paper-with-me

Papers

Dense Associative Memory for Pattern Recognition

2016-06-03 · NeurIPS 2016 12 · Dmitry Krotov, John J. Hopfield

A model of associative memory is studied, which stores and reliably retrieves many more patterns than the number of neurons in the network. We propose a simple duality between this dense associative memory and neural networks commonly used in deep learning. On the associative memory side of this duality, a family of models that smoothly interpolates between two limiting cases can be constructed. One limit is referred to as the feature-matching mode of pattern recognition, and the other one as the prototype regime. On the deep learning side of the duality, this family corresponds to feedforward neural networks with one hidden layer and various activation functions, which transmit the activities of the visible neurons to the hidden layer. This family of activation functions includes logistics, rectified linear units, and rectified polynomials of higher degrees. The proposed duality makes it possible to apply energy-based intuition from associative memory to analyze computational properties of neural networks with unusual activation functions - the higher rectified polynomials which until now have not been used in deep learning. The utility of the dense memories is illustrated for two test cases: the logical gate XOR and the recognition of handwritten digits from the MNIST data set.

📄 PDF Abstract BibTeX arXiv:1606.01164

Code (3)

dimakrotov/dense_associative_memory
hmcalister/hopfield-network-pytorch pytorch
nacer-eb/krotovhopfieldwaddington tf

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Higher-Order Kuramoto Oscillator Network for Dense Associative Memory

2025-07-29 · Jona Nagerl, Natalia G. Berloff arxiv

Networks of phase oscillators can serve as dense associative memories if they incorporate higher-order coupling beyond the classical Kuramoto model's pairwise interactions. Here we introduce a generalized Kuramoto model …

Dense Associative Memory Through the Lens of Random Features

2024-10-31 · Benjamin Hoover, Duen Horng Chau, Hendrik Strobelt, Parikshit Ram 외

Dense Associative Memories are high storage capacity variants of the Hopfield networks that are capable of storing a large number of memory patterns in the weights of the network of a given size. Their common formulation…

Neural networks with redundant representation: detecting the undetectable

2019-11-28 · Elena Agliari, Francesco Alemanno, Adriano Barra, Martino Centonze 외

We consider a three-layer Sejnowski machine and show that features learnt via contrastive divergence have a dual representation as patterns in a dense associative memory of order P=4. The latter is known to be able to He…

Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory

2026-04-08 · Tatiana Petrova, Evgeny Polyachenko, Radu State arxiv

We study the thermodynamic memory capacity of modern Hopfield networks (Dense Associative Memory models) with continuous states under geometric constraints, extending classical analyses of pairwise associative memory. We…

Semantically-correlated memories in a dense associative model

2024-04-10 · Thomas F Burns

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…

Image RetrievalmodelRetrievalTemporal Sequences