Peng, C.C. and Magoulas, George D. (2009) Nonmonotone learning of recurrent neural networks in symbolic sequence processing applications. pp. 325-335. ISSN 1865-0929.Full text not available from this repository.
In this paper, we present a formulation of the learning problem that allows deterministic nonmonotone learning behaviour to be generated, i.e. the values of the error function are allowed to increase temporarily although learning behaviour is progressively improved. This is achieved by introducing a nonmonotone strategy on the error function values. We present four training algorithms which are equipped with nonmonotone strategy and investigate their performance in symbolic sequence processing problems. Experimental results show that introducing nonmonotone mechanism can improve traditional learning strategies and make them more effective in the sequence problems tested.
|Keyword(s) / Subject(s):||BFGS, conjugate gradient, Levenberg-Marquardt, nonmonotone learning, recurrent neural networks, resilient propagation, training algorithms, symbolic sequences|
|School or Research Centre:||Birkbeck Schools and Research Centres > School of Business, Economics & Informatics > Computer Science and Informatics|
|Date Deposited:||05 Apr 2011 13:53|
|Last Modified:||17 Apr 2013 12:20|
Archive Staff Only (login required)