MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  The cascade-correlation learning architecture (1990) [551 citations — 4 self]

Download:
Download as a PDF | Download as a PS
by Scott E. Fahlman, Christian Lebiere
Advances in Neural Information Processing Systems 2
http://reports-archive.adm.cs.cmu.edu/anon/1990/CMU-CS-90-100.ps
Add To MetaCart

Abstract:

Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks. Instead of just adjusting the weights in a network of fixed topology, Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights are frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology, it retains the structures it has built even if the training set changes, and it requires no back-propagation of error signals through the connections of the network.

Citations

2138 Learning Internal Representations by Error Propagation – Rumelhart, Hinton, et al. - 1986
245 Increased Rates of Convergence Through Learning Rate Adaptation. Neural Networks – Jacobs - 1988
223 Faster-Learning Variations on Back-Propagation: An Empirical Study – Fahlman - 1988
108 Learning to tell two spirals apart – Lang, Witbrock - 1988
102 Dynamic node creation in backpropagation networks – Ash - 1989
73 Improving the convergence of back-propagation learning with second order methods – Becker, LeCun - 1989
51 Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization – Watrous - 1987
39 Efficient Parallel learning algorithms for neural networks – Kramer, Sangiovanni-Vincentelli - 1988
28 Fast learning in multi-resolution hierarchies – Moody - 1989
23 Three constructive algorithms for network learning – Gallant - 1986
22 Consonant Recognition by Modular Construction of Large Phonemic Time-delay Neural Networks – Waibel - 1989
9 Speech recognition with back propagation – Franzini - 1987
3 Self-organizing neural nets for the identification problem – Tenorio, Lee - 1989
1 Nonlinear Signal Prediction and System Modelling", Los Alamos National Laboratory – Lapedes, Farber - 1987
1 Scaling Relations in Back-Propagation Learning – Tesauro, Janssens - 1988
View or Download | Add to My Collection | Correct Errors