QFT and neural nets: the basic idea — LessWrong

Previously in the series: The laws of large numbers and Basics of Bayesian learning. • Reminders: formalizing learning in ML and Bayesian learning …

x QFT and neural nets: the basic idea — LessWrong Interpretability (ML & AI) Physics AI Frontpage 28 QFT and neural nets: the basic idea by Dmitry Vaintrob 24th Jan 2025 10 min read 0 28 Previously in the series: The laws of large numbers and Basics of Bayesian learning . Reminders: formalizing learning in ML and Bayesian learning Learning and inference in neural nets and Bayesian models As a very basic sketch, in order to specify an ML algorithm one needs five pieces of data. An architecture : i.e., a parametrized space of functions that associates to each weight vector θ ∈ R w a function f θ

related reading

• Bayesian Neural Networkscs.toronto.edu
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• On neural scaling and the quanta hypothesisericjmichaud.com
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Zoom In: An Introduction to Circuitsdistill.pub
• A Comprehensive Introduction to Bayesian Deep Learning - Joris Baanjorisbaan.nl
• The Little Book of Deep Learningfleuret.org
• NL.pdfabehrouz.github.io
• A Recipe for Training Neural Networkskarpathy.github.io
• arxiv.org/pdf/1805.08522arxiv.org
• Statistical Mechanics of Deep Learningganguli-gang.stanford.edu