Researchers use statistical physics and "toy models" to explain how neural networks avoid overfitting and stabilize learning in high-dimensional spaces.

Ernie Smith is a former contributor to BizTech, an old-school blogger who specializes in side projects, and a tech history nut who researches vintage operating systems for fun. In data analysis, it is ...

Physics meets AI: Harvard scientists applied renormalization theory to a simplified model, revealing how large neural networks stabilize learning in high‑dimensional spaces. Scaling mystery solved?: ...

Overfitting in ML is when a model learns training data too well, failing on new data. Investors should avoid overfitting as it mirrors risks of betting on past stock performances. Techniques like ...

Two new research efforts are offering deeper insight into how artificial intelligence can be made safer and more effective. Harvard physicists have developed a simplified, physics-inspired model to ...