中文
相关论文

相关论文: Phase Diagram and Storage Capacity of Sequence Pro…

200 篇论文

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

Studies have been made on the phase transition phenomena of an oscillator network model based on a standard Hebb learning rule like the Hopfield model. The relative phase informations---the in-phase and anti-phase, can be embedded in the…

无序系统与神经网络 · 物理学 2014-09-08 Toru Aonishi

We investigate the maximum number of embedded patterns in the two-dimensional Hopfield model. The grand state energies of two specific network states, namely, the energies of the pure-ferromagnetic state and the state of specific one stored…

无序系统与神经网络 · 物理学 2009-11-07 Shinsuke Koyama

A recent dynamic mean-field theory for sequence processing in fully connected neural networks of Hopfield-type (During, Coolen and Sherrington, 1998) is extended and analized here for a symmetrically diluted network with finite connectivity…

无序系统与神经网络 · 物理学 2009-11-10 W. K. Theumann

We study a simple extended model of oscillator neural networks capable of storing sparsely coded phase patterns, in which information is encoded both in the mean firing rate and in the timing of spikes. Applying the methods of statistical…

无序系统与神经网络 · 物理学 2009-10-31 Masaki Nomura , Toshio Aoyagi

Transformer-based models have demonstrated exceptional performance across diverse domains, becoming the state-of-the-art solution for addressing sequential machine learning problems. Even though we have a general understanding of the…

无序系统与神经网络 · 物理学 2024-06-12 Ángel Poc-López , Miguel Aguilera

We study the storage of multiple phase-coded patterns as stable dynamical attractors in recurrent neural networks with sparse connectivity. To determine the synaptic strength of existent connections and store the phase-coded patterns, we…

神经元与认知 · 定量生物学 2015-05-28 Siliva Scarpetta , Ferdinando Giacco , Antonio de Candia

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

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

The dynamics and the stationary states for the competition between pattern reconstruction and asymmetric sequence processing are studied here in an exactly solvable feed-forward layered neural network model of binary units and patterns near…

无序系统与神经网络 · 物理学 2009-11-11 F. L. Metz , W. K. Theumann

Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfield associative memory model, well beyond the limits obtained previously. We investigate the properties of new fixed points to discover that…

无序系统与神经网络 · 物理学 2017-11-22 Jacopo Rocchi , David Saad , Daniele Tantari

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 introduce a spherical Hopfield-type neural network involving neurons and patterns that are continuous variables. We study both the thermodynamics and dynamics of this model. In order to have a retrieval phase a quartic term is added to…

无序系统与神经网络 · 物理学 2009-11-10 D. Bolle , Th. M. Nieuwenhuizen , I. Perez Castillo , T. Verbeiren

The dynamics of an extremely diluted neural network with high order synapses acting as corrections to the Hopfield model is investigated. As in the fully connected case, the high order terms may strongly improve the storage capacity of the…

凝聚态物理 · 物理学 2009-10-22 N. Lemke , J. J. Arenzon , F. A. Tamarit

Continuous-Time Recurrent Neural Networks (CTRNNs) have been widely used for their capacity to model complex temporal behaviour. However, their internal dynamics often remain difficult to interpret. In this paper, we propose a new class of…

无序系统与神经网络 · 物理学 2025-11-17 Miguel Aguilera , Daniele De Martino , Ivan Garashchuk , Dmitry Sinelshchikov

The synchronous dynamics and the stationary states of a recurrent attractor neural network model with competing synapses between symmetric sequence processing and Hebbian pattern reconstruction is studied in this work allowing for the…

无序系统与神经网络 · 物理学 2015-05-13 F. L. Metz , W. K. Theumann

The thermodynamic and retrieval properties of the Ashkin-Teller neural network model storing an infinite number of patterns are examined in the replica-symmetric mean-field approximation. In particular, for linked patterns…

无序系统与神经网络 · 物理学 2009-10-31 D. Bolle , P. Kozlowski

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

Associative memory models retrieve stored information through content-based addressing, mimicking the neural processes of animal brains. The classical Hopfield network-based models store memories as vectors of discrete values and have good…

神经元与认知 · 定量生物学 2026-01-21 Nurani Rajagopal Rohan , V. Srinivasa Chakravarthy , Sayan Gupta

We present results for two different kinds of high order connections between neurons acting as corrections to the Hopfield model. Equilibrium properties are analyzed using the replica mean-field theory and compared with numerical…

凝聚态物理 · 物理学 2009-10-22 J. J. Arenzon , R. M. C. de Almeida
‹ 上一页 1 2 3 10 下一页 ›