Nonlinear Sciences – Adaptation and Self-Organizing Systems
Scientific paper
1998-06-03
Math'l Modeling and Scientific Comp.,V.5,#2/3, 1996
Nonlinear Sciences
Adaptation and Self-Organizing Systems
50p, 30 figs. Pang did most of the work here. Werbos created the designs. With her agreement, Werbos included this in int'l pa
Scientific paper
This paper shows that a new type of artificial neural network (ANN) -- the Simultaneous Recurrent Network (SRN) -- can, if properly trained, solve a difficult function approximation problem which conventional ANNs -- either feedforward or Hebbian -- cannot. This problem, the problem of generalized maze navigation, is typical of problems which arise in building true intelligent control systems using neural networks. (Such systems are discussed in the chapter by Werbos in K.Pribram, Brain and Values, Erlbaum 1998.) The paper provides a general review of other types of recurrent networks and alternative training techniques, including a flowchart of the Error Critic training design, arguable the only plausible approach to explain how the brain adapts time-lagged recurrent systems in real-time. The C code of the test is appended. As in the first tests of backprop, the training here was slow, but there are ways to do better after more experience using this type of network.
Pang Xiaoying
Werbos Paul
No associations
LandOfFree
Neural network design for J function approximation in dynamic programming does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Neural network design for J function approximation in dynamic programming, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network design for J function approximation in dynamic programming will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-318620