NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Algorithm for Training a Recurrent Multilayer PerceptronAn improved algorithm has been devised for training a recurrent multilayer perceptron (RMLP) for optimal performance in predicting the behavior of a complex, dynamic, and noisy system multiple time steps into the future. [An RMLP is a computational neural network with self-feedback and cross-talk (both delayed by one time step) among neurons in hidden layers]. Like other neural-network-training algorithms, this algorithm adjusts network biases and synaptic-connection weights according to a gradient-descent rule. The distinguishing feature of this algorithm is a combination of global feedback (the use of predictions as well as the current output value in computing the gradient at each time step) and recursiveness. The recursive aspect of the algorithm lies in the inclusion of the gradient of predictions at each time step with respect to the predictions at the preceding time step; this recursion enables the RMLP to learn the dynamics. It has been conjectured that carrying the recursion to even earlier time steps would enable the RMLP to represent a noisier, more complex system.
Document ID
20110016856
Acquisition Source
Johnson Space Center
Document Type
Other - NASA Tech Brief
Authors
Parlos, Alexander G.
(Texas A&M Univ. College Station, TX, United States)
Rais, Omar T.
(Texas A&M Univ. College Station, TX, United States)
Menon, Sunil K.
(Texas A&M Univ. College Station, TX, United States)
Atiya, Amir F.
(California Inst. of Tech. Pasadena, CA, United States)
Date Acquired
August 25, 2013
Publication Date
June 1, 2004
Publication Information
Publication: NASA Tech Briefs, June 2004
Subject Category
Man/System Technology And Life Support
Report/Patent Number
MSC-22893
Distribution Limits
Public
Copyright
Public Use Permitted.
No Preview Available