Thomas F Burns

2 accepted papers

2024

Semantically-correlated memories in a dense associative model

ICML 2024poster

I introduce a novel associative memory model named *Correlated Dense Associative Memory* (CDAM), which integrates both auto- and hetero-association in a unified framework for continuous-valued memory patterns. Employing an arbitrary graph structure to semantically link memory patterns, CDAM is theor…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2023

Simplicial Hopfield networks

Thomas F Burns, Tomoki Fukai

ICLR 2023poster

Hopfield networks are artificial neural networks which store memory patterns on the states of their neurons by choosing recurrent connection weights and update rules such that the energy landscape of the network forms attractors around the memories. How many stable, sufficiently-attracting memory pa…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗