The Recurrent Cascade-Correlation Architecture
By Scott E. Fahlman. 1990
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- J. Urgen Schmidhuber
- Yoshua Bengio
- J. V. Leeuwen
- Kenneth O. Stanley
- R. Lee
- Mark B. Ring
- Alessandro Sperduti
- Christoph Bergmeir
Citations in the corpus
- Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS (2012, background): “…backpropagation (Riedmiller and Braun 1993; Riedmiller 1994), backpercolation (Jurik 1994), (recurrent) cascade-correlation (Fahlman and Lebiere 1990; Fahlman 1991), counter-propagation (Hecht-Nielsen 1987), scaled conjugate gradient (Møller 1993), and TACOMA learning (Lange et al. 1994).”
- Supervised neural networks for the classification of structures (1997, methodology): “Fahlman extended the algorithm to the classi cation of sequences, obtaining good results [8].”
- Continual learning in reinforcement environments (1995, methodology): “Recurrent Cascade Correlation (RCC) was able to learn this task using only two or three hidden units in an average of 25,000 string presentations [27].”
- CHILD: A First Step Towards Continual Learning (1997, methodology): “They also are not typically constructive learning methods, though RCC, Recurrent Cascade Correlation (Fahlman, 1991), and the network introduced by Giles, et al.”
- Sequence Learning (2001, methodology): “Within this class we can mention Recurrent CascadeCorrelation [18], a partition algorithm using Radial Basis Functions [68], and Recurrent Neural Trees [60].”
- An evolutionary algorithm that constructs recurrent neural networks (1994, background): “Constructive algorithms initially assume a simple network and add nodes and links as warranted [2-8], while destructive methods start with a large network and prune off superfluous components [9-12].”
- Learning Sequential Tasks by Incrementally Adding Higher Orders (1992, methodology): “It has also been demonstrated by Fahlman that a recurrent network that incrementally adds nodes during training-his Recurrent Cascade-Correlation algorithm [5]-can be superior to non-incremental, recurrent networks [2,4, 11, 12, 15].”