Evolution Is the New Deep Learning

Re:Evolution Is the New Deep Learning by klmr on Thursday March 22, 2018 @01:32PM (#16650762)

I agree, the examples aren’t the best chosen. But there are cases which are pretty well established in biology as being maladaptations. — The laryngeal nerve is the most famous of those [1] because there’s really no advantage to the way it develops, and its characteristics poses significant health problems that do affect evolutionary fitness negatively. Yet there’s no easy fix to solve its positioning through gradual mutations.

[1] https://en.wikipedia.org/wiki/Recurrent_laryngeal_nerve#Evid...

[ Parent | on HN ]

Re:Evolution Is the New Deep Learning by bckygldstn on Thursday March 22, 2018 @02:33PM (#16651306)

That nerve seems like an example of a local optimum. The way to avoid this is either to increase the mutation rate, or modify the fitness function so the intermediate states aren't so heavily penalised.

We can't easily do that with real evolution but it's configurable with evolutionary algorithms, as with most machine learning algorithms. The hard part is finding those parameters.

[ Parent | on HN ]