Results 1 - 10 of 1,124

Gradient-based learning applied to document recognition

by Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner - Proceedings of the IEEE , 1998
"... Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify hi ..."
Abstract - Cited by 1533 (84 self) - Add to MetaCart
high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed

Learning and transferring mid-level image representations using convolutional neural networks

by Maxime Oquab, Leon Bottou Ivan Laptev, Josef Sivic - In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR , 2014
"... Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large-scale visual recognition challenge (ILSVRC2012). The suc-cess of CNNs is attributed to their ability to learn rich mid-level image representations as opposed to hand-designed low-level f ..."
Abstract - Cited by 71 (3 self) - Add to MetaCart
Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large-scale visual recognition challenge (ILSVRC2012). The suc-cess of CNNs is attributed to their ability to learn rich mid-level image representations as opposed to hand-designed low

Research on Fault Diagnosis Method Based on Rule Base Neural Network

by Zheng Ni , Zhang Lin , Wang Wenfeng , Zhang Bo , Liu Yongjin , Zhang Dajiang
"... The relationship between fault phenomenon and fault cause is always nonlinear, which influences the accuracy of fault location. And neural network is effective in dealing with nonlinear problem. In order to improve the efficiency of uncertain fault diagnosis based on neural network, a neural networ ..."
Abstract - Add to MetaCart
The relationship between fault phenomenon and fault cause is always nonlinear, which influences the accuracy of fault location. And neural network is effective in dealing with nonlinear problem. In order to improve the efficiency of uncertain fault diagnosis based on neural network, a neural

Diffusion-Convolutional Neural Networks

by James Atwood , Don Towsley
"... Abstract We present diffusion-convolutional neural networks (DCNNs), a new model for graph-structured data. Through the introduction of a diffusion-convolution operation, we show how diffusion-based representations can be learned from graphstructured data and used as an effective basis for node cla ..."
Abstract - Add to MetaCart
Abstract We present diffusion-convolutional neural networks (DCNNs), a new model for graph-structured data. Through the introduction of a diffusion-convolution operation, we show how diffusion-based representations can be learned from graphstructured data and used as an effective basis for node

NEURAL NETWORK ALGORITHM FOR MOTOR FAULT DIAGNOSIS

by Wu Hongbing, Lou Peihuang, Tang Dunbing
"... Abstract- A fault diagnosis method based on adaptive dynamic clone selection neural network (ADCSNN) is proposed in this paper. In this method the weights of neural network is encoded as the antibody, and the network error is considered as the antigen. The algorithm is then applied to fault detectio ..."
Abstract - Add to MetaCart
Abstract- A fault diagnosis method based on adaptive dynamic clone selection neural network (ADCSNN) is proposed in this paper. In this method the weights of neural network is encoded as the antibody, and the network error is considered as the antigen. The algorithm is then applied to fault

APPLICATION OF NEURAL NETWORKS IN FAULT DIAGNOSIS OF ROTATING MACHINERY

by He Qing , Du Dongmei
"... ABSTRACT The fault diagnosis method based on artificial neural networks is summarized. An object-oriented paradigm is introduced to fault diagnosis for large scale rotating machinery, for example, turbine-generator. A fault diagnosis method based on object-oriented artificial neural networks for mo ..."
Abstract - Add to MetaCart
ABSTRACT The fault diagnosis method based on artificial neural networks is summarized. An object-oriented paradigm is introduced to fault diagnosis for large scale rotating machinery, for example, turbine-generator. A fault diagnosis method based on object-oriented artificial neural networks

DIAGNOSIS BASED ON NEURAL NETWORK 1

by Peijiang Chen
"... Because of the product variety and structure complexity of the engineering machinery, it was difficult to meet the requirements of fault detection and maintenance for the traditional diagnosis technologies. In order to improve the diagnostic level, the intelligent control technology of neural networ ..."
Abstract - Add to MetaCart
network and its application in engineering machinery fault diagnosis were studied. The basic concepts of engineering machinery fault diagnosis were introduced and several commonly used fault diagnosis methods were discussed. On the basis of analyzing the model and algorithm of BP neural network, a fault

Fault Diagnosis for Wireless Sensor Network's Node Based on Hamming Neural Network and Rough Set

by Lei Lin , Hou-Jun Wang , Chuan-Long Dai
"... Abstract-To accurately diagnose node fault in wireless sensor network (WSN) can improve long-distance service of nodes in WSN, assure reliability of information transfer and prolong lifetime of WSN. In this paper, a novel method of fault diagnosis for node of WSN was brought forward. First, attribu ..."
Abstract - Add to MetaCart
Abstract-To accurately diagnose node fault in wireless sensor network (WSN) can improve long-distance service of nodes in WSN, assure reliability of information transfer and prolong lifetime of WSN. In this paper, a novel method of fault diagnosis for node of WSN was brought forward. First

Analog Circuit Fault Diagnosis Based on Distributed Neural Network

by Long Wang, Yanheng Liu, Xiaoguang Li, Jian Guan, Qi Song
"... Abstract—In order to solve the problems caused by large dataset, such as the network scale and the training time, a new method of analog circuit fault diagnosis based on distributed neural network is presented in this paper. The model of distributed neural network is simply introduced. The arithmeti ..."
Abstract - Add to MetaCart
Abstract—In order to solve the problems caused by large dataset, such as the network scale and the training time, a new method of analog circuit fault diagnosis based on distributed neural network is presented in this paper. The model of distributed neural network is simply introduced

A NEURAL NETWORK BASED SYSTEM FOR SOFT FAULT DIAGNOSIS IN ELECTRONIC CIRCUITS

by unknown authors
"... The paper considers the architecture and the main steps of development of a neural network based system for diagnosis of soft faults in analog electronic circuits. The definition of faults of interest, selection of an optimal set of measurements, feature extraction, the construction of the artificia ..."
Abstract - Add to MetaCart
The paper considers the architecture and the main steps of development of a neural network based system for diagnosis of soft faults in analog electronic circuits. The definition of faults of interest, selection of an optimal set of measurements, feature extraction, the construction
Results 1 - 10 of 1,124