论文信息 - The Recurrent Cascade-Correlation Architecture

The Recurrent Cascade-Correlation Architecture

Recurrent Cascade-Correlation (RCC) is a recurrent version of the Cascade-Correlation learning architecture of Fahlman and Lebiere [Fahlman, 1990]. RCC can learn from examples to map a sequence of inputs into a desired sequence of outputs. New hidden units with recurrent connections are added to the network as needed during training. In effect, the network builds up a finite-state machine tailored specifically for the current problem. RCC retains the advantages of Cascade-Correlation: fast learning, good generalization, automatic construction of a near-minimal multi-layered network, and incremental training.

Scott E. Fahlman | S. Fahlman

[1] Michael C. Mozer,et al. A Focused Backpropagation Algorithm for Temporal Pattern Recognition , 1989, Complex Syst..

[2] David Zipser,et al. Learning Sequential Structure with the Real-Time Recurrent Learning Algorithm , 1991, Int. J. Neural Syst..

[3] Christian Lebiere,et al. The Cascade-Correlation Learning Architecture , 1989, NIPS.

[4] James L. McClelland,et al. Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

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

[6] Alex Waibel,et al. Consonant recognition by modular construction of large phonemic time-delay neural networks , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[7] Jeffrey L. Elman,et al. Finding Structure in Time , 1990, Cogn. Sci..

[8] Robert B. Allen,et al. Connectionist Language Users , 1990 .