中文
相关论文

相关论文: Diluted neural networks with adapting and correlat…

200 篇论文

We show that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance. We focus on the representative case of learning random patterns with binary…

无序系统与神经网络 · 物理学 2015-09-21 Carlo Baldassi , Alessandro Ingrosso , Carlo Lucibello , Luca Saglietti , Riccardo Zecchina

The effects of a variable amount of random dilution of the synaptic couplings in Q-Ising multi-state neural networks with Hebbian learning are examined. A fraction of the couplings is explicitly allowed to be anti-Hebbian. Random dilution…

无序系统与神经网络 · 物理学 2009-11-10 D. Bolle , J. Busquets Blanco , T. Verbeiren

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

A fundamental question in neuroscience is how structure and function of neural systems are related. We study this interplay by combining a familiar auto-associative neural network with an evolving mechanism for the birth and death of…

适应与自组织系统 · 物理学 2019-04-26 Ana P. Millán , J. J. Torres , S. Johnson , J. Marro

Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from…

计算机视觉与模式识别 · 计算机科学 2021-03-16 Binghan Li , Yindong Hua , Yifeng Liu , Mi Lu

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task related neural dynamics we study trained Recurrent Neural Networks. We develop a Mean Field Theory for Reservoir Computing…

神经元与认知 · 定量生物学 2017-06-28 Alexander Rivkind , Omri Barak

We investigate a disordered multi-dimensional linear system in which the interaction parameters vary stochastically in time with defined temporal correlations. We refer to this type of disorder as "annealed", in contrast to quenched…

无序系统与神经网络 · 物理学 2025-02-07 Francesco Ferraro , Christian Grilletta , Amos Maritan , Samir Suweis , Sandro Azaele

Synaptic plasticity allows cortical circuits to learn new tasks and to adapt to changing environments. How do cortical circuits use plasticity to acquire functions such as decision-making or working memory? Neurons are connected in complex…

神经元与认知 · 定量生物学 2023-03-08 Néstor Parga , Luis Serrano-Fernández , Joan Falcó-Roget

Deep Neural Networks (DNNs) rely on inherent fluctuations in their internal parameters (weights and biases) to effectively navigate the complex optimization landscape and achieve robust performance. While these fluctuations are recognized…

机器学习 · 计算机科学 2025-11-14 Darsh Pareek , Umesh Kumar , Ruthu Rao , Ravi Janjam

Neural activity exhibits a vast range of timescales that can be several fold larger than the membrane time constant of individual neurons. Two types of mechanisms have been proposed to explain this conundrum. One possibility is that large…

神经元与认知 · 定量生物学 2019-03-26 Manuel Beiran , Srdjan Ostojic

Understanding how the brain learns to compute functions reliably, efficiently and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could…

神经元与认知 · 定量生物学 2017-05-24 Sophie Denève , Alireza Alemi , Ralph Bourdoukan

The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This…

无序系统与神经网络 · 物理学 2017-02-08 Wolfgang Kinzel

Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost. However, this comes at the price of losing granularity in the…

计算机视觉与模式识别 · 计算机科学 2023-05-17 Robin Hesse , Simone Schaub-Meyer , Stefan Roth

The parallel dynamics of the asymmetric extremely diluted Ashkin-Teller neural network is studied using signal-to-noise analysis techniques. Evolution equations for the order parameters are derived, both at zero and finite temperature. The…

无序系统与神经网络 · 物理学 2015-06-25 D. Bolle' , G. Jongen

A dynamical neural network consists of a set of interconnected neurons that interact over time continuously. It can exhibit computational properties in the sense that the dynamical system's evolution and/or limit points in the associated…

机器学习 · 计算机科学 2018-05-24 Tsung-Han Lin , Ping Tak Peter Tang

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

机器学习 · 计算机科学 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

From the proliferative mechanisms generating neurons from progenitor cells to neuron migration and synaptic connection formation, several vicissitudes culminate in the mature brain. Both component loss and gain remain ubiquitous during…

神经元与认知 · 定量生物学 2024-08-06 Rodrigo Siqueira Kazu , Kleber Neves , Bruno Mota

In this work we solve the dynamics of pattern diluted associative networks, evolving via sequential Glauber update. We derive dynamical equations for the order parameters, that quantify the simultaneous pattern recall of the system, and…

无序系统与神经网络 · 物理学 2015-06-19 Silvia Bartolucci , Alessia Annibale

In recent years, deep learning has been connected with optimal control as a way to define a notion of a continuous underlying learning problem. In this view, neural networks can be interpreted as a discretization of a parametric Ordinary…

最优化与控制 · 数学 2020-07-07 Joubine Aghili , Olga Mula

Existing analyses of optimization in deep learning are either continuous, focusing on (variants of) gradient flow, or discrete, directly treating (variants of) gradient descent. Gradient flow is amenable to theoretical analysis, but is…

机器学习 · 计算机科学 2021-12-30 Omer Elkabetz , Nadav Cohen