Better Deep Learning
Penalize the large weights with weight regularization
Sparse representation with activity regularization
- large activations may indicate an over-fit model
- there is a tension between the expressiveness and the generalization of the learned features
- encourage small activations with additional penalty
- track activation mean value
Force small weights with weight constraints
Decouple layers with dropout
Promote robustness with Noise
Halt training at the right time with early stopping
Issues Log