Yinyin Liu,Janusz A Starzyk,Zhen Zhu
Yinyin Liu
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approximation algorithm avoids overfitting by means of a novel and...
Norikazu Takahashi,Jun Guo,Tetsuo Nishi
Norikazu Takahashi
Global convergence of the sequential minimal optimization (SMO) algorithm for support vector regression (SVR) is studied in this paper. Given l training samples, SVR is formulated as a convex quadratic programming (QP) problem with l pairs ...
Implementation of pipelined FastICA on FPGA for real-time blind source separation [0.03%]
基于FPGA的实时独立成分分析盲源信号分离技术的研究与实现
Kuo-Kai Shyu,Ming-Huan Lee,Yu-Te Wu et al.
Kuo-Kai Shyu et al.
Fast independent component analysis (FastICA) algorithm separates the independent sources from their mixtures by measuring non-Gaussian. FastICA is a common offline method to identify artifact and interference from their mixtures such as el...
Centroid neural network with a divergence measure for GPDF data clustering [0.03%]
基于散度测度的高斯概率密度函数数据聚类向量机中枢神经网络
Dong-Chul Park,Oh-Hyun Kwon,Jio Chung
Dong-Chul Park
An unsupervised competitive neural network for efficient clustering of Gaussian probability density function (GPDF) data of continuous density hidden Markov models (CDHMMs) is proposed in this paper. The proposed unsupervised competitive ne...
Charlotte Yuk-Fan Ho,Bingo Wing-Kuen Ling,Hak-Keung Lam et al.
Charlotte Yuk-Fan Ho et al.
In this paper, it is found that the weights of a perceptron are bounded for all initial weights if there exists a nonempty set of initial weights that the weights of the perceptron are bounded. Hence, the boundedness condition of the weight...
Beyond feedforward models trained by backpropagation: a practical training tool for a more efficient universal approximator [0.03%]
超越反向传播训练的前馈模型：一种更高效通用逼近器的实际训练工具
Roman Ilin,Robert Kozma,Paul J Werbos
Roman Ilin
Cellular simultaneous recurrent neural network (SRN) has been shown to be a function approximator more powerful than the multilayer perceptron (MLP). This means that the complexity of MLP would be prohibitively large for some problems while...
Randa Herzallah,David Lowe
Randa Herzallah
Control design for stochastic uncertain nonlinear systems is traditionally based on minimizing the expected value of a suitably chosen loss function. Moreover, most control methods usually assume the certainty equivalence principle to simpl...
Minimizing the effect of process mismatch in a neuromorphic system using spike-timing-dependent adaptation [0.03%]
基于脉冲时间依赖自适应的神经形态系统工艺偏差影响最小化方法研究
Katherine Cameron,Alan Murray
Katherine Cameron
This paper investigates whether spike-timing-dependent plasticity (STDP) can minimize the effect of mismatch within the context of a depth-from-motion algorithm. To improve noise rejection, this algorithm contains a spike prediction element...
Blur identification by multilayer neural network based on multivalued neurons [0.03%]
基于多值神经元的多层神经网络模糊识别方法研究
Igor Aizenberg,Dmitriy V Paliy,Jacek M Zurada et al.
Igor Aizenberg et al.
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algor...
Stéfane Gazut,Jean-Marc Martinez,Gérard Dreyfus et al.
Stéfane Gazut et al.
This paper addresses the problem of the optimal design of numerical experiments for the construction of nonlinear surrogate models. We describe a new method, called learner disagreement from experiment resampling (LDR), which borrows ideas ...