I assume you mean strictly chaotic, vs probabilistic?

Some of the new photonic processors accelerate AI inferencing by being probabilistic, but as you point out, you can't train on this class of processors. Possibly specifically because trying to use the current 'back-propagation' algorithms, you lose sufficient fine details for the network to backpropagate far enough into the network.

Being able to do something similar to 'back-propagation' but in a probabilistic way, would be huge as it would open up photonics even further into the AI space.

I also think we are not using genetic algorithms nearly enough to solve this problem space.

'Chaotic' here means 'sensitive dependence to initial conditions'. When chaotic functions are in play the early layers essentially never get adjusted because the derivative of the final output becomes gigantic.

I assume you mean strictly chaotic, vs probabilistic?

Some of the new photonic processors accelerate AI inferencing by being probabilistic, but as you point out, you can't train on this class of processors. Possibly specifically because trying to use the current 'back-propagation' algorithms, you lose sufficient fine details for the network to backpropagate far enough into the network.

Being able to do something similar to 'back-propagation' but in a probabilistic way, would be huge as it would open up photonics even further into the AI space.

I also think we are not using genetic algorithms nearly enough to solve this problem space.

'Chaotic' here means 'sensitive dependence to initial conditions'. When chaotic functions are in play the early layers essentially never get adjusted because the derivative of the final output becomes gigantic.