Tight Genes: Intro to Genetic Algorithms
summary
Genetic algorithms are shown working with concrete numbers: demos use population of 10 candidates, single-point crossover, and a 1-in-4 mutation chance, stopping after 100-generation no-improvement stop. Ruby code generates truckload knapsack runs that start with a $20,000 best and evolve to $26,000, and D&D stat evolution finds an 18 strength/Constitution fighter after several generations and a wizard after 11. The approach mirrors NASA’s 2005 ST5 antenna design (launched 2006) where surprising, nonintuitive shapes win once a simulator provides a fitness score.
AI-written summary · about
chapters (9)
- 0:00Introduction to genetic algorithms
- 4:58How genetic algorithms work
- 8:25Creating candidate solutions
- 14:34Fitness function explained
- 19:13Breeding and selection methods
- 23:25Mutation for diversity
- 27:19When to use genetic algorithms
- 39:41Key takeaways and recap
- 40:24Q&A session
related talks
46mTight Genes: Intro to Genetic Algorithms
46mTight Genes: Intro to Genetic Algorithms
57mSolutions That Evolve: Building Self-Improving Systems with Genetic Algorithms
24mGenetic Algorithms in Go
46mBeing Creative with Genetic Algorithms and Typeclasses
30mEvolutionary Algorithms Perfecting the Art of "Good Enough"
01h 26mHow to Evolve Your Way Out of a Paper Bag
42mLet's Talk About Sex: Breeding Programs with Evolution