Shun-ichi Amari on how 'do as you like' freedom birthed the math behind AI's 60 years
FrnkNlsn · x · 2026-11-12
An in-depth IT Critique interview with Shun-ichi Amari, RIKEN honorary researcher whose 1967 theory of training multi-layer neural networks via stochastic gradient descent is a source of the work behind the 2024 Nobel Prize in Physics.
Amari recounts his evacuation-era childhood, landing in a newly founded mathematical engineering course after grades slipped amid student activism, and a mentor's advice to 'stay out of academic circles and see the world'—showing how free-form learning fostered originality. He also founded information geometry, a common mathematical basis for statistics, information theory, and machine learning.
More from AGI Musings
- CrewAI Founder: Anti-American-AI FUD Won't Stop Until Volatility Shakes You Out — robleclerc · 2026-11-12
- Kai-Fu Lee wraps 12-hour London blitz promoting 'AI Native' book launch — kaifulee · 2026-11-12
- Do closed AI labs' research agendas diverge? Talent flow acts as a penalty term — stochasticchasm · 2026-11-12
- AI 'doomers' call themselves 'the Cassandra fringe' — critic says the analogy flatters overconfidence — DrTechlash · 2026-11-12
- AI agent traffic reportedly grew 8x in just two months — Dr_Singularity · 2026-11-12
- Ten gems from Diogo's Code Summit talk: RLHF is part of the problem, software is back — TheTuringPost · 2026-11-12