Universal Hopfield networks: a general framework for single-shot associative memory models
A large number of neural network models of associative memory have been proposed in the literature. These include the classical Hopfield networks (HNs), sparse distributed memories (SDMs), and more recently the modern continuous Hopfield networks (MCHNs), which possess close links with self-attentio...
Main Authors: | Millidge, B, Salvatori, T, Song, Y, Lukasiewicz, T, Bogacz, R |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Proceedings of Machine Learning Research
2022
|
Similar Items
-
Recurrent predictive coding models for associative memory employing covariance learning
by: Tang, M, et al.
Published: (2023) -
Recurrent predictive coding models for associative memory employing covariance learning.
by: Mufeng Tang, et al.
Published: (2023-04-01) -
Inferring neural activity before plasticity as a foundation for learning beyond backpropagation
by: Song, Y, et al.
Published: (2024) -
Learning on arbitrary graph topologies via predictive coding
by: Salvatori, T, et al.
Published: (2023) -
Associative memories via predictive coding
by: Salvatori, T, et al.
Published: (2021)