Abstract | ||
---|---|---|
The training strategy used in connectionist learning has not received much attention in the literature. We suggest a new strategy for backpropagation learning, increased complexity training, and show experimentally that it leads to faster convergence compared to both the conventional training strategy using a fixed set, and to combined subset training. Increased complexity training combined with an incremental increase in the success ratio required on the training set produced even quicker convergence. |
Year | DOI | Venue |
---|---|---|
1993 | 10.1007/3-540-56798-4_158 | IWANN |
Keywords | Field | DocType |
complexity training,backpropagation | Convergence (routing),Training set,Computer science,Artificial intelligence,Backpropagation,Machine learning,Connectionism | Conference |
ISBN | Citations | PageRank |
3-540-56798-4 | 2 | 0.41 |
References | Authors | |
3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ian Cloete | 1 | 132 | 16.61 |
Jacques Ludik | 2 | 8 | 1.62 |