Evolution Is the New Deep Learning
sentient.ai
Evolution Is the New Deep Learning
1–10 of 242 posts
Re: Evolution Is the New Deep Learning
#2As 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.
Re: Evolution Is the New Deep Learning
#3This article explains very little about the actual technique. Digging into the paper, it seems like this has to do more with training a network with multiple data sources at the same time, to take advantage of related patterns across data sets.
I'm not professionally versed in NNs myself, but what would be the closest equivalent to recreating this sort of training with tools available today? (in Keras or R for instance)
Re: Evolution Is the New Deep Learning
#4As 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.
Thank you, saved it for later. Do you have any other links to offer?
Re: Evolution Is the New Deep Learning
#5As 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.
Thank you, saved it for later. Do you have any other links to offer?
Unfortunately not in this domain.
Re: Evolution Is the New Deep Learning
#6A philosophical tangent: Evolution did not always produce the best outcomes. Would neuroevolution be vulnerable to similar effects? Probably a good research area. https://www.wired.com/2009/07/st-best-5/
Re: Evolution Is the New Deep Learning
#7As 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.
Not quite a typical piece - it managed to make it to #2 on HN.
Re: Evolution Is the New Deep Learning
#8Interesting to see that we're a long way from this technique actually generating anything valuable.
E.g. if you try the LSTM Music Maker they link to (https://www.sentient.ai/sentient-labs/ea/lstm-music/) and enter a melody, the resulting 'improvisation' will neither have any of the hallmarks of your initial input nor obey any of the conventions of any genre of music I recognise. It'll just spew out a random-seeming spray of notes. Compared to, say, JukeDeck (https://www.jukedeck.com/make/track-generator/essential), which uses bog-standard AI, it's got a long way to go.
Re: Evolution Is the New Deep Learning
#9This is how we all wind up in a Peter Watts novel.
Re: Evolution Is the New Deep Learning
#10A philosophical tangent: Evolution did not always produce the best outcomes. Would neuroevolution be vulnerable to similar effects? Probably a good research area. https://www.wired.com/2009/07/st-best-5/
Biological evolution seem pretty susceptible to overfitting to ecological circumstances—I worry that there would be an analog for these techniques with NNs