论文信息 - The Cascade-Correlation Learning Architecture

The Cascade-Correlation Learning Architecture

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.

Christian Lebiere | Scott E. Fahlman | C. Lebiere | S. Fahlman

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

[2] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[3] Gerald Tesauro,et al. Scaling Relationships in Back-propagation Learning , 1988, Complex Syst..

[4] Raymond L. Watrous. Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization , 1988 .

[5] Robert A. Jacobs,et al. Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[6] Alberto L. Sangiovanni-Vincentelli,et al. Efficient Parallel Learning Algorithms for Neural Networks , 1988, NIPS.

[7] John E. Moody,et al. Fast Learning in Multi-Resolution Hierarchies , 1988, NIPS.

[8] K. Lang,et al. Learning to tell two spirals apart , 1988 .

[9] Timur Ash,et al. Dynamic node creation in backpropagation networks , 1989 .

[10] Yann LeCun,et al. Improving the convergence of back-propagation learning with second-order methods , 1989 .

[11] 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,.

[12] S. Fahlman. Fast-learning variations on back propagation: an empirical study. , 1989 .

[13] Geoffrey E. Hinton,et al. Proceedings of the 1988 Connectionist Models Summer School , 1989 .