Efficient Cross-Validation for Feedforward Neural Networks (2007)
In this paper, we study the use of cross-validation for estimating the prediction risk of feedforward neural networks. In particular, the problem of variability due to the choice of random initial...
Reference Priors for Neural Networks: Laplace versus Gaussian (2007)
Motivated by the principle of maximum entropy, the Laplace prior has been introduced in the Bayesian inference approach to training feedforward neural networks as the prior distribution for network...
A Theoretically Sound Learning Algorithm for Constructive Neural Networks (2007)
Determining network size used to require various ad hoc rules of thumb. In recent years, several researchers proposed methods to handle this problem with as little human intervention as possible....
Objective Functions for Training Units in Constructive Neural New Hidden Networks (2007)
Abstract-- In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of...
Speedup of kernel eigenvoice speaker adaptation by embedded kernel PCA (2004)
Mak, Brian Kan-Wing, Ho, Simon, Kwok, Tin-Yau
Recently, we proposed an improvement to the eigenvoice (EV) speaker adaptation called kernel eigenvoice (KEV) speaker adaptation. In KEV adaptation, eigenvoices are computed using kernel PCA, and a...
Objective Functions for Training New Hidden Units in Constructive Neural Networks (1999)
In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of objective...
Objective functions for training new hidden units in constructive neural networks (1997)
In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of objective...
Objective functions for training new hidden units in constructive neural networks (1997)
Abstract--- In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of...
In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add...
Constructive algorithms for structure learning in feedforward neural networks / (1996)
Thesis (Ph. D.)--Hong Kong University of Science and Technology, 1996.
Constructive algorithms for structure learning in feedforward neural networks (1996)
Thesis (Ph.D.)--Hong Kong University of Science and Technology, 1996
In a regression problem, one is given a d-dimensional random vector X, the components of which are called predictor variables, and a random variable, Y, called response. A regression surface...
Bayesian Regularization in Constructive Neural Networks (1996)
. In this paper, we study the incorporation of Bayesian regularization into constructive neural networks. The degree of regularization is automatically controlled in the Bayesian inference framework...
In a regression problem, one is given a d- dimensional random vector X, the components of which are called predictor variables, and a random variable, Y , called response. A regression surface...
In a regression problem, one is given a d- dimensional random vector X, the components of which are called predictor variables, and a random variable, Y , called response. A regression surface...
Constructive feedforward neural networks for regression problems : a survey (1995)
In this paper, we review the procedures for constructing feedforward neural networks in regression problems. While standard back-propagation performs gradient descent only in the weight space of a...
Improving the Approximation and Convergence Capabilities of Projection Pursuit Learning (1995)
: Projection pursuit regression (PPR) is a statistical technique that has been successfully applied to high-dimensional data. Projection pursuit learning (PPL) formulates PPR in a neural network...
Constructive Feedforward Neural Networks for Regression Problems: A Survey (1995)
In this paper, we review the procedures for constructing feedforward neural networks in regression problems. While standard back-propagation performs gradient descent only in the weight space of a...
Constructive neural networks : some practical considerations (1994)
Based on a Hilbert space point of view, we proposed in our previous work a novel objective function for training new hidden units in a constructive feedforward neural network. Moreover, we proved...
Constructive neural networks: Some practical considerations (1994)
Abstract--- Based on a Hilbert space point of view, we proposed in our previous work a novel objective function for training new hidden units in a constructive feedforward neural network. Moreover,...
Constructive Neural Networks: Some Practical Considerations (1994)
Based on a Hilbert space point of view, we proposed in our previous work a novel objective function for training new hidden units in a constructive feedforward neural network. Moreover, we proved...
Theoretical analysis of constructive neural networks (1993)
Determining network size used to require various _ad hoc_ rules of thumb. In recent years, several researchers proposed methods to handle this problem with as little human intervention as possible....
Theoretical Analysis of Constructive Neural Networks (1993)
Determining network size used to require various ad hoc rules of thumb. In recent years, several researchers proposed methods to handle this problem with as little human intervention as possible....
Experimental Analysis of Input Weight Freezing in Constructive Neural Networks (1993)
An important research problem in constructive network algorithms is how to train the new network after the addition of a hidden unit. There are two ways to train the resultant network. One calls for...