Yes, this is traditionally a big effort in the neuromorphic community originating in Carver Meads lab at Caltech.

Perhaps the best success of such analog computation efforts are with Neurogrid (full disclosure I worked with this group): https://web.stanford.edu/group/brainsinsilicon/

One thing to keep in mind is that communication is often still in digital spikes, which some may argue is more neuron like than an analog encoding.

Yes, I work at a startup that's doing this, but it's very dangerous with the amounts of noise, which seem fine on MNIST and even CIFAR, but you die on imagenet.

The key to circumventing this is very complicated and our "secret sauce".

Can you say a bit more about what you mean by "it's very dangerous with the amounts of noise"?

Network accuracy crashes

I'm hoping that we could see photonic computers.