A training data selection method for multi-class data is proposed. This method can be used for multilayer neural networks (MLNN). The MLNN can be applied to pattern classification, signal process, and other problems that can be considered as the classification problem. The proposed data selection algorithm selects the important data to achieve a good classification performance. However, the training using the selected data converges slowly, so we also propose an acceleration method. The proposed training method adds the randomly selected data to the boundary data. The validity of the proposed methods is confirmed through the computer simulation
Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in...
The main problem for Supervised Multi-layer Neural Network (SMNN) model lies in finding the suitabl...
Neural networks are finding increasing use as an adaptive signal classifier in many engineering appl...
A training data selection method for multi-class data is proposed. This method can be used for multi...
金沢大学大学院自然科学研究科知能情報・数理A training data selection method is proposed for multilayer neural networks (ML...
金沢大学大学院自然科学研究科情報システムIn this paper, a training data selection method for multilayer neural networks (...
In this paper, a training data selection method for multilayer neural networks (MLNNs) in on-line tr...
金沢大学理工研究域電子情報学系A training data reduction method for a multilayer neural network (MLNN) is proposed i...
Abstract—The response of a multilayered perceptron (MLP) network on points which are far away from t...
We present a global algorithm for training multilayer neural networks in this Letter. The algorithm ...
Abstract. A method for training of an ML network for classification has been proposed by us in [3,4]...
This study highlights on the subject of weight initialization in multi-layer feed-forward networks....
Over the past few years, deep neural networks have been at the center of attention in machine learn...
The main problem for Supervised Multi-layer Neural Network (SMNN) model such as Back propagation net...
One connectionist approach to the classification problem, which has gained popularity in recent year...
Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in...
The main problem for Supervised Multi-layer Neural Network (SMNN) model lies in finding the suitabl...
Neural networks are finding increasing use as an adaptive signal classifier in many engineering appl...
A training data selection method for multi-class data is proposed. This method can be used for multi...
金沢大学大学院自然科学研究科知能情報・数理A training data selection method is proposed for multilayer neural networks (ML...
金沢大学大学院自然科学研究科情報システムIn this paper, a training data selection method for multilayer neural networks (...
In this paper, a training data selection method for multilayer neural networks (MLNNs) in on-line tr...
金沢大学理工研究域電子情報学系A training data reduction method for a multilayer neural network (MLNN) is proposed i...
Abstract—The response of a multilayered perceptron (MLP) network on points which are far away from t...
We present a global algorithm for training multilayer neural networks in this Letter. The algorithm ...
Abstract. A method for training of an ML network for classification has been proposed by us in [3,4]...
This study highlights on the subject of weight initialization in multi-layer feed-forward networks....
Over the past few years, deep neural networks have been at the center of attention in machine learn...
The main problem for Supervised Multi-layer Neural Network (SMNN) model such as Back propagation net...
One connectionist approach to the classification problem, which has gained popularity in recent year...
Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in...
The main problem for Supervised Multi-layer Neural Network (SMNN) model lies in finding the suitabl...
Neural networks are finding increasing use as an adaptive signal classifier in many engineering appl...