Name
Abstract | ||
|---|---|---|
New estimates for the generalization error are established for the two-layer neural network model. These new estimates are a priori in nature in the sense that the bounds depend only on some norms of the underlying functions to be fitted, not the parameters in the model. In contrast, most existing results for neural networks are a posteriori in nature in the sense that the bounds depend on some norms of the model parameters. The error rates are comparable to that of the Monte Carlo method for integration problems. Moreover, these bounds are equally effective in the over-parametrized regime when the network size is much larger than the size of the dataset. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Machine Learning | Network size,Applied mathematics,Monte Carlo method,Computer science,A priori and a posteriori,Generalization error,Artificial neural network |
DocType | Volume | Citations |
Journal | abs/1810.06397 | 3 |
PageRank | References | Authors |
0.44 | 0 | 3 |