News for hackers. Stuff that matters.
Re:Parametric Study of a Genetic Algorithm (2003) [pdf] by sgk284 on Sunday August 06, 2017 @02:22PM (#14942605)
Gradient methods have certainly gotten most of the attention, but there is the field of neuroevolution[1] and OpenAI recently released a paper covering evolutionary strategies for neural networks: https://blog.openai.com/evolution-strategies/

[1] https://en.wikipedia.org/wiki/Neuroevolution

Re:Parametric Study of a Genetic Algorithm (2003) [pdf] by ramgorur on Sunday August 06, 2017 @05:25PM (#14943647)
But I used to know GAs don't need gradient information, right? The algorithm is supposed to discover the gradient by itself, if there is any.
Re:Parametric Study of a Genetic Algorithm (2003) [pdf] by mehh on Monday August 07, 2017 @03:19AM (#14945857)
GA can be used for topology and parameter tweaking.