中文
相关论文

相关论文: A spectral approach to Hebbian-like neural network…

200 篇论文

Neural networks with recurrent asymmetric couplings are important to understand how episodic memories are encoded in the brain. Here, we integrate the experimental observation of wide synaptic integration window into our model of sequence…

神经元与认知 · 定量生物学 2023-02-10 Zijian Jiang , Ziming Chen , Tianqi Hou , Haiping Huang

The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is $\alpha \sim 0.14$, far from the…

神经与进化计算 · 计算机科学 2018-10-30 Alberto Fachechi , Elena Agliari , Adriano Barra

This article delves into the Hopfield neural network model, drawing inspiration from biological neural systems. The exploration begins with an overview of the model's foundations, incorporating insights from mechanical statistics to deepen…

无序系统与神经网络 · 物理学 2024-10-29 Matteo Silvestri

Associative memory is a fundamental function in the brain. Here, we generalize the standard associative memory model to include long-range Hebbian interactions at the learning stage, corresponding to a large synaptic integration window. In…

无序系统与神经网络 · 物理学 2021-12-21 Jianwen Zhou , Zijian Jiang , Tianqi Hou , Ziming Chen , K Y Michael Wong , Haiping Huang

Among the performance-enhancing procedures for Hopfield-type networks that implement associative memory, Hebbian Unlearning (or dreaming) strikes for its simplicity and its clear biological interpretation. Yet, it does not easily lend…

无序系统与神经网络 · 物理学 2023-08-28 Marco Benedetti , Louis Carillo , Enzo Marinari , Marc Mèzard

Recent works have highlighted the need for a new dynamical paradigm in the modeling of brain function and evolution. Specifically, these models should incorporate non-constant and asymmetric synaptic weights $T_{ij}$ in the neuron-neuron…

神经元与认知 · 定量生物学 2025-11-03 Franco Cardin , Alberto Lovison , Amos Maritan , Aram Megighian

The paper examines the problem of accessing a vector memory from a single neuron in a Hebbian neural network. It begins with the review of the author's earlier method, which is different from the Hopfield model in that it recruits…

神经与进化计算 · 计算机科学 2009-05-26 Subhash Kak

We consider $L$-directional associative memories, composed of $L$ Hopfield networks, displaying imitative Hebbian intra-network interactions and anti-imitative Hebbian inter-network interactions, where couplings are built over a set of…

无序系统与神经网络 · 物理学 2025-04-11 Elena Agliari , Andrea Alessandrelli , Paulo Duarte Mourao , Alberto Fachechi

A set of fixed points of the Hopfield type neural network was under investigation. Its connection matrix is constructed with regard to the Hebb rule from a highly symmetric set of the memorized patterns. Depending on the external parameter…

生物物理 · 物理学 2007-05-23 Hong-Liang Lu , Xi-Jun Qiu

In this work we introduce a multi-species generalization of the Hopfield model for associative memory, where neurons are divided into groups and both inter-groups and intra-groups pair-wise interactions are considered, with different…

无序系统与神经网络 · 物理学 2018-07-11 Elena Agliari , Danila Migliozzi , Daniele Tantari

We introduce a three-dimensional vectorial extension of the Hopfield associative-memory model in which each neuron is a unit vector on $S^2$ and synaptic couplings are $3\times 3$ blocks generated through a vectorial Hebbian rule. The…

无序系统与神经网络 · 物理学 2025-12-10 F. Gallavotti , A. Zaccone

Through a redefinition of patterns in an Hopfield-like model, we introduce and develop an approach to model discrete systems made up of many, interacting components with inner degrees of freedom. Our approach clarifies the intrinsic…

统计力学 · 物理学 2015-05-19 Elena Agliari , Adriano Barra

The network embedding task is to represent the node in the network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix,…

机器学习 · 计算机科学 2022-09-01 Yuchen Liang , Dmitry Krotov , Mohammed J. Zaki

A set of fixed points of the Hopfield type neural network is under investigation. Its connection matrix is constructed with regard to the Hebb rule from a highly symmetric set of the memorized patterns. Depending on the external parameter…

无序系统与神经网络 · 物理学 2007-05-23 Leonid B. Litinsky

Sequence memory is an essential attribute of natural and artificial intelligence that enables agents to encode, store, and retrieve complex sequences of stimuli and actions. Computational models of sequence memory have been proposed where…

神经与进化计算 · 计算机科学 2023-11-06 Hamza Tahir Chaudhry , Jacob A. Zavatone-Veth , Dmitry Krotov , Cengiz Pehlevan

The Hebbian unlearning algorithm, i.e. an unsupervised local procedure used to improve the retrieval properties in Hopfield-like neural networks, is numerically compared to a supervised algorithm to train a linear symmetric perceptron. We…

无序系统与神经网络 · 物理学 2022-03-15 Marco Benedetti , Enrico Ventura , Enzo Marinari , Giancarlo Ruocco , Francesco Zamponi

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…

神经与进化计算 · 计算机科学 2022-06-20 Beren Millidge , Tommaso Salvatori , Yuhang Song , Thomas Lukasiewicz , Rafal Bogacz

We consider Hopfield networks, where neurons interact pair-wise by Hebbian couplings built over $i$. a set of definite patterns (ground truths), $ii$. a sample of labeled examples (supervised setting), $iii$. a sample of unlabeled examples…

无序系统与神经网络 · 物理学 2025-10-16 Elena Agliari , Alberto Fachechi , Domenico Luongo

In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal…

机器学习 · 计算机科学 2024-02-21 Elena Agliari , Francesco Alemanno , Miriam Aquaro , Alberto Fachechi

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…

无序系统与神经网络 · 物理学 2024-02-21 Francesco Alemanno , Miriam Aquaro , Ido Kanter , Adriano Barra , Elena Agliari
‹ 上一页 1 2 3 10 下一页 ›