Nonlinear discriminant functions and associative memories

By Demetri Psaltis, C. Park. 1987

Subfields: Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

1. Stephen Grossberg
2. Günter Klambauer
3. Dmitry Krotov
4. Sepp Hochreiter
5. Hubert Ramsauer
6. Angela Bitto-Nemling
7. Markus Holzleitner
8. John J. Hopfield

Citations in the corpus

• CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, background): “Their storage capacity can be considerably increased by polynomial terms in the energy function (Chen et al., 1986; Psaltis & Cheol, 1986; Baldi & Venkatesh, 1987; Gardner, 1987; Abbott & Arian, 1987; Horn & Usher, 1988; Caputo & Niemann, 2002; Krotov & Hopfield, 2016).”
• Dense Associative Memory for Pattern Recognition (2016, methodology): “For the case of polynomial energy function a very similar family of models was considered in [11, 12, 13, 14, 15, 16].”
• Nonlinear neural networks: Principles, mechanisms, and architectures (1988, methodology): “Inspired by an interest in brain modeling, Widrow (1962) developed his classical gradient descent Adeline adaptive pattern recognition machine before using this background to make his major contributions to the theory of adaptive antennas.”
• History Compression via Language Models in Reinforcement Learning (2022, background): “Their storage capacity can be considerably increased by polynomial terms in the energy function (Chen et al., 1987; Psaltis & Park, 1986; Baldi & Venkatesh, 1987; Gardner, 1987; Abbott & Arian, 1987; Horn & Usher, 1988; Caputo & Niemann, 2002; Krotov & Hopfield, 2016).”