Arrow Research search
Back to ICML

ICML 2020

Associative Memory in Iterated Overparameterized Sigmoid Autoencoders

Conference Paper Accepted Paper Artificial Intelligence ยท Machine Learning

Abstract

Recent work showed that overparameterized autoencoders can be trained to implement associative memory via iterative maps, when the trained input-output Jacobian of the network has all of its eigenvalue norms strictly below one. Here, we theoretically analyze this phenomenon for sigmoid networks by leveraging recent developments in deep learning theory, especially the correspondence between training neural networks in the infinite-width limit and performing kernel regression with the Neural Tangent Kernel (NTK). We find that overparameterized sigmoid autoencoders can have attractors in the NTK limit for both training with a single example and multiple examples under certain conditions. In particular, for multiple training examples, we find that the norm of the largest Jacobian eigenvalue drops below one with increasing input norm, leading to associative memory.

Authors

Keywords

No keywords are indexed for this paper.

Context

Venue
International Conference on Machine Learning
Archive span
1993-2025
Indexed papers
16471
Paper id
1052574779941918478
v2026.09.13