News for hackers. Stuff that matters.
Re:The quest to evolve neural networks through evolutionary ... by halflings on Monday October 30, 2017 @12:18AM (#15583054)
Again, this is very detached from what ANNs or genetic algorithms are: relatively simple methods to optimise fitness (or "cost") functions.

They are nowhere close to the complexity of a brain, and certainly do not have enough capacity to be a realistic simulation of the universe.

> How do we know until we've tried it? Tried what, is the question? What's an ant-level intelligence? We have algorithms that can detect images/speech at super-human level (at least in some conditions). Worthy questions, but unrelated to these algorithms.

Re:The quest to evolve neural networks through evolutionary ... by Turing_Machine on Monday October 30, 2017 @12:28AM (#15583090)
I'm not sure that ants are doing a "realistic simulation of the universe", though, or anything like it. From what I understand, they're a lot closer to little robots than they are to something that can do Kip Thorne-level astrophysics, or Thomas Aquinas-level philosophy.

I am thinking, in particular, of an experiment done by Richard Feynman where he got ants walking across small sheets of glass. After shuffling the sheets around so the chemical trail became a loop, he was able to get the ants tirelessly marching around in a circle (which they would presumably do until they dropped).

Heck, you probably don't even need an ANN at all to do that, much less an evolutionary one.