English
Related papers

Related papers: Hierarchical Associative Memory

200 papers

We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow/fast analysis to derive an averaged system whose dynamics…

Neurons and Cognition · Quantitative Biology 2011-02-02 Mathieu N. Galtier , Olivier D. Faugeras , Paul C. Bressloff

We introduce a novel approach to endowing neural networks with emergent, long-term, large-scale memory. Distinct from strategies that connect neural networks to external memory banks via intricately crafted controllers and hand-designed…

Machine Learning · Computer Science 2020-08-18 Tri Huynh , Michael Maire , Matthew R. Walter

An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its…

Machine Learning · Statistics 2016-11-30 Arya Mazumdar , Ankit Singh Rawat

We study the optimal memorization capacity of modern Hopfield models and Kernelized Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories. We present a tight analysis by establishing a connection between the…

Machine Learning · Statistics 2024-11-04 Jerry Yao-Chieh Hu , Dennis Wu , Han Liu

The task of a neural associative memory is to retrieve a set of previously memorized patterns from their noisy versions using a network of neurons. An ideal network should have the ability to 1) learn a set of patterns as they arrive, 2)…

Neural and Evolutionary Computing · Computer Science 2014-07-25 Amin Karbasi , Amir Hesam Salavati , Amin Shokrollahi

A synfire chain is a simple neural network model which can propagate stable synchronous spikes called a pulse packet and widely researched. However how synfire chains coexist in one network remains to be elucidated. We have studied the…

Neurons and Cognition · Quantitative Biology 2009-11-13 Kazuya Ishibashi , Kosuke Hamaguchi , Masato Okada

An important difference between brains and deep neural networks is the way they learn. Nervous systems learn online where a stream of noisy data points are presented in a non-independent, identically distributed (non-i.i.d.) way. Further,…

Neural and Evolutionary Computing · Computer Science 2023-07-28 Nick Alonso , Jeff Krichmar

We propose a dynamical neural network model with a hierarchical and modular structure. The network architecture can be derived by minimizing an energy function that is originally designed based on two kinds of neurons with quite different…

Neurons and Cognition · Quantitative Biology 2026-04-14 Kazuyoshi Tsutsumi , Ernst Niebur

Increasing the size of a Transformer does not always lead to enhanced performance. This phenomenon cannot be explained by the empirical scaling laws. Furthermore, the model's enhanced performance is closely associated with its memorization…

Machine Learning · Computer Science 2024-12-02 Xueyan Niu , Bo Bai , Lei Deng , Wei Han

This paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been proposed, and different sequence learning models have been…

Neural and Evolutionary Computing · Computer Science 2007-05-23 J. Bose , S. B. Furber , J. L. Shapiro

We complement our previous work [arxiv: 0707.0565] with the full (non diluted) solution describing the stable states of an attractor network that stores correlated patterns of activity. The new solution provides a good fit of simulations of…

Disordered Systems and Neural Networks · Physics 2007-07-23 Emilio Kropff

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Machine Learning · Computer Science 2020-07-01 Antonio Carta , Alessandro Sperduti , Davide Bacciu

Most deep learning models are limited to specific datasets or tasks because of network structures using fixed layers. In this paper, we discuss the differences between existing neural networks and real human neurons, propose association…

Artificial Intelligence · Computer Science 2023-01-31 Seokjun Kim , Jaeeun Jang , Hyeoncheol Kim

Associative memory models based on Hopfield networks and self-attention based on key-value mechanisms have been popular approaches in the study of memory mechanisms in deep learning. It has been pointed out that the state update rule of the…

Machine Learning · Computer Science 2025-11-27 Tsubasa Masumura , Masato Taki

Despite significant advances in graph representation learning, little attention has been paid to the more practical continual learning scenario in which new categories of nodes (e.g., new research areas in citation networks, or new types of…

Machine Learning · Computer Science 2021-12-01 Xikun Zhang , Dongjin Song , Dacheng Tao

In this study we introduce a novel energy functional for long-sequence memory, building upon the framework of dense Hopfield networks which achieves exponential storage capacity through higher-order interactions. Building upon earlier work…

Machine Learning · Computer Science 2025-07-03 Ahmed Farooq

Codifying memories is one of the fundamental problems of modern Neuroscience. The functional mechanisms behind this phenomenon remain largely unknown. Experimental evidence suggests that some of the memory functions are performed by…

Neurons and Cognition · Quantitative Biology 2022-05-17 Ivan Y. Tyukin , Alexander N. Gorban , Carlos Calvo , Julia Makarova , Valeri A. Makarov

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

Machine Learning · Computer Science 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

While Hopfield networks are known as paradigmatic models for memory storage and retrieval, modern artificial intelligence systems mainly stand on the machine learning paradigm. We show that it is possible to formulate a teacher-student…

Disordered Systems and Neural Networks · Physics 2024-01-02 Francesco Alemanno , Luca Camanzi , Gianluca Manzan , Daniele Tantari

The neuronal paradigm of studying the brain has left us with limitations in both our understanding of how neurons process information to achieve biological intelligence and how such knowledge may be translated into artificial intelligence…

Neurons and Cognition · Quantitative Biology 2020-05-12 Leo Kozachkov , Konstantinos P. Michmizos