Software engineering methods for neural networks

作者: A. Senyard , E. Kazmierczak , L. Sterling

DOI: 10.1109/APSEC.2003.1254402

关键词:

摘要: Neural networks have been used to solve a wide range of problems. Unfortunately, many the applications neural reported in literature built an ad-hoc manner, without being informed by techniques and tools software engineering. The problem with developing using "trial error" or "build fix" approach, is that successes are difficult repeat. Building specific problems processes repeatable only if there sufficient culture disciplined practice experienced people organisation facilitate process. We propose set methods for can be systematically repeatably "engineer" explore "design "for networks, validating verifying operation learning algorithms network software. A feature our approach separate generic components from application components.

参考文章(28)
Jonathan P. Bowen, Michael G. Hinchey, Formal Methods and Safety-Critical Standards IEEE Computer. ,(1994)
A.P. Ravn, H. Rischel, V. Stavridou, PROVABLY CORRECT SAFETY CRITICAL SOFTWARE IFAC Proceedings Volumes. ,vol. 23, pp. 13- 18 ,(1990) , 10.1016/S1474-6670(17)52170-9
Gerrit A. Riessen, Graham J. Williams, Xin Yao, PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks Evolutionary Programming. pp. 35- 46 ,(1997) , 10.1007/BFB0014799
Patrícia Duarte de Lima Machado, Silvio Lemos Meira, On the Use of Formal Specifications in the Design and Simulation of Artificial Neural Networks ZUM '95 Proceedings of the 9th International Conference of Z Usres on The Z Formal Specification Notation. pp. 63- 82 ,(1995) , 10.1007/3-540-60271-2_113
John W Prior, Eugenic Evolution for Combinatorial Optimization University of Texas at Austin. ,(1998)
D.M. Rodvold, A software development process model for artificial neural networks in critical applications international joint conference on neural network. ,vol. 5, pp. 3317- 3322 ,(1999) , 10.1109/IJCNN.1999.836192
R. M. Golden, A unified framework for connectionist systems. Biological Cybernetics. ,vol. 59, pp. 109- 120 ,(1988) , 10.1007/BF00317773