Hacker News Reader

Comment by peterstoziek | Hacker News Reader

As expected, the article seems to be a typical content marketing piece. If you're looking for real insights into evolutionary algorithms, specifically "neuroevolution", I highly recommend to read this article: https://www.oreilly.com/ideas/neuroevolution-a-different-kin...

I enjoyed it much more than - what feels like - a quickly thrown together marketing piece with no real value for the reader.

View on HN

Thanks for the great link surveying Evolution and NEAT ( Neuroevolution of Neural Nets ) by Ken Stanley who pioneered the method.

The OP is by Risto Miikkulainen who was Stanley's collaborator on NEAT and should not be summarily dismissed.

Note that this blog post is not an article per se, but an overview of a research website (https://sentient.ai/sentient-labs/ea) built around five new research papers. The website offers demos that illustrate neuroevolution and evolutionary computation concepts at a much more concrete level than the papers can.

For a short intro to neuroevolution there is http://www.scholarpedia.org/article/Neuroevolution

However, these overview articles do not include the newest research on evolving deep learning networks. Three such papers are introduced at https://www.sentient.ai/sentient-labs/ea-1/; there are other recent ones at https://research.googleblog.com/2018/03/using-evolutionary-a... and https://eng.uber.com/deep-neuroevolution/. It is a rapidly developing area.

Thank you, saved it for later. Do you have any other links to offer?

Unfortunately not in this domain.

Here's a recent survey / observational science paper by some prominent "neuroevolution" / A-Life researchers. https://arxiv.org/abs/1803.03453. I found this refreshing because it's rare that science papers talk about the debugging and experimental process and debugging journeys underlying this research.

A few links you can look at if you're interested in neuroevolution, from the same group of researchers:

Ken Stanley and Risto Miikkulainen original NEAT (NeuroEvolution of Augmenting Topologies) paper: http://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf

Ken Stanley's novelty search page, and a link to his book, "Why Greatness Cannot Be Planned: The Myth of the Objective": http://eplex.cs.ucf.edu/noveltysearch/userspage/

Risto Miikkulainen's Evolving Deep Neural Networks paper: https://arxiv.org/abs/1703.00548

Ken Stanley & team's work at Uber, with links to some recent papers: https://eng.uber.com/deep-neuroevolution/

Are these evolutionary techniques considered more or less sample-efficient (and or cpu-efficient) compared to DL with GD ??

Not quite a typical piece - it managed to make it to #2 on HN.

I upvote links that promote discussion of interesting concepts, even if the article itself is really bad - like this one.

I couldn't bother reading the original article, but designing neural networks via evolutionary algorithms is a very interesting concept I wasn't aware of.

Reply on news.ycombinator.com