#geneticalgorithms

0 posts0 participants0 posts today

Amin GirasolVia the <a href="https://oldbytes.space/@ataripodcast" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@ataripodcast</a>: in a 25-minute video, Jean Michel Sellier, Research Assistant Professor at Purdue University, demonstrates the use of an <a href="https://oldbytes.space/tags/Atari800XL" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Atari800XL</a> to train a neural network using a genetic algorithm instead of the memory-hungry technique of gradient descent.<a href="https://hackaday.com/2025/02/21/genetic-algorithm-runs-on-atari-800-xl/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://hackaday.com/2025/02/21/genetic-algorithm-runs-on-atari-800-xl/</a>I've had a soft spot for Artificial Life for a long time. During the last AI Winter in the mid 1990s, I was spurred to get back into education and onto a career in commercial software development by Stephen Levy's book "Artificial Life: The Quest for a New Creation". I loved that Artificial Life researchers borrowed well-understood mechanisms from genetics and implemented them in software to converge iteratively on solutions, in contrast to AI research, which was attempting to build models of categories which were not understood at all (and largely still aren't) - intelligence (whatever that is) and perception.In subsequent years I wondered why I wasn't hearing any hype about Artificial Life; it turns out practitioners have been quietly getting on with solving problems using the technique. Meanwhile, yet again, AI boosters have blustered their way into the consciousness with another round of overcooked hype.The Stephen Levy book is still worth a read, if you can find it. (IIRC Danny Hillis and the Connection Machine folks get a mention too.)(I don't know if any of the genetic algorithm folks turned out to be supporters of eugenics, as many of the current crop of AI boosters seem to be.)<a href="https://archive.org/details/artificiallifequ0000levy_l1x2" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://archive.org/details/artificiallifequ0000levy_l1x2</a><a href="https://en.m.wikipedia.org/wiki/AI_winter#The_setbacks_of_the_late_1980s_and_early_1990s" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://en.m.wikipedia.org/wiki/AI_winter#The_setbacks_of_the_late_1980s_and_early_1990s</a><a href="https://oldbytes.space/tags/solarpunk" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#solarpunk</a> <a href="https://oldbytes.space/tags/permacomputing" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#permacomputing</a> <a href="https://oldbytes.space/tags/geneticalgorithms" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#geneticalgorithms</a> <a href="https://oldbytes.space/tags/ArtificialLife" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ArtificialLife</a> <a href="https://oldbytes.space/tags/RetroComputing" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#RetroComputing</a> <a href="https://oldbytes.space/tags/VintageComputing" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#VintageComputing</a> <a href="https://oldbytes.space/tags/TESCREAL" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#TESCREAL</a> <a href="https://oldbytes.space/tags/Eugenics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Eugenics</a> <a href="https://oldbytes.space/tags/Genetics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Genetics</a>

Forgetful Bri :ms_robot_grin:Looked into more genetics info, and now I'm having flashbacks to friends studying biology and having meltdowns over how many mutations grass will put up with.I'm still trying to figure out how to encode traits for the game mentioned in my previous post. The first idea was to represent the entire genome as a single bitstring. The sequence "101010010" corresponds to the creature described here: <a href="https://wetdry.world/@forgetful_bri/112022884899696857" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://wetdry.world/@forgetful_bri/112022884899696857</a>This method isn't very flexible though. The genome of every creature has to be the same length. If a new trait was added in down the line, all the existing creatures would either need to be scrapped, updated, or handled specially.Another idea would be to include an identifier for a trait in the encoded sequence, rather than determining a trait by its position in the sequence. So the previous sequence might be marked "A10 B10100 C10" and would result in the same creature as the sequence "B10100 A10 C10".The main advantage here is that new traits can be added on at any time. The existing creatures just won't have them, and the trait won't be used at all when generating a description. The disadvantage is that sequences could differ in length or in position, which would complicate the process of simulating crossover.Maybe that would be the best way of going about it though?Creatures just wouldn't be able to form offspring if they had sequences of different lengths, unless a mutation occurs that increases/decreases the length of a sequence. Creatures could also develop similar traits despite having very different sequences, since positioning doesn't matter.Yeah… The more I think about it, the more this method seems "messy" in an organic manner.If anyone has any ideas/thoughts/tips, I'd love to hear them :blobcatscience:<a href="https://wetdry.world/tags/Biology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Biology</a> <a href="https://wetdry.world/tags/Genetics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Genetics</a> <a href="https://wetdry.world/tags/Bioinformatics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Bioinformatics</a> <a href="https://wetdry.world/tags/Biochemistry" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Biochemistry</a> <a href="https://wetdry.world/tags/Worldbuilding" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Worldbuilding</a> <a href="https://wetdry.world/tags/GeneticAlgorithms" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#GeneticAlgorithms</a>

Jason H. Moore, Ph.D.Is the evolution metaphor still necessary or even useful for genetic programming? <a href="https://link.springer.com/article/10.1007/s10710-023-09469-9" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://link.springer.com/article/10.1007/s10710-023-09469-9</a> <a href="https://mastodon.online/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#artificialintelligence</a> <a href="https://mastodon.online/tags/geneticprogramming" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#geneticprogramming</a> <a href="https://mastodon.online/tags/geneticalgorithms" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#geneticalgorithms</a>

Gert :debian: :gnu: :linux:I fenomeni di emergenza in un sistema in evoluzione sembrano essere legati alla comparsa di processi dinamici nuovi rispetto alla loro qualità e imprevedibili sulla base della caratteristica iniziale del sistema. Per questo motivo è difficile modellizzare i fenomeni di emergenza perché il modello in uso può diventare improvvisamente inadeguato a delineare nuove manifestazioni dinamiche e quindi la vera identità del sistema.In questa simulazione (nel primo video la registrazione di una sessione) ho cercato di costruire un metamodello che descriva alcuni fenomeni di emergenza durante l’evoluzione del sistema dinamico organismo-ambiente. Usando algoritmi genetici ho realizzato un sistema di agenti artificiali che interagiscono risolvendo una versione spaziale del Dilemma del Prigioniero Iterato (Axelrod, 1984; Axelrod e Dion, 1988).Il sistema, compresso tra i vincoli di una crescente complessità interna e l’impossibilità di scindersi, si mantiene spontaneamente entro valori di entropia che gli consentono di mantenere coerenza e “identità” nel tempo, permettendogli di far emergere diversi nuovi equilibri di Nash nella tabella dei payoff ( cultura? economia? politica?…) che regola gli scambi tra agenti artificiali; i nuovi equilibri di Nash emergenti nella tabella dei payoff facilitano l’emergere di alcuni “clan” che si replicano secondo le dinamiche genetiche del Cross-Over.Per ogni generazione, le azioni del “clan vincente” contribuiscono a modificare la tabella dei payoff secondo regole più vantaggiose per la loro logica di interazione (cooperare/rifiutare/defezionare).Ogni volta il nuovo equilibrio di Nash emergente viene mantenuto per alcune generazioni, oscillando tra diversi valori di entropia, finché un nuovo “clan” di agenti virtuali prevale sugli altri, orientando l’intero sistema verso l’emergere di un nuovo equilibrio di Nash nella tabella dei payoff. <a href="https://qoto.org/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://qoto.org/tags/geneticalgorithms" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#geneticalgorithms</a> <a href="https://qoto.org/tags/gametheory" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#gametheory</a>

Recent searches

Search options

Administered by:

Server stats: