English
Related papers

Related papers: Gauged Neural Network: Phase Structure, Learning, …

200 papers

How do humans and animals perform trial-and-error learning when the space of possibilities is infinite? In a previous study, we used an interval timing production task and discovered an updating strategy in which the agent adjusted the…

Neurons and Cognition · Quantitative Biology 2022-05-10 Jing Wang , Yousuf El-Jayyousi , Ilker Ozden

Recent generalizations of the Hopfield model of associative memories are able to store a number $P$ of random patterns that grows exponentially with the number $N$ of neurons, $P=\exp(\alpha N)$. Besides the huge storage capacity, another…

Disordered Systems and Neural Networks · Physics 2024-02-14 Carlo Lucibello , Marc Mézard

We investigate the role of the learning rate in a Kuramoto Model of coupled phase oscillators in which the coupling coefficients dynamically vary according to a Hebbian learning rule. According to the Hebbian theory, a synapse between two…

Adaptation and Self-Organizing Systems · Physics 2015-05-14 Ritwik K. Niyogi , L. Q. English

We introduce LeapfrogLayers, an invertible neural network architecture that can be trained to efficiently sample the topology of a 2D $U(1)$ lattice gauge theory. We show an improvement in the integrated autocorrelation time of the…

High Energy Physics - Lattice · Physics 2022-01-17 Sam Foreman , Xiao-Yong Jin , James C. Osborn

In neural network's Literature, Hebbian learning traditionally refers to the procedure by which the Hopfield model and its generalizations store archetypes (i.e., definite patterns that are experienced just once to form the synaptic…

Disordered Systems and Neural Networks · Physics 2024-02-21 Francesco Alemanno , Miriam Aquaro , Ido Kanter , Adriano Barra , Elena Agliari

How does the brain predict physical outcomes while acting in the world? Machine learning world models compress visual input into latent spaces, discarding the spatial structure that characterizes sensory cortex. We propose isomorphic world…

Neurons and Cognition · Quantitative Biology 2026-02-24 Joshua Nunley

We introduce a mixed-effects model to learn spatiotempo-ral patterns on a network by considering longitudinal measures distributed on a fixed graph. The data come from repeated observations of subjects at different time points which take…

Learning and the ability to learn are important factors in development and evolutionary processes [1]. Depending on the level, the complexity of learning can strongly vary. While associative learning can explain simple learning behaviour…

Neurons and Cognition · Quantitative Biology 2007-05-23 Reimer Kuehn , Ion-Olimpiu Stamatescu

Sequential activation of neurons is a common feature of network activity during a variety of behaviors, including working memory and decision making. Previous network models for sequences and memory emphasized specialized architectures in…

Neurons and Cognition · Quantitative Biology 2016-03-16 Kanaka Rajan , Christopher D Harvey , David W Tank

Ever since the last two decades of the past century pioneering studies in the field of statistical physics had focused their efforts on developing models of neural networks that could display memory storage and retrieval. Though many…

Disordered Systems and Neural Networks · Physics 2023-05-16 Enrico Ventura

We introduce a model of generalized Hebbian learning and retrieval in oscillatory neural networks modeling cortical areas such as hippocampus and olfactory cortex. Recent experiments have shown that synaptic plasticity depends on spike…

Disordered Systems and Neural Networks · Physics 2007-05-23 Silvia Scarpetta , Zhaoping Li , John Hertz

In \cite{Hop82}, Hopfield introduced a \emph{Hebbian} learning rule based neural network model and suggested how it can efficiently operate as an associative memory. Studying random binary patterns, he also uncovered that, if a small…

Machine Learning · Statistics 2024-03-05 Mihailo Stojnic

The Transformer architecture, underpinned by the self-attention mechanism, has become the de facto standard for sequence modeling tasks. However, its core computational primitive scales quadratically with sequence length (O(N^2)), creating…

Computation and Language · Computer Science 2025-09-03 Rishiraj Acharya

Leaky integrate-and-fire (LIF) models are mean-field limits, with a large number of neurons, used to describe neural networks. We consider inhomogeneous networks structured by a connec-tivity parameter (strengths of the synaptic weights)…

Neurons and Cognition · Quantitative Biology 2017-06-20 Benoît Perthame , Delphine Salort , Gilles Wainrib

The General Associative Memory Model (GAMM) has a constant state-dependant energy surface that leads the output dynamics to fixed points, retrieving single memories from a collection of memories that can be asynchronously preloaded. We…

Neural and Evolutionary Computing · Computer Science 2022-12-13 Arjun Karuvally , Terry J. Sejnowski , Hava T. Siegelmann

Recently, the possibility of quantum simulation of dynamical gauge fields was pointed out by using a system of cold atoms trapped on each link in an optical lattice. However, to implement exact local gauge invariance, fine-tuning the…

Quantum Physics · Physics 2015-06-12 Kenichi Kasamatsu , Ikuo Ichinose , Tetsuo Matsui

Associative memory, traditionally modeled by Hopfield networks, enables the retrieval of previously stored patterns from partial or noisy cues. Yet, the local computational principles which are required to enable this function remain…

A specific type of neural network, the Restricted Boltzmann Machine (RBM), is implemented for classification and feature detection in machine learning. RBM is characterized by separate layers of visible and hidden units, which are able to…

Disordered Systems and Neural Networks · Physics 2012-01-11 Adriano Barra , Alberto Bernacchia , Enrica Santucci , Pierluigi Contucci

We introduce and study a new model of interacting neural networks, incorporating the spatial dimension (e.g. position of neurons across the cortex) and some learning processes. The dynamic of each neural network is described via the elapsed…

Analysis of PDEs · Mathematics 2020-09-03 Delphine Salort , Nicolas Torres

We study a learning rule based upon the temporal correlation (weighted by a learning kernel) between incoming spikes and the internal state of the postsynaptic neuron, building upon previous studies of spike timing dependent synaptic…

Neurons and Cognition · Quantitative Biology 2007-05-23 Juergen Jost