- Entropy
The level of uncertainty. It must range between 0 and 1. 0 < entropy < 1 certain uncertain |
The greater the value of entropy, the greater the uncertainty for probability,
the smaller the value the less the uncertainty.
reference : towardsdatascience.com/cross-entropy-loss-function-f38c4ec8643e
- Cross-Entropy
How far it is from the actual expected value, is used when adjusting model weights during training. The smaller the loss the better the model.
'Machine Learning' 카테고리의 다른 글
tensorflow (0) | 2022.03.16 |
---|---|
Glance ML (0) | 2022.03.11 |
Support Vector Machine, Margin, Kernel, Regularization, Gamma (0) | 2021.03.30 |
Softmax (0) | 2021.03.24 |
Logistic Regression, Sigmoid function (0) | 2021.03.17 |