News for hackers. Stuff that matters.
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by p1esk on Thursday November 14, 2019 @01:10PM (#21537773)
No need to simulate any of the environment. You only need to record the neural inputs to a fly’s brain. Sure that’s also challenging, but nowhere as challenging as simulating the entire fly’s brain. My point is if you manage to accomplish the latter, the former would be a breeze.
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by mac01021 on Thursday November 14, 2019 @02:24PM (#21538478)
> You only need to record the neural inputs to a fly’s brain.

I don't think that's true. As soon as your simulated fly's behavior diverges from the actual fly's, all of the recorded input after that point is invalid/useless because it will not match the simulated fly's position/orientation/whatever.

Also, how many dollar of investment and years into the future do you think we are from being able to record all of a fly's neural input while it is moving freely?

Re:Andrej Karpathy talks about how Tesla's NNs are structure... by p1esk on Sunday November 24, 2019 @05:09AM (#21619448)
To start with you only need to study input-response pairs (sensory input causing motor commands). You enter the neural inputs from a real fly into the simulation, and compare responses of the real fly and the simulated one. Once you understand what's going on, proceed to do sequence of inputs, and compare the sequence of responses. The goal is not to produce the identical sequence of actions by tuning the simulation, it's understanding how the actions are being computed from the inputs.

Having a detailed simulation like this would greatly accelerate Numenta's style research, where instead of piecing together information from published papers, you would get it straight from the experiments you control.