728x90
https://en.wikipedia.org/wiki/Empirical_risk_minimization
Empirical risk minimization - Wikipedia
Empirical risk minimization (ERM) is a principle in statistical learning theory which defines a family of learning algorithms and is used to give theoretical bounds on their performance. The core idea is that we cannot know exactly how well an algorithm wi
en.wikipedia.org
728x90
'Dic' 카테고리의 다른 글
| Inductive Bias (0) | 2019.11.17 |
|---|---|
| Beta distribution (0) | 2019.11.17 |
| Graph Convolutional Networks (0) | 2019.11.14 |
| ‘model.eval()’ vs ‘with torch.no_grad()’ (0) | 2019.11.05 |
| Semi-supervised learning (0) | 2019.10.31 |