home.social

#evolutionaryalgorithms — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #evolutionaryalgorithms, aggregated by home.social.

  1. DeepMind's AlphaEvolve strikes again:

    After recovering 0.7% of global GCP compute through better scheduling algos, AlphaEvolve helped FM Logistics achieve "10.4% improvement in routing efficiency over the previous best solution", leading to "15,000+ fewer kilometers of warehouse travel per year at full operational scale".

    It's really nice to see evolutionary algorithms make a comeback. AlphaEvolve uses an LLM (Gemini) as as a mutation function, and using similar mutate-evaluate-select loops typical of traditional evolutionary algorithms.

    cloud.google.com/blog/products

    #AlphaEvolve #DeepMind #EvolutionaryAlgorithms

  2. I'm really enjoying my latest research project. This one's exploring how different spatial environments can lead to different evolutionary dynamics. Here we see an environment where it's harder to survive in the middle than on the edges (that is, it requires higher scores from a fitness function). We can see the population evolve increasing fitness as it spreads into the interior space.

    #EvolutionaryComputation #EvolutionaryAlgorithms #science #evolution

  3. Just checked #EvolutionaryAlgorithms and #EvolutionaryComputation tags. And I found posts from just two: myself and @moshesipper

    It's time to feel scientifically lonely :)

    But really, why some people like me are attracted to less or more unpopulated regions of science and engineering?

    #science

  4. A #GeneticProgramming question. There is this Lexicase selection algorithm which is basically terminating individuals which don't perform good on a single testcase. If it was regression, it could make sense, but on a binary classification, this means suddenly a huge number of programs in the population will vanish as they misclassify a single data sample. I haven't tested yet. But to me it makes little sense. Where am I wrong?

    #machinelearning #EvolutionaryAlgorithms
    ping @lspector

  5. New paper out ✒️😊

    We present a novel approach to performing fitness approximation in #geneticalgorithms (#GAs) using #machinelearning (#ML) models, focusing on dynamic adaptation to the evolutionary state.

    mdpi.com/2078-2489/15/12/744

    With talented grad students Itai Tzruia and Tomer Halperin, and my colleague Dr. Achiya Elyasaf.

    #evolutionaryalgorithms

    #evolutionarycomputation

  6. I'm at uni, studying both evolutionary computation and deep learning. I'm a seasoned programmer, but both of these tools are new and challenging, because I'm used to having control over the programs I write. These techniques are both about getting computers to figure out their own way to do things.

    The difference is, with DL, there's some very specific thing I want to accomplish, and when I can't get the computer to do that, it's quite frustrating. With EC, I have way less of an expectation about what's supposed to happen, and often the weird stuff the computer comes up with is a delightful surprise.

    I guess the flip side is that EC is a bit too wild and unpredictable to be a very profitable enterprise at this point, but it's fun for research!

    #programming #ml #deep_learning #EvolutionaryAlgorithms

  7. I keep designing weird bio-inspired evolutionary algorithms, only to discover (while building them) that they're sorta inside-out versions of groundbreaking EAs of the past couple of decades.

    This is both frustrating, and tremendously exciting. On the one hand, I keep feeling scooped. On the other hand, I'm rediscovering known good ideas, and I hope my flip in perspective brings something interesting and important to the story! I really do think we've been thinking about evolution wrong all this time.

    I guess the challenge is for me to show that.

    #alife #EvolutionaryAlgorithms #science

  8. Looking forward to presenting our steps towards enabling access to all sounds with #EvolutionaryAlgorithms, next week during EvoMUSART in Aberystwyth. Summary and supplementary material is online at: uio.no/ritmo/english/people/ph

  9. Hey fedi, I vaguely recall hearing a story about early evolutionary algorithms trying to build a 50hz sine wave generator with electronics, but instead the algorithm built an antenna and amplifier to pick up and boost a 50hz hum.

    Is there any truth to this? Have I got any details right?

    #EvolutionaryAlgorithms #boostok

  10. One idea I'm thinking about for #GeneticProgramming

    In GP, we usually need to evolve multiple subpopulations named "demes" rather than one big population as the converge on smaller population happens faster. Then we have small, infrequent migrations between subpopulations, like 5% of population of each subpopulation/deme.

    #GP #GeneticProgramming #EvolutionaryAlgorithms #EA #GeneticAlgorithm #EvolutionaryMachineLearning #AI #ML #EML #research #researching #Question #Idea

    1/2

  11. Evolutionary algorithm (Evolution 🧬)

    In computational intelligence, an evolutionary algorithm is a subset of evolutionary computation, a generic population-based metaheuristic optimization algorithm. An EA uses mechanisms inspired by biological evolution, such as reproduction, mutation, recombination, and selection. Candidate solutions to the optimization problem play...

    en.wikipedia.org/wiki/Evolutio

    #EvolutionaryAlgorithm #Evolution #Cybernetics #EvolutionaryAlgorithms

  12. #Neulich ein Skript für #EvolutionaryAlgorithms angefangen zu schreiben. Gerade sehe ich: das ist schon zwei Jahre her! #timeisrunning

  13. #introduction
    Hi! I’m Tiago, I’m from Portugal and I like #mathematics #MachineLearning and #EvolutionaryAlgorithms.
    I study computer engineering in university and in my free time I do research on ML and evolutionary algorithms :)