alt Hacker NewsBe careful about how you interpret that paper. It looks really impressive -- real neurons in a petri dish seem to successfully (if amateurishly) murk a few imps.
https://www.youtube.com/watch?v=yRV8fSw6HaE
But there's more to the setup than you might assume from a casual reading. Here's the code used for that demo:
https://github.com/SeanCole02/doom-neuron
So there is an entire pytorch stack wrapped around the mysterious little blob of neurons -- they aren't just wired straight into WASD. There is a conventional convnet-based encoder, running on a GPU, in the critical path. The README tries to argue that the "neurons are doing the learning" but to my dilettante, critical eye it really looks as though there is a hell of a lot of learning happening in the convnet also.
Are the neurons learning to play doom, or are they learning to inject ever so slightly more effective noise into the critical path? Would this work just as well if we replaced the neurons with some other non-markovian sludge? The authors do ablation experiments to try to get to the bottom of this but I can't really tell how compelling the results are (due to my own ignorance/stupidity of course)
Replies
Someone should try to replace the neurons with urand and see if the chip can still play Doom, in the spirit of the qday prize winner.
This reminds me of https://news.ycombinator.com/item?id=47897647, where a quantum computing demo worked equally well if you replaced the QC with an entropy source.
> but to my dilettante, critical eye it really looks as though there is a hell of a lot of learning happening in the convnet also.
Yeah it feels like they constructed the conclusion and worked backwards from there. I'm not seeing how their claim has much merit.
All opinions are my own:
The whole point of the CNNs is to act like a auto encoder for input and an auto decoder for output. The only reason why this is done in the first place is because the number of electrodes in the dish is pitiful and has no chance of describing something as complex as Doom. They are there to create a latent space that can be fed through 60 odd electrodes and decode the neuron latent space into pressing buttons.
The pong version of the game was the proof of concept that neurons can learn without a latent space intermediate in either direction. Both the world state and neuronal control were raw signals: https://pubmed.ncbi.nlm.nih.gov/36228614/
What I wanted to do after dish brain pong, but never had the budget for, was using live animals as the computational substrate. Use the visual cortex of one as the input, send the neural spikes to a second animals frontal lobe for computation and finally send those signals to a third animals motor cortex to physically press buttons. It's a shame we never raised enough because it wouldn't have cost more than $15m to build the hardware and do the biological proof of concept.