AnthonyI came across a post on LinkedIn about evolutionary computation, and opted to post this in response:
I never stopped using evolutionary computation. I'm even weirder and use coevolutionary algorithms. Unlike EC, the latter have a bad reputation as being difficult to apply, but if you know what you're doing (e.g. by reading my publications ๐) they're quite powerful in certain application areas. I've successfully applied them to designing resilient physical systems, discovering novel game-playing strategies, and driving online tutoring systems, among other areas. They can inform more conventional multi-objective optimization.
Many challenging problems are not easily "vectorized" or "numericized", but might have straightforward representations in discrete data structures. Combinatorial optimization problems can fall under this umbrella. Techniques that work directly with those representations can be orders of magnitude faster/smaller/cheaper than techniques requiring another layer of representation (natural language for LLMs, vectors of real values for neural networks). Sure, given enough time and resources clever people can work out a good numerical re-representation that allows a deep neural network to solve a problem, or prompt engineer an LLM. But why whack at your problem with a hammer when you have a precision instrument?
I started to put up notes about (my way of conceiving) coevolutionary algorithms on my web site, here. I stopped because it's a ton of work and nobody reads these as far as I can tell. Sound off if you read anything there!
#AI #GenAI #GenerativeAI #LLMs #EvolutionaryComputation #GeneticAlgorithms #GeneticProgramming #EvolutionaryAlgorithms #CoevolutionaryAlgorithms #Cooptimization #CombinatorialOptimization #optimization
I never stopped using evolutionary computation. I'm even weirder and use coevolutionary algorithms. Unlike EC, the latter have a bad reputation as being difficult to apply, but if you know what you're doing (e.g. by reading my publications ๐) they're quite powerful in certain application areas. I've successfully applied them to designing resilient physical systems, discovering novel game-playing strategies, and driving online tutoring systems, among other areas. They can inform more conventional multi-objective optimization.
Many challenging problems are not easily "vectorized" or "numericized", but might have straightforward representations in discrete data structures. Combinatorial optimization problems can fall under this umbrella. Techniques that work directly with those representations can be orders of magnitude faster/smaller/cheaper than techniques requiring another layer of representation (natural language for LLMs, vectors of real values for neural networks). Sure, given enough time and resources clever people can work out a good numerical re-representation that allows a deep neural network to solve a problem, or prompt engineer an LLM. But why whack at your problem with a hammer when you have a precision instrument?
I started to put up notes about (my way of conceiving) coevolutionary algorithms on my web site, here. I stopped because it's a ton of work and nobody reads these as far as I can tell. Sound off if you read anything there!
#AI #GenAI #GenerativeAI #LLMs #EvolutionaryComputation #GeneticAlgorithms #GeneticProgramming #EvolutionaryAlgorithms #CoevolutionaryAlgorithms #Cooptimization #CombinatorialOptimization #optimization
Dr. Anna Latour
Constraints Journal
QIC Journal
Mohammad Hajiaghayi
