Neural-Speciation. An evolutionary engine for micro-transformers that optimizes initialization hyperparameters. Uses unsupervised clustering to discover distinct "species" of learning strategies that convergently evolve for rapid generalization. Includes 3D phylogenetic mapping tools to visualize the mathematical landscape of learning.

github.com/Mmorgan-ML/Neural-Speciation

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.