Scott E. Fahlman,
The Recurrent Cascade-Correlation Architecture.
Tech. Rep. CMU-CS-91-100, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, May 1991.
Scott E. Fahlman,
The Recurrent Cascade-Correlation Architecture.
Tech. Rep. CMU-CS-91-100, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, May 1991.
Recurrent Cascade-Correlation (RCC) is a recurrent version of the Cascade-Correlation learning architecture of Fahlman and Lebiere. 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 one at a time, as they are 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 the ability to learn complex behaviours through a sequence of simple lessons. The power of RCC is demonstrated on two tasks: learning a finite-state grammar from examples of legal strings, and learning to recognize characters in Morse code.