A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Ronald J. Williams, David Zipser · Neural Computation · 1989
The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal supervised learning tasks. These algorithms have (1) the advantage that they do not require a precisely defined training interval, operating while the network runs; and (2) the disadvantage that they require nonlocal communication in the network being trained and are computationally expensive. These algorithms allow networks having recurrent connections to learn complex tasks that require the retention of information over time periods having either fixed or indefinite length.
Cited by 4,366 works. doi:10.1162/neco.1989.1.2.270
Authors
References
- Learning Internal Representations by Error Propagation
- Neural networks and physical systems with emergent collective computational abilities.
- Finding Structure in Time
- Learning State Space Trajectories in Recurrent Neural Networks
- A learning rule for asynchronous perceptrons with feedback in a combinatorial environment
- Dynamics and architecture for neural computation
- Experimental Analysis of the Real-time Recurrent Learning Algorithm
- Learning Sequential Structure in Simple Recurrent Networks
- A self-optimizing, nonsymmetrical neural net for content addressable memory and pattern recognition
- Optimization of time-varying systems