News for hackers. Stuff that matters.

A comment on Neuro Evolution of Augmented Topologies.

Re:Neuro Evolution of Augmented Topologies by eggy on Wednesday November 24, 2021 @08:07AM (#29329603)
They seem to be similar to Gene Sher's TWEANNS - Topology and Weight Evolving Neural Networks - that I learned about in his 2012 book, "Handbook of Neuroevolution Through Erlang" (sure, it didn't pick up because Erlang ;))

Gene's specific implementation is DXNN (Discover and eXplore Neural Network) implemented in 2010 [1]

[1] https://arxiv.org/abs/1008.2412

[ Parent | on HN ]
Re:Neuro Evolution of Augmented Topologies by dkislyuk on Wednesday November 24, 2021 @09:57AM (#29330554)
Sher's TWEANN work cites NEAT and HyperNEAT quite extensively — Stanley's original work here is pretty influential in the neuroevolution space!
[ Parent | on HN ]
Re:Neuro Evolution of Augmented Topologies by eggy on Wednesday November 24, 2021 @11:15PM (#29338166)
I missed that, thanks! I'll have to take another look.

When I think of neural networks that evolve changes in their topology and the weights between those connections, over and over towards optimizing a solution to function, I get the vision of the recursive Life in Life video[1] where Conway's Game of Life is emulated in Game of Life.

[1] https://www.youtube.com/watch?v=xP5-iIeKXE8

[ Parent | on HN ]