Original Contribution: A method for improving the real-time recurrent learning algorithm

Authors:
Thierry Catfolis
Affiliations:
-
Venue:
Neural Networks
Year:
1993

Citing 4
Cited 2

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Storing temporal sequences

Neural Networks
Discrete time leaky integrator network with synaptic noise

Neural Networks
AI in Process Control

AI in Process Control

Mapping a complex temporal problem into a combination of static and dynamic neural networks

ACM SIGART Bulletin
Learning in fully recurrent neural networks by approaching tangent planes to constraint surfaces

Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Williams and Zipser (1989) proposed two analogue learning algorithms for fully recurrent networks. The first method is an exact gradient-following algorithm for problems where data consists of epochs. The second method, called the Real-Time Recurrent Learning (RTRL) algorithm, uses data described by a temporal stream of inputs and outputs, without time marks or epochs. In this paper we describe a new implementation of this RTRL algorithm. This improved implementation makes it possible to increase the performance of the learning algorithm during the training phase by using some a priori knowledge about the temporal necessities of the problem. The reduction of the computational expense of the training enables the use of this algorithm for more complex problems. Some simulations of a process control task demonstrate the properties of this algorithm.