Evolution Is the New Deep Learning

Re:Evolution Is the New Deep Learning by jmmcd on Friday March 23, 2018 @07:01AM (#16656754)

> Genetic Algorithms do exactly the same thing that Deep Learning methods do: optimize a function for a particular criterion.

The difference is that for a GA, that can be any function, whereas for NNs it must be decomposable into a sum of partial objectives, and differentiable. Moreover, the result of training an NN is a function mapping a vector to a vector, whereas the result of training a GA could be an object drawn from any search space.

[ Parent | on HN ]

Re:Evolution Is the New Deep Learning by randomsearch on Friday March 23, 2018 @07:12AM (#16656815)

I think there's a further difference - with some GAs (including GP, widely used by Sentient) the structure of the solution is "designed" alongside the parameterisation of that structure.

Most DL work parameter tunes a structure that is hacked by human guesswork.

The two approaches have strengths and weaknesses, and in no way does this make EC in general superior to DL, but perhaps different.

[ Parent | on HN ]

Re:Evolution Is the New Deep Learning by jmmcd on Friday March 23, 2018 @07:50AM (#16657020)

I agree, but I intended that point as part of my final point -- an EA can draw a solution from any search space, including a space of trees, for example, as in GP.

[ Parent | on HN ]