Abstract | ||
---|---|---|
We review the training problem for feedforward neural networks and discuss various techniques for accelerating and stabilizing the convergence during training. Among other techniques, these include a self-adjusting step gain, bipolar sigmoid activation functions, training on all classes in parallel, adjusting the exponential rates in the sigmoids, bounding the sigmoid derivatives away from zero, training on exemplars to which noise has been added, adjusting the initial weight set to a subdomain of low values of the sum-squared error, and adjusting the momentum coefficient over the iterations. We also examine methods to assure the generalization of the learning, which include the pruning of unimportant weights and adding noise to exemplars for training. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1016/0925-2312(94)00026-3 | Neurocomputing |
Keywords | Field | DocType |
Feedforward neural networks,Training,Acceleration of convergence,Stabilization,Pruning,Generalized learning | Convergence (routing),Feedforward neural network,Exponential function,Control theory,Computer science,Artificial intelligence,Machine learning,Sigmoid function,Speedup,Bounding overwatch | Journal |
Volume | Issue | ISSN |
10 | 1 | 0925-2312 |
Citations | PageRank | References |
10 | 1.07 | 6 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carl G. Looney | 1 | 198 | 21.58 |