中文
相关论文

相关论文: Solution space and storage capacity of fully conne…

200 篇论文

Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks as the curse of dimensionality (CoD) cannot be evaded when trying to approximate even a single ReLU neuron…

机器学习 · 统计学 2024-06-27 Fanghui Liu , Leello Dadi , Volkan Cevher

Learning in neural networks critically hinges on the intricate geometry of the loss landscape associated with a given task. Traditionally, most research has focused on finding specific weight configurations that minimize the loss. In this…

统计力学 · 物理学 2024-09-30 Margherita Mele , Roberto Menichetti , Alessandro Ingrosso , Raffaello Potestio

We study a model of associative memory based on a neural network with small-world structure. The efficacy of the network to retrieve one of the stored patterns exhibits a phase transition at a finite value of the disorder. The more ordered…

适应与自组织系统 · 物理学 2009-11-10 Luis G. Morelli , Guillermo Abramson , Marcelo N. Kuperman

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned…

机器学习 · 计算机科学 2020-02-18 Deniz Oktay , Johannes Ballé , Saurabh Singh , Abhinav Shrivastava

Associative memory or content addressable memory is an important component function in computer science and information processing and is a key concept in cognitive and computational brain science. Many different neural network…

神经与进化计算 · 计算机科学 2025-02-19 Anders Lansner , Naresh B Ravichandran , Pawel Herman

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

机器学习 · 计算机科学 2021-10-11 Elvis Nunez , Maxwell Horton , Anish Prabhu , Anurag Ranjan , Ali Farhadi , Mohammad Rastegari

Characterizing the capacity region of multi-source wireless relay networks is one of the fundamental issues in network information theory. The problem is, however, quite challenging due to inter-user interference when there exist multiple…

信息论 · 计算机科学 2013-10-29 Sang-Woon Jeon , Sae-Young Chung

We investigate from a computational perspective the efficiency of the Willshaw synaptic update rule in the context of familiarity discrimination, a binary-answer, memory-related task that has been linked through psychophysical experiments…

神经元与认知 · 定量生物学 2012-08-01 João Sacramento , Andreas Wichert

Dimensionality reduction, a form of compression, can simplify representations of information to increase efficiency and reveal general patterns. Yet, this simplification also forfeits information, thereby reducing representational capacity.…

In computer vision and machine learning, a crucial challenge is to lower the computation and memory demands for neural network inference. A commonplace solution to address this challenge is through the use of binarization. By binarizing the…

机器学习 · 计算机科学 2023-07-06 Guy Berger , Aviv Navon , Ethan Fetaya

Binary classification is one of the most common problem in machine learning. It consists in predicting whether a given element belongs to a particular class. In this paper, a new algorithm for binary classification is proposed using a…

机器学习 · 计算机科学 2019-03-12 Alexandre Quemy

We study analytically the effect of metrically structured connectivity on the behavior of autoassociative networks. We focus on three simple rate-based model neurons: threshold-linear, binary or smoothly saturating units. For a connectivity…

无序系统与神经网络 · 物理学 2009-11-11 Yasser Roudi , Alessandro Treves

The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neural network architectures. Recent works have experimentally shown that two different solutions found…

机器学习 · 计算机科学 2024-03-04 Damien Ferbach , Baptiste Goujaud , Gauthier Gidel , Aymeric Dieuleveut

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

We develop a variational framework to understand the properties of functions learned by fitting deep neural networks with rectified linear unit activations to data. We propose a new function space, which is reminiscent of classical bounded…

机器学习 · 统计学 2022-04-18 Rahul Parhi , Robert D. Nowak

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both…

机器学习 · 计算机科学 2018-09-11 Jorn W. T. Peters , Max Welling

Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the…

机器学习 · 计算机科学 2024-09-05 Linu Pinto , Sasi Gopalan

We consider the problem of finding weights and biases for a two-layer fully connected neural network to fit a given set of data points as well as possible, also known as EmpiricalRiskMinimization. Our main result is that the associated…

计算复杂性 · 计算机科学 2024-03-25 Daniel Bertschinger , Christoph Hertrich , Paul Jungeblut , Tillmann Miltzow , Simon Weber

The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Julien Combes , Alexandre Derville , Jean-François Coeurjolly

This paper explores learned-context neural networks. It is a multi-task learning architecture based on a fully shared neural network and an augmented input vector containing trainable task parameters. The architecture is interesting due to…

机器学习 · 计算机科学 2025-08-07 Anders T. Sandnes , Bjarne Grimstad , Odd Kolbjørnsen