The Experts below are selected from a list of 249345 Experts worldwide ranked by ideXlab platform
Jose Aguilar - One of the best experts on this subject based on the ideXlab platform.
-
CIARP - Statistical Pattern Recognition Problems and the Multiple Classes Random Neural Network Model
Lecture Notes in Computer Science, 2004Co-Authors: Jose AguilarAbstract:The purpose of this paper is to describe the use of the multiple classes random Neural Network Model to learn various statistical patterns. We propose a pattern recognition algorithm for the recognition of statistical patterns based upon the non-linear equations of the multiple classes random Neural Network Model using gradient descent of a quadratic error function. In this case the classification errors are considered.
-
learning algorithm and retrieval process for the multiple classes random Neural Network Model
Neural Processing Letters, 2001Co-Authors: Jose AguilarAbstract:Gelenbe has Modeled Neural Networks using an analogy with queuing theory. This Model (called Random Neural Network) calculates the probability of activation of the neurons in the Network. Recently, Fourneau and Gelenbe have proposed an extension of this Model, called multiple classes random Neural Network Model. The purpose of this paper is to describe the use of the multiple classes random Neural Network Model to learn patterns having different colors. We propose a learning algorithm for the recognition of color patterns based upon non-linear equations of the multiple classes random Neural Network Model using gradient descent of a quadratic error function. In addition, we propose a progressive retrieval process with adaptive threshold values. The experimental evaluation shows that the learning algorithm provides good results.
-
IJCNN (5) - Multiple classes random Neural Network Model and color pattern recognition problems
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for, 2000Co-Authors: Jose Aguilar, V. RossellAbstract:The purpose of the paper is to describe the use of the multiple classes random Neural Network Model to learn patterns having different colors. We propose a learning algorithm for the recognition of color patterns based upon the nonlinear equations of the multiple classes random Neural Network Model using gradient descent of a quadratic error function. In addition, we propose a progressive retrieval process with adaptive threshold value.
Keiji Yamada - One of the best experts on this subject based on the ideXlab platform.
-
Inverse recall Neural Network Model and feedback pattern recognition
1993Co-Authors: Keiji YamadaAbstract:An inverse recall Neural Network Model and a feedback pattern recognition method based on the Model are proposed. The inverse recall Neural Network Model is trained by the same method as that used for a typical multilayer feedforward Model. The Model can produce an inverse mapping of the trained feedforward mappings to show the parts of an input pattern. The Model is applied to the feedback recognition method which can extract features from input patterns and discriminates between them by the inverse recall Neural Network Model. The feedback recognition method adjusts feature extraction parameters so as to detect the important parts shown by the Neural Network Model in order to present them to the Network, and to produce more certain recognition results. This method is examined on handwritten alpha-numerics. It is found that rejection ratio can be reduced by half at the same error ratio. >
-
ICNN - Inverse recall Neural Network Model and feedback pattern recognition
IEEE International Conference on Neural Networks, 1Co-Authors: Keiji YamadaAbstract:An inverse recall Neural Network Model and a feedback pattern recognition method based on the Model are proposed. The inverse recall Neural Network Model is trained by the same method as that used for a typical multilayer feedforward Model. The Model can produce an inverse mapping of the trained feedforward mappings to show the parts of an input pattern. The Model is applied to the feedback recognition method which can extract features from input patterns and discriminates between them by the inverse recall Neural Network Model. The feedback recognition method adjusts feature extraction parameters so as to detect the important parts shown by the Neural Network Model in order to present them to the Network, and to produce more certain recognition results. This method is examined on handwritten alpha-numerics. It is found that rejection ratio can be reduced by half at the same error ratio. >
Bao Zhenwu - One of the best experts on this subject based on the ideXlab platform.
-
The Neural Network Model of optical fiber direction coupler
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003, 2003Co-Authors: Li Jiusheng, Bao ZhenwuAbstract:The coupling length and coupling ratio is defined as input and output respectively, which are used to train the Neural Network Model. RBF Neural Network Model is built for optical fiber direction coupler, which is in turn simulated and designed through the Model. This method has the advantages of speediness, accuracy and reliability, which are identified by the design example. It can be used to design the other kind of optical passive device. This way is a novel design approach, which can save the cost of device design, decrease period of design and has a good prospect of application.
Zhenwu Bao - One of the best experts on this subject based on the ideXlab platform.
-
Neural Network Model of optical fiber direction coupler design
Optical Modeling and Performance Predictions, 2004Co-Authors: Zhenwu BaoAbstract:The coupling length and coupling ratio is defined as input and output respectively, which are used to train the Neural Network Model. Radial base function Neural Network Model is built for optical fiber direction coupler, which is in turn simulated and designed through the Model. This method has the advantages of speediness, accuracy and reliability, which are identified by the design example. It can be used to design the other kind of optical passive device. This way is a novel design approach, which can save the cost of device design, decrease period of design and has a good prospect of application.
Xiaoyu Guo - One of the best experts on this subject based on the ideXlab platform.
-
LSTM-Based Neural Network Model for Semantic Search
Smart Service Systems Operations Management and Analytics, 2020Co-Authors: Xiaoyu Guo, Jing Ma, Xiaofeng LiAbstract:To improve web search quality and serve a better search experience for users, it is important to capture semantic information from user query which contains user’s intention in web search. Long Short-Term Memory Long Short-Term Memory (LSTM) (LSTM), a significant Network in deep learning Deep learning has made tremendous achievements in capturing semantic information and predicting the semantic relatedness of two sentences. In this study, considering the similarity between predicting the relatedness of sentence pair task and semantic search Semantic search , we provide a novel channel to process semantic search task: see semantic search as an atypical predicting the relatedness of sentence pair task. Furthermore, we propose an LSTM-Based Neural Network Model which is suitable for predicting the semantic relatedness between user query and potential documents. The proposed LSTM-Based Neural Network Model is trained by Home Depot dataset. Results show that our Model outperforms than other Models.
-
LSTM-Based Neural Network Model for Semantic Search
Smart Service Systems Operations Management and Analytics, 2019Co-Authors: Xiaoyu GuoAbstract:To improve web search quality and serve a better search experience for users, it is important to capture semantic information from user query which contains user’s intention in web search. Long Short-Term Memory (LSTM), a significant Network in deep learning has made tremendous achievements in capturing semantic information and predicting the semantic relatedness of two sentences. In this study, considering the similarity between predicting the relatedness of sentence pair task and semantic search, we provide a novel channel to process semantic search task: see semantic search as an atypical predicting the relatedness of sentence pair task. Furthermore, we propose an LSTM-Based Neural Network Model which is suitable for predicting the semantic relatedness between user query and potential documents. The proposed LSTM-Based Neural Network Model is trained by Home Depot dataset. Results show that our Model outperforms than other Models.
