中文
相关论文

相关论文: The Capacity of Modern Hopfield Networks under the…

200 篇论文

This paper examines the memory capacity of generalized neural networks. Hopfield networks trained with a variety of learning techniques are investigated for their capacity both for binary and non-binary alphabets. It is shown that the…

神经与进化计算 · 计算机科学 2013-07-31 Matt Stowe , Subhash Kak

Understanding the memory capacity of neural networks remains a challenging problem in implementing artificial intelligence systems. In this paper, we address the notion of capacity with respect to Hopfield networks and propose a dynamic…

神经与进化计算 · 计算机科学 2017-09-19 Saarthak Sarup , Mingoo Seok

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…

无序系统与神经网络 · 物理学 2024-02-14 Carlo Lucibello , Marc Mézard

The structure of continuous Hopfield networks is revisited from a system-theoretic point of view. After adopting a novel electrical network interpretation involving nonlinear capacitors, it is shown that Hopfield networks admit a…

最优化与控制 · 数学 2026-01-07 Arjan van der Schaft

The gap between the huge volumes of data needed to train artificial neural networks and the relatively small amount of data needed by their biological counterparts is a central puzzle in machine learning. Here, inspired by biological…

无序系统与神经网络 · 物理学 2022-04-19 Miriam Aquaro , Francesco Alemanno , Ido Kanter , Fabrizio Durante , Elena Agliari , Adriano Barra

The Little-Hopfield network is an auto-associative computational model of neural memory storage and retrieval. This model is known to robustly store collections of randomly generated binary patterns as stable-states of the network dynamics.…

神经元与认知 · 定量生物学 2015-04-30 Christopher Hillar , Ngoc Tran , Kilian Koepsell

Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving high-capacity storage of long sequences in classical…

机器学习 · 计算机科学 2026-05-26 Aakash Kumar , Anatoly Khina , Frederik Mallmann-Trenn , Emanuele Natale

The Hopfield recurrent neural network is a classical auto-associative model of memory, in which collections of symmetrically-coupled McCulloch-Pitts neurons interact to perform emergent computation. Although previous researchers have…

适应与自组织系统 · 物理学 2015-06-09 Christopher Hillar , Ngoc M. Tran

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…

机器学习 · 统计学 2024-03-05 Mihailo Stojnic

In a recent paper ``The capacity of the Hopfield model, J. Feng and B. Tirozzi claim to prove rigorous results on the storage capacity that are in conflict with the predictions of the replica approach. We show that their results are in…

无序系统与神经网络 · 物理学 2009-10-30 Anton Bovier

Recent research has established a connection between modern Hopfield networks (HNs) and transformer attention heads, with guarantees of exponential storage capacity. However, these models still face challenges scaling storage efficiently.…

机器学习 · 计算机科学 2025-04-11 Saul Santos , António Farinhas , Daniel C. McNamee , André F. T. Martins

We analyze the storage capacity of the Hopfield models on classes of random graphs. While such a setup has been analyzed for the case that the underlying random graph model is an Erd\"{o}s-Renyi graph, other architectures, including those…

概率论 · 数学 2015-07-29 Matthias Löwe , Franck Vermet

Hopfield networks are artificial neural networks which store memory patterns on the states of their neurons by choosing recurrent connection weights and update rules such that the energy landscape of the network forms attractors around the…

神经与进化计算 · 计算机科学 2023-05-10 Thomas F Burns , Tomoki Fukai

A prevalent assumption regarding real-world data is that it lies on or close to a low-dimensional manifold. When deploying a neural network on data manifolds, the required size, i.e., the number of neurons of the network, heavily depends on…

机器学习 · 计算机科学 2024-10-30 Jiachen Yao , Mayank Goswami , Chao Chen

We investigate the computational limits of the memory retrieval dynamics of modern Hopfield models from the fine-grained complexity analysis. Our key contribution is the characterization of a phase transition behavior in the efficiency of…

机器学习 · 计算机科学 2024-06-04 Jerry Yao-Chieh Hu , Thomas Lin , Zhao Song , Han Liu

We propose and analyze a new variation of the so-called {\em exponential Hopfield model}, a recently introduced family of associative neural networks with unprecedented storage capacity. Our construction is based on a cost function defined…

无序系统与神经网络 · 物理学 2025-09-09 Linda Albanese , Andrea Alessandrelli , Adriano Barra , Peter Sollich

In the Hopfield model the ability of the network to generalization is studied in the case of the network trained by one input image ({\it the standard}).

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

Unsupervised learning in a generalized Hopfield associative-memory network is investigated in this work. First, we prove that the (generalized) Hopfield model is equivalent to a semi-restricted Boltzmann machine with a layer of visible…

神经与进化计算 · 计算机科学 2017-07-26 Huiling Zhen , Shang-Nan Wang , Hai-Jun Zhou

The Hopfield model is a pioneering neural network model with associative memory retrieval. The analytical solution of the model in mean field limit revealed that memories can be retrieved without any error up to a finite storage capacity of…

无序系统与神经网络 · 物理学 2017-10-31 Do-Hyun Kim , Jinha Park , B. Kahng

The Hopfield model is a paradigmatic model of neural networks that has been analyzed for many decades in the statistical physics, neuroscience, and machine learning communities. Inspired by the manifold hypothesis in machine learning, we…

无序系统与神经网络 · 物理学 2023-05-01 Matteo Negri , Clarissa Lauditi , Gabriele Perugini , Carlo Lucibello , Enrico Malatesta
‹ 上一页 1 2 3 10 下一页 ›