DocumentCode :
2027372
Title :
Towards the software engineering of neural networks: a maturity model
Author :
Senyard, Anthony ; Dart, Philip ; Sterling, Leon
Author_Institution :
Dept. of Comput. Sci. & Software Eng., Melbourne Univ., Vic., Australia
fYear :
2000
fDate :
2000
Firstpage :
45
Lastpage :
51
Abstract :
Neural networks are being used increasingly in a wide range of real-world applications. However, existing studies have reported major problems in neural network software development. This paper analyses these problems and describes how existing software engineering practice can address some of them. Other problems are identified as requiring new approaches tailored to neural network development. A unified framework is presented, in the form of an extension to the Capability Maturity Model, aimed at instituting good software engineering practice for neural network development. The framework should be of interest to neural network software developers, and it suggests research directions towards the software engineering of neural networks
Keywords :
neural nets; software engineering; Capability Maturity Model; neural network software development; research directions; software engineering practice; Algorithm design and analysis; Application software; Capability maturity model; Computer science; Control systems; Identity-based encryption; Neural networks; Programming; Software engineering; Software testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Software Engineering Conference, 2000. Proceedings. 2000 Australian
Conference_Location :
Canberra, ACT
Print_ISBN :
0-7695-0631-3
Type :
conf
DOI :
10.1109/ASWEC.2000.844558
Filename :
844558
Link To Document :
بازگشت