Results 1  10
of
56,779
Robust Neural Network Classifier
"... Abstract Classification is a data mining technique used to predict Patterns ’ membership. Pattern classification involves building a function that maps the input feature space to an output space of two or more than two classes. Neural Networks (NN) are an effective tool in the field of pattern clas ..."
Abstract
 Add to MetaCart
learning algorithm based on in order to improve the robustness of neural network training by employing a family of robust statistics estimators, commonly known as Mestimators, and hence obtain robust NN classifiers. Comparative study between robust classifiers and nonrobust (traditional) classifiers
An EvidenceTheoretic Neural Network Classifier
 IN IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS
, 1995
"... A new classifier based on the DempsterShafer theory of evidence is presented. The approach consists in considering the similarity to prototype vectors as evidence supporting certain hypotheses concerning the class membership of a pattern to be classified. The different items of evidence are represe ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
are represented by basic belief assignments over the set of classes and combined by Dempster's rule of combination. An implementation of this procedure in a neural network with specific architecture and learning procedure is presented. A comparison with LVQ and RBF neural network classifiers is performed.
Evolving Efficient Neural Network Classifiers
"... The problem of classifying sensory inputs is ubiquitous for both biological and artificial systems. Determining which neural network learning algorithms are best for particular classes of classification problems can be difficult because each algorithm usually has a number of parameters that need to ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The problem of classifying sensory inputs is ubiquitous for both biological and artificial systems. Determining which neural network learning algorithms are best for particular classes of classification problems can be difficult because each algorithm usually has a number of parameters that need
Design of Robust Neural Network Classifiers
 in Proceedings of IEEE ICASSP'98, IEEE
, 1998
"... This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the loglikelihood and a regularization term (prior). In order to perform robust classification, we present a ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the loglikelihood and a regularization term (prior). In order to perform robust classification, we present
Cooperative Modular Neural Network Classifiers
 Neurocomputing J
, 1996
"... The current generation of nonmodular neural network classifiers is unable to cope with classification problems which have a wide range of overlap among classes. This is due to the high coupling among the networks' hidden nodes. Modular neural network structures attempt to reduce this limitatio ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
The current generation of nonmodular neural network classifiers is unable to cope with classification problems which have a wide range of overlap among classes. This is due to the high coupling among the networks' hidden nodes. Modular neural network structures attempt to reduce
Fuzzy Hypersphere Neural Network Classifier
"... In this paper fuzzy hypersphere neural network (FHSNN) is proposed with its learning algorithm, which is used for rotation invariant handwaritten character recognition. The FHSNN utilizes fuzzy sets as pattern classes in which each fuzzy set is an union of fuzzy set hyperspheres. The fuzzy set hyper ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
. Finally, FHSNN algorithm is used to classify these features by its strong ability of discriminating illdefined character classes. The performance of FHSNN algorithm is compared with other two fuzzy neural network classifiers and found to be superior with respect to the training time, recall time per
Combining Evolving Neural Network Classifiers Using Bagging
"... AbslraclThe performance of the neural network classifier significantly depends on its architecture and generalization. It is usual to find the proper architecture by trial and error. This is time consuming and may not always find the optimal network. For this reason, we apply genetic algorithms to ..."
Abstract
 Add to MetaCart
AbslraclThe performance of the neural network classifier significantly depends on its architecture and generalization. It is usual to find the proper architecture by trial and error. This is time consuming and may not always find the optimal network. For this reason, we apply genetic algorithms
Semantic Adaptation of Neural Network Classifiers in Image Segmentation
"... Abstract. Semantic analysis of multimedia content is an on going research area that has gained a lot of attention over the last few years. Additionally, machine learning techniques are widely used for multimedia analysis with great success. This work presents a combined approach to semantic adaptati ..."
Abstract
 Add to MetaCart
adaptation of neural network classifiers in multimedia framework. It is based on a fuzzy reasoning engine which is able to evaluate the outputs and the confidence levels of the neural network classifier, using a knowledge base. Improved image segmentation results are obtained, which are used for adaptation
ON NEURAL NETWORK CLASSIFIERS WITH SUPERVISED TRAINING
"... Abstract: A study on classification capability of neural networks is presented, considering two types of architectures with supervised training, namely Multilayer Perceptron (MLP) and RadialBasis Function (RBF). To illustrate the classifiers’ construction, we have chosen a problem that occurs in re ..."
Abstract
 Add to MetaCart
Abstract: A study on classification capability of neural networks is presented, considering two types of architectures with supervised training, namely Multilayer Perceptron (MLP) and RadialBasis Function (RBF). To illustrate the classifiers’ construction, we have chosen a problem that occurs
Convergence of a neural network classifier
 In Proceedings of 29/h CDC
, 1990
"... In this paper, we prove that the vectors in the LVQ learning algorithm converge. We do this by showing that the learning algorithm performs stochastic approximation. Convergence is then obtained by identifying the appropriate conditions on the learning rate and on the underlying statistics of the cl ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
In this paper, we prove that the vectors in the LVQ learning algorithm converge. We do this by showing that the learning algorithm performs stochastic approximation. Convergence is then obtained by identifying the appropriate conditions on the learning rate and on the underlying statistics of the classification problem. We also present a modification to the learning algorithm which we argue results in convergence of the LVQ error to the Bayesian optimal error as the appropriate parameters become large. 1
Results 1  10
of
56,779