Papers - YAMAMORI Kunihito
-
Evaluation of GP-based time series prediction
Ohta Takehiro, Yoshihara Ikuo, Yamamori Kunihito, Yasunaga Moritoshi
宮崎大學工學部紀要 31 325 - 330 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：宮崎大学
-
Development of a multi-modal nueral network for predicting protein secondary structure
Zhu Hanxi, Yoshihara Ikuo, Yamamori Kunihito, Yasunaga Moritoshi
宮崎大學工學部紀要 31 331 - 338 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：宮崎大学
-
Comparison with defect compensation methods for freed-forward neural networks
Yamamori Kunihito, Takahashi Kinya, Yoshihara Ikuo
宮崎大學工學部紀要 31 379 - 383 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：宮崎大学
-
A parallel greedy GA for symmetric and asymmetric TSPs
Nguyen Hung Dinh, Yoshihara Ikuo, Yamamori Kunihito, Yasunaga Moritoshi
宮崎大學工學部紀要 31 339 - 346 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：宮崎大学
-
Timetabling for University Classes using Genetic Algorithm
Yoshihara Ikuo, Koizumi Naoki, Yamamori Kunihito
宮崎大學工學部紀要 31 355 - 360 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：宮崎大学
-
Research on identifying intron-exon boundaries in DNA sequences
Kamimai Yoshiyuki, Yoshihara Ikuo, Yamamori Kunihito, Yasunaga Moritoshi
宮崎大學工學部紀要 31 313 - 318 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：宮崎大学
-
Genetic algorithms with immune mechanism for symmetric TSPs
Yoshihara Ikuo, Morishige Shinya, Yamamori Kunihito
Memoirs of the Faculty of Engineering, Miyazaki University 31 319 - 324 2002.7
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Miyazaki University
-
An Efficient Defect Compensation Scheme for Multi-Layer Neural Networks on WSI Devices Reviewed
K.Yamamori, T.Abe, S.Horiguchi, I.Yoshihara
Proc. International Joint Conference on Neural Networks 1056 - 1061 2002.5
Language：English Publishing type：Research paper (international conference proceedings)
-
Prediction of Protein Secondary Structure by Multi-Modal Neural Networks Reviewed
H.Zhu, I.Yoshihara, K.Yamamori
Proc. International Joint Conference on Neural Networks 280 - 285 2002.5
Language：English Publishing type：Research paper (international conference proceedings)
-
A Parallel Hybrid Genetic Algorithm for Multiple Protein Sequence Alignment Reviewed
H.D.Nguyen, I.Yoshihara,K.Yamamori, M.Yasunaga
Proc. Congress on Evolutionary Computation 309 - 314 2002.5
Language：English Publishing type：Research paper (international conference proceedings)
-
A parallel hybrid genetic algorithm for multiple protein sequence alignment
Nguyen H., Yoshihara I., Yamamori K., Yasunaga M.
Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002 1 309 - 314 2002
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002
This paper presents a parallel hybrid genetic algorithm (GA) for solving sum-of-pairs multiple protein sequence alignment. The method is based on a multiple population GENITOR-type GA and involves local search heuristics. It is then extended to parallel to exploit the benefit of a multiprocessor system. Benchmarks from the BAliBASE library are used to validate the method. © 2002 IEEE.
-
Comparison of defect compensation methods for feedforward neural networks
Takahashi K., Horiguchi S., Yamamori K., Yoshihara I.
Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2002-January 293 - 300 2002
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC
© 2002 IEEE. Recently, many defect compensation methods have been proposed for feedforward neural networks implemented in hardware devices. However, there are few accurate quantitative comparisons with the performance of these defect compensation methods. In this paper, we compare the following three defect compensation methods; partial retraining (PR) scheme, whole network backpropagation (BP) retraining and FT (fault-tolerant) BP method. The BP algorithm and PR scheme retrain the neural network after defects have occurred. The FTBP method tries to obtain the weights those are robust for the defects. We can say that both the BP algorithm and PR scheme are cure-type compensation methods and the FTBP method is a precaution-type compensation method. We compare the average recognition rate, average training time and the generalization ability among these three methods in detail. The experiments show that the whole network retraining by the BP algorithm has the highest reliability on the XOR problem and face image recognition problem on the neural networks with a single broken link defect and two broken link defects.
-
An efficient defect compensation scheme for multi-layer neural networks on WSI devices
Yamamori K., Abe T., Horiguchi S., Yoshihara I.
Proceedings of the International Joint Conference on Neural Networks 1 1056 - 1061 2002
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Proceedings of the International Joint Conference on Neural Networks
This paper discusses on high speed off-line defect compensation scheme for trained multi-layer neural networks implemented in WSI devices. Since partial retraining scheme utilizes the redundancy of neural networks, no additional circuits is needed. The performance of partial retraining scheme will be compared with that by back-propagation algorithm on face image recognition problem.
-
Aligning multiple protein sequences by parallel hybrid genetic algorithm.
Nguyen H., Yoshihara I., Yamamori K., Yasunaga M.
Genome informatics. International Conference on Genome Informatics 13 123 - 132 2002
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Genome informatics. International Conference on Genome Informatics
This paper presents a parallel hybrid genetic algorithm (GA) for solving the sum-of-pairs multiple protein sequence alignment. A new chromosome representation and its corresponding genetic operators are proposed. A multi-population GENITOR-type GA is combined with local search heuristics. It is then extended to run in parallel on a multiprocessor system for speeding up. Experimental results of benchmarks from the BAliBASE show that the proposed method is superior to MSA, OMA, and SAGA methods with regard to quality of solution and running time. It can be used for finding multiple sequence alignment as well as testing cost functions.
-
Performance Evaluation of a Partial Retraining Scheme for Defective Multi-Layer Neural Networks Reviewed
K.Yamamori, T.Abe, S.Horiguchi
Proc. 6th Australasian Computer Systems Architecture Conference 138 - 145 2001.1
Language：English Publishing type：Research paper (international conference proceedings)
-
Two-Stage Parallel Partial Retraining Scheme for Defective Multi-Layer Neural Networks Reviewed
K.Yamamori, T.Abe, S.Horiguchi
Proc. The Fourth International Conference/Exhibition on High Performance Computing in Asia-Pacific Region 2 642 - 647 2000.5
Language：English Publishing type：Research paper (international conference proceedings)
-
Theoretical Learning-Speed Evaluation of Parallel Back-Propagation Algorithms Reviewed
K.Yamamori, T.Abe, S.Horiguchi
Systems Research and Information Systems 9 121 - 148 2000.1
Language：English Publishing type：Research paper (scientific journal)
-
Three-Layers Neural Model between Cortical areas V1 and IT Reviewed
S.Kato, K.Yamamori, S.Horiguchi
Proc. International Conference on Artificial Neural Networks, Vol.2, 1003-1008 2 1003 - 1008 1998.8
Language：English Publishing type：Research paper (international conference proceedings)
-
Theoretical Performance Evaluation of Parallel Back-Propagation Algorithms Reviewed
K.Yamamori, T.Abe, S.Horiguchi
Proc. International Conference on Parallel and Distributed Processing Techniques and Applications 2 1095 - 1102 1998.7
Language：English Publishing type：Research paper (international conference proceedings)
-
並列計算機上の誤差逆伝搬学習法の並列学習モデル Reviewed
山森一人，堀口進
電子情報通信学会論文誌 J80-D-II ( 2 ) 370 - 377 1998.2
Language：Japanese Publishing type：Research paper (scientific journal)