Deep Learning Book 21
- [DL Book] 11.5. Debugging Strategies
- [DL Book] 11.4. Selecting Hyperparameters
- [DL Book] 11.3. Determining Whether to Gather More Data
- [DL Book] 11.2. Default Baseline Models
- [DL Book] 11.1. Evaluation Metrics
- [DL Book] 11. Practical Methodologies
- [DL Book] 8.1. How Learning Differs from Pure Optimization
- [DL Book] 8. Optimization for Deep Learning
- [DL Book] 7-13. Adversarial Training
- [DL Book] 7-12. Dropout
- [DL Book] 7-11. Bagging and other Ensemble Methods
- [DL Book] 7-10. Sparse Representations
- [DL Book] 7-9. Parameter Tying and Parameter Sharing
- [DL Book] 7-8. Early Stopping
- [DL Book] 7-7. Multitask Learning
- [DL Book] 7-5. Noise Robustness
- [DL Book] 7-4. Data Augmentation
- [DL Book] 7-3. Regularization and Under-Constrained Problems
- [DL Book] 7-1-1. Parameter Norm Penalties, L1 Regularization
- [DL Book] 7-1-1. Parameter Norm Penalties, L2 Regularization
- [DL Book] 7. Regularization for Deep Learning