论文信息 - Comparison of learning algorithms for feedforward networks in large scale networks and problems

Comparison of learning algorithms for feedforward networks in large scale networks and problems

The performance of fine learning algorithms for feedforward networks applied to several large scale experiments is evaluated and discussed. In particular, the following algorithms are compared in terms of convergence ability and speed: ALECO-2, a recently proposed constrained optimization learning algorithm, online and off-line backpropagation; Fahlman's Quickprop; and Jacob's Delta-Bar-Delta. All the above learning techniques are applied to three representative large scale benchmark training tasks (two large encoders and one large multiplexer) in a uniform way so as to guarantee fair comparison. The results of this experimental study show clearly that ALECO-2 outperforms all its rivals in terms of convergence ability and speed.

S. J. Perantonis | D. A. Karras | Dimitrios Alexios Karras | S. Perantonis

[1] Lee A. Feldkamp,et al. Strategies and issues in applications of neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2] Tom Tollenaere,et al. SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.

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

[4] Gerald Tesauro,et al. Scaling and Generalization in Neural Networks: A Case Study , 1988, NIPS.

[5] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[6] Kazuki Joe,et al. A Large-Scale Neural Network Which Recognizes Handwritten Kanji Characters , 1989, NIPS.

[7] G.D. Wilensky,et al. Scaling of back-propagation training time to large dimensions , 1990, 1990 IJCNN International Joint Conference on Neural Networks.