Overparameterized neural networks implement associative memory

Abstract

Development of computational models of memory is a subject of long-standing interest at the intersection of machine learning and neuroscience. Our main finding is that overparameterized neural networks trained using standard optimization methods provide a simple mechanism for implementing associative memory. Remarkably, this mechanism allows for the storage and retrieval of sequences of examples. This finding also sheds light on inductive biases in overparameterized networks: while there are many functions that can achieve zero training loss in the overparameterized regime, our result shows that increasing depth and width in neural networks leads to maps that are more contractive around training examples, thereby allowing for storage and retrieval of more training examples.

Document Details

Document Type
Pub Defense Publication
Publication Date
Oct 16, 2020
Source ID
10.1073/pnas.2005013117

Entities

People

  • Adityanarayanan Radhakrishnan
  • Caroline Uhler
  • Mikhail A. Belkin

Organizations

  • Google
  • Massachusetts Institute of Technology
  • National Science Foundation
  • Nvidia
  • Office of Naval Research
  • Ohio State University
  • Simons Foundation

Tags

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks