In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval

Matthew Smart; Alberto Bietti; Anirvan M. Sengupta

2025 ICML ICML 2025

In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Matthew Smart, Alberto Bietti, Anirvan M. Sengupta

Topics

Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Transformers Artificial Intelligence > Core AI > Large Language Models

Keywords

associative memory retrieval modern hopfield network attention layer gradient descent update in-context denoising one-layer transformer

Download PDF