搜索结果: 1-15 共查到“数学 Neural Networks”相关记录22条 . 查询时间(0.14 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Entropy-Dissipation Informed Neural Networks for McKean-Vlasov type PDEs
McKean-Vlasov型 偏微分方程 熵耗散 信息神经网络
2023/4/13
We extend the concept of self-consistency for the Fokker-Planck equation (FPE) [Shen et al., 2022] to the more general McKean-Vlasov equation (MVE). While FPE describes the macroscopic behavior of par...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Convergence Thery of Deep Neural Networks: Arbitrary Activation Functions and Pooling
深度神经网络 激活函数 池化
2023/4/28
Deep neural networks, as a powerful system to represent high dimensional complex functions, play a key role in deep learning. Convergence of deep neural networks is a fundamental issue in building the...
Convergence and Rate Analysis of Neural Networks for Sparse Approximation
Locally Competitive Algorithm sparse approximation global stability exponential convergence non-smooth objective
2011/9/23
Abstract: We present an analysis of the Locally Competitive Algorithm (LCA), a Hopfield-style neural network that solves sparse approximation problems (e.g., approximating a vector from a dictionary u...
Thermal and Mechanical Modeling of Fluid and Heat Flow in a Porous Metal Using Neural Networks for Application as TPS in Space Vehicles
Neyral Network Porous Media Prous Passages
2013/1/30
This paper contains novel model using feedback neural networks for a work piece temperature predic- tion.The heat and mass transfer in a porous metal workpiece which is heated by a fire gun is studied...
Two-Photon Exchange Effect Studied with Neural Networks
Two-Photon Exchange Neural Networks
2011/7/21
The novel approach to the extraction of the two-photon exchange (TPE) correction from the elastic $ep$ scattering data is presented. The Bayesian framework for the neural networks is adapted. As the r...
Exponential stability of stochastic fuzzy Hopfield neural networks with time-varying delays and impulses
Stochastic Fuzzy Hopfield neural networks
2010/9/20
In this paper, the model of stochastic fuzzy Hopfield neural networks with time-varying delays and impulses (ISFVDHNNs) is established as a modified Takagi-Sugeno (TS) fuzzy model in which the consequ...
Wavelet neural networks for nonlinear time series analysis
Non Stationary-nonlinear Time Series Wavelet Networks
2010/9/27
A wavelet network is an important tool for analyzing time series especially when it is nonlinear and non-stationary. It takes advantage of high resolution of wavelets and learning and feed forward nat...
Collective chaos in pulse-coupled neural networks
Disordered Systems and Neural Networks (cond-mat.dis-nn) Chaotic Dynamics (nlin.CD)
2010/11/10
We study the dynamics of two symmetrically coupled populations of leaky integrate-and-fire neurons characterized by an excitatory coupling. Upon varying the coupling strength, we find symmetry-breakin...
Integrate and Fire Neural Networks, Piecewise Contractive Maps and Limit Cycles
Neural Networks Maps Limit Cycles
2010/11/11
We study the global dynamics of integrate and fire neural networks composed of an arbitrary number of identical neurons interacting by inhibition and excitation. We prove that if the interactions are...
Sequential optimizing investing strategy with neural networks
Sequential optimizing neural networks
2010/4/27
In this paper we propose an investing strategy based on neural network models combined with ideas from game-theoretic probability of Shafer and Vovk. Our proposed strategy uses parameter values of a n...
Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform
Texture Wavelet transform Artificial neural networks Classification
2009/10/13
A large number of approaches for texture analysis have been suggested for the purpose of texture classification. Recently, wavelet frames were proposed for texture features extraction. In this study, ...
LMI approach to stability analysis of discrete-time BAM neural networks with time-varying delays
Discrete-time BAM neural network exponential stability
2010/9/10
In this paper, a discrete-time bidirectional associative memory (BAM) neural network with time-varying delays is considered. The description of the activation functions is more general than the recent...
Stability analysis of impulsive fuzzy recurrent neural networks with hybrid delays
Stability analysis impulsive fuzzy recurrent neural networks hybrid
2010/9/13
In this paper, the impulsive fuzzy recurrent neural network with both time-varying delays and distributed delays is considered. Applying the idea of vector Lyapunov function, M-matrix theory and analy...
Universal Approximation by Ridge Computational Models and Neural Networks: A Survey
nonlinear computational models ridge computational units universal approximation com-plexity
2008/11/10
Computational models made up of linear combinations of ridge basis functions, widely used in machine learning and artificial intelligence, are considered. For such models, the literature on the so-cal...
Further results on global stability criterion of neural networks with continuously distributed delays
Global stability Neural networks LMI
2010/9/14
Based on the recent result given in Park [19], a further result for global asymptotic stability of the equilibrium point for a class of uncertain neural networks with discrete and distributed delays i...