Ask HN: Why doesn't AI use dynamical neurons instead of static activations?

1 pointsby tonii1419 miesięcy temu7 comments

Why doesn’t AI use dynamical neurons instead of static activations even when it is known that biological neurons are dynamical systems?

7 comments

rini179 miesięcy temu

I guess it's impossible to simulate billions of dynamical neurons with current computer architecture, it is limited by memory bandwidth.

tonii1419 miesięcy temu

I agree, but maybe there is no need for billions of neurons to be simulated right away. Artificial neural networks were pretty small at the time.

rini179 miesięcy temu

and they did not do much

tonii1419 miesięcy temu

Not true. AI has been around far longer than modern LLMs and has performed well in non-generative areas, often with orders of magnitude fewer parameters.

nialse9 miesięcy temu

Dynamical neurons are not used because they add enormous computational cost and instability for limited practical gain.

tonii1419 miesięcy temu

What do you mean by "they add instability"?

nialse9 miesięcy temu

Neural nets are unstable during training and dynamic weights amplifies the problem. Thus, the neural networks could end up in totally unusable states at inference time.