Thursday, October 17, 2013

An introduction to neural networks

Pattern learning with the back-propagation algorithm
Andrew Blais (onlymice@gnosis.cx), Author, Gnosis Software, Inc.
David Mertz (mertz@gnosis.cx), Developer, Gnosis Software, Inc.
Summary: Neural nets may be the future of computing. A good way to understand them is with a puzzle that neural nets can be used to solve. Suppose that you are given 500 characters of code that you know to be C, C++, Java, or Python. Now, construct a program that identifies the code's language. One solution is to construct a neural net that learns to identify these languages. This article discusses the basic features of neural nets and approaches to constructing them so you can apply them in your own coding.

http://www.ibm.com/developerworks/library/l-neural/index.html?S_TACT=105AGX52&S_CMP

http://www1.maths.leeds.ac.uk/~charles/statlog/

No comments:

Post a Comment