The Cascade-Correlation learning architecture
Scott E. Fahlman, Christian J. Lebiere · 2018
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."
Cited by 2,372 works. doi:10.1184/r1/6610403
Authors
References
- Learning Internal Representations by Error Propagation
- Improving the convergence of back-propagation learning with second-order methods
- Increased rates of convergence through learning rate adaptation
- Consonant recognition by modular construction of large phonemic time-delay neural networks
- Consonant Recognition by Modular Construction of Large Phonemic Time-Delay Neural Networks
- Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization
- Fast-learning variations on back propagation: an empirical study.
- Learning to Tell Two Spirals Apart
- Efficient Parallel Learning Algorithms for Neural Networks
- Fast Learning in Multi-Resolution Hierarchies