clustering them to iterate on them separately. An online learning NEAT agent is in practice is an online collection of behaviors, adapting and swapping dominance as their fitness changes.
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#3I post a link to NEAT here about once a week. The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs) Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks. Its easier to learn and implement tha…
I think the major iteration that will come next is "NEAT in a dream" where a robot or agent online-trains a library of behaviors on an model of the environment constantly updated with the new experiences generated by the dominate behaviors interacting with reality.
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#4I post a link to NEAT here about once a week. The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs) Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks. Its easier to learn and implement tha…
> The big problem is that NEAT can't leverage a GPU effectively at scale
I worry how much experimentation we are leaving on the table simply because these paths wouldn't implicate nvidia stockholders in an advantageous manner.
Modern CPUs might as well be GPUs when you are running GA experiments from the 80s and 90s on them. We can do millions of generations per hour and populations that span many racks of machines with the technology on hand right now.
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#5I post a link to NEAT here about once a week. The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs) Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks. Its easier to learn and implement tha…
I feel a bit embarrassed as, despite almost 15 years working in the field, I've not played with NEAT yet nor read up well on it. TIME TO CHANGE THAT :)
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#6Shameless plug:
I have an implementation in Rust (CPU only) with added GRU gates
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#7There's a lot of really interesting work in neuroevolution that has the potential to make some really interesting unsupervised training regimes. I think theres some really interesting possibilities for unique encoding schemes like ACE encoding to speed up training and provide much smarter behavior out the other end. Especially, if "genes" can form reusable elements of neural topology that makes scaling networks faster. Reusing components all over body is how we fit such complexity in the relatively little unique DNA we have. The other interesting thing about using genetic algorithms for a portion of training/network mapping is that allows you to have heterogenous networks, so you can have simulations or representations of astrocyte/glial behaivor easily get integrated with neural networks. With traditional training methods it's a massive fucking pain to train a non-feed forward network.
I do think that languages like Elixir and other cpu concurrent strong tools can really be leveraged to make some dynamite libraries.
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#8Shameless plug: I have an implementation in Rust (CPU only) with added GRU gates https://crates.io/crates/neat-gru
Damn thats awesome, might be the thing that really gets me to mess around with Rust.
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#9I post a link to NEAT here about once a week. The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs) Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks. Its easier to learn and implement tha…
> The big problem is that NEAT can't leverage a GPU effectively at scale I worry how much experimentation we are leaving on the table simply because these paths wouldn't implicate nvidia stockholders in an advantageous manner. Modern CPUs might as well be GPUs when you are running GA experiments from the 80s and 90s on them. We can do millions of generations per hour and populations that span many racks of machines w…
The more immediate causal reason is that there is no off the shelf high performance hardware to accelerate these paths. GPUs were made for graphics, not machine learning. They just happened to be really good at running certain kinds of models that can be reduced to a ton of matrix math that GPUs do really really fast.
Something like Intel Xeon Phi or one of the many-many-core ARM designs I've heard talked about for years would be better for more open ended research in this field. You want loads and loads of simple general purpose cores with local RAM. Put like 4096 32-bit ARM or RISC-V cores with super fast local RAM on a die and transactional or DMA-like access to larger main memory, and make it so these chips can be cross linked to form even larger clusters the way nVidia cards can. This is the kind of hardware you'd want.
When I was in college in the early 2000s I played around with genetic algorithms and artificial life simulations on a cluster of IBM Cell Broadband Engine processors at the University of Cincinnati. That CPU was an early hybrid many-core design where you had one PowerPC-based controller and a bunch of simplified specialized cores like a GPU but more designed for general purpose compute. Programming it was hairy but you could get great performance for the time on a lot of things.
Computing is unfortunately full of probably better roads not taken for circumstantial reasons. JavaScript was originally supposed to be a functional language-- a real, cleaner one. There were much, much better OSes around than Unix in the 80s and 90s but they were proprietary or hardware-specific. We are stuck with IPv4 for a long time because IPv6 came too late, and if they'd just added say 1-2 more octets to V4 then V6 would not be necessary. I could go on for a while.
This has led to a "worse is better" view that I think might just be a rationalization for the tyranny of path-dependent effects and lock-in after deployment.
Re: Neuroevolution of augmenting topologies (NEAT algorithm)
#10I post a link to NEAT here about once a week. The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs) Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks. Its easier to learn and implement tha…
> The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs)
Is that true? These graphs can be transformed into a regular tensor shape with zero weights on unused connections. If you were worried about too much time/space used by these zero weights, you could introduce parsimony pressure related to the dimensions of transformed tensors rather than on the bipartite graph.