Name
Abstract | ||
|---|---|---|
Bounds on the number of training examples needed to guarantee a certain level of generalization performance in the ARTMAP architecture are derived. Conditions are derived under which ARTMAP can achieve a specific level of performance assuming any unknown, but fixed, probability distribution on the training data |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/ICNN.1997.616176 | Neural Networks,1997., International Conference |
Keywords | Field | DocType |
art neural nets,generalisation (artificial intelligence),learning (artificial intelligence),neural net architecture,performance evaluation,probability,artmap,pac learning,generalization,learning algorithm,neural architecture,probability distribution,computer science,testing,machine learning,learning artificial intelligence,computer architecture,neural networks,training data | Training set,Architecture,Computer science,Probability distribution,Neural net architecture,Artificial intelligence,Artificial neural network,Machine learning | Conference |
Volume | ISBN | Citations |
2 | 0-7803-4122-8 | 4 |
PageRank | References | Authors |
0.47 | 2 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Heileman, G.L. | 1 | 26 | 4.69 |
| Michael Georgiopoulos | 2 | 641 | 65.56 |
| Healy, M.J. | 3 | 4 | 0.47 |
| Verzi, S.J. | 4 | 6 | 0.89 |