Open AccessProceedings Article
The Cascade-Correlation Learning Architecture
Scott E. Fahlman,Christian Lebiere +1 more
- Vol. 2, pp 524-532
Reads0
Chats0
TLDR
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.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.read more
Citations
More filters
Book ChapterDOI
Constructive Function Approximation
Paul E. Utgoff,Doina Precup +1 more
TL;DR: Three algorithms are applied to two tasks, measuring the error in the approximated function as learning proceeds, and issues of feature overlap, independence, and coverage are addressed.
Book ChapterDOI
Learning Controllers for Industrial Robots
TL;DR: From the experimental comparison, it appears that both Fuzzy Controllers and RBFNs synthesised from examples are excellent approximators, and that, in practice, they can be even more accurate than MLPs.
Journal ArticleDOI
Evaluation of constructive neural networks with cascaded architectures
TL;DR: Five different constructive neural network algorithms are investigated, of which four were methods found in the literature and one was the authors' own recently developed algorithm, which produces rather often the best performance level among the investigated algorithms.
Journal ArticleDOI
On the automated, evolutionary design of neural networks: past, present, and future
TL;DR: This work aims to provide a complete reference of all works related to neuroevolution of convolutional neural networks up to the date, and to the best of its knowledge, this is the best survey reviewing the literature in this field.
Book ChapterDOI
The Legion System: A Novel Approach to Evolving Hetrogeneity for Collective Problem Solving
TL;DR: It was found that the amount of heterogeneity evolved in an agent group is dependent of the given problem domain: for the first task, the Legion system evolved heterogeneous groups; for the second task, primarily homogeneous groups evolved.
References
More filters
Book ChapterDOI
Learning internal representations by error propagation
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
MonographDOI
Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Book
Learning internal representations by error propagation
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
Journal ArticleDOI
Increased Rates of Convergence Through Learning Rate Adaptation
TL;DR: A study of Steepest Descent and an analysis of why it can be slow to converge and four heuristics for achieving faster rates of convergence are proposed.