Live data from Hacker News

Why AI lags behind the human brain in computational power

11–12 of 12 posts

Re: Why AI lags behind the human brain in computational power

#11

Post by skyde » Sun, Nov 07, 2021, 6:35 AM UTC

yaroslavvb wrote: post #2

Realistic simulation of neurons is expensive. Back in my grad school days we ran Genesis and could afford at most 10k neurons - each neuron needs a lot of work to model the corresponding differential equations. However, it's unclear how to translate this into requirements for artificial neural networks -- the type of computation is too different. A different metric is a more relevant goalpost -- number of synapses. I…

we already know biological neural networks like the worm C-elegant is more intelligent than an artificial neural network of the same size.

isn’t it sufficient proof the bottleneck is elsewhere ?

Re: Why AI lags behind the human brain in computational power

#12

Post by candiodari » Sun, Nov 07, 2021, 11:15 PM UTC

named-user wrote: post #9

TheDudeMan wrote: post #8

Lost me at "Traditional neural nets have two input layers."

Yes, the input layer and .... The input layer?

There used to be a time, long ago, when neural networks had 2 layers: the input layer and the output layer, with full connections between the two. There's an old proof that, if you don't have nonlinearities there's an equivalent 2-layer net for any arbitrarily deep neural net.

So the real difference between modern "deep neural networks" and "neural networks" is not actually the depth, even though it is. It's just that neural networks, old definition, a 2 layer net can match any depth net, so you wouldn't use more. The real difference isn't the depth, but the nonlinearity (the tanh/sigmoid/relu operation).

Post reply on HN