论文信息 - Subgrouping Reduces Complexity and Speeds Up Learning in Recurrent Networks

Subgrouping Reduces Complexity and Speeds Up Learning in Recurrent Networks

Recurrent nets are more powerful than feedforward nets because they allow simulation of dynamical systems. Everything from sine wave generators through computers to the brain are potential candidates, but to use recurrent nets to emulate dynamical systems we need learning algorithms to program them. Here I describe a new twist on an old algorithm for recurrent nets and compare it to its predecessors.

David Zipser | D. Zipser

[1] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[2] Ronald J. Williams,et al. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.