DigiNews

Tech Watch by Johan Denoyer

← Back to articles

Human-like Neural Nets by Catapulting

Quality: 8/10 Relevance: 9/10

Summary

Explores speculative method of building human-like NNs by catapulting through extreme overparameterization and high-learning-rate training to induce generalization. Links concepts like grokking, isoperimetry, and dynamic evaluation to discuss how such regimes could affect AI robustness, alignment, and scalability, and outlines potential experiments, datasets, and hardware considerations.

🚀 Service construit par Johan Denoyer