PIRSA:25040093 Conference

DOI10.48660/25040093

Conference/School: Theory + AI Workshop: Theoretical Physics for AI

Loureiro, B. (2025). Statistical physics of learning with two-layer neural networks. Perimeter Institute. https://pirsa.org/25040093

Loureiro, Bruno. Statistical physics of learning with two-layer neural networks. Perimeter Institute, Apr. 10, 2025, https://pirsa.org/25040093 

@misc{ pirsa_PIRSA:25040093,
  doi = {10.48660/25040093},
  url = {https://pirsa.org/25040093},
  author = {Loureiro, Bruno},
  keywords = {},
  language = {en},
  title = {Statistical physics of learning with two-layer neural networks},
  publisher = {Perimeter Institute},
  year = {2025},
  month = {apr},
  note = {PIRSA:25040093 see, \url{https://pirsa.org}}
}

Abstract

Feature learning - or the capacity of neural networks to adapt to the data during training - is often quoted as one of the fundamental reasons behind their unreasonable effectiveness. Yet, making mathematical sense of this seemingly clear intuition is still a largely open question. In this talk, I will discuss a simple setting where we can precisely characterise how features are learned by a two-layer neural network during the very first few steps of training, and how these features are essential for the network to efficiently generalise under limited availability of data.

Resources

Next talk