- 0 - Introduction
- 1. Optimizing neural networks
- 2. Prerequisites for the course
- 3. Setting up exercise files
- 1 - Introduction to Deep Learning Optimization
- 1. What is deep learning
- 2. Review of artificial neural networks
- 3. An ANN model
- 4. Model optimization and tuning
- 5. The deep learning tuning process
- 6. Experiment setups for the course
- 2 - Tuning the Deep Learning Network
- 1. Epoch and batch size tuning
- 2. Epoch and batch size experiment
- 3. Hidden layers tuning
- 4. Determining nodes in a layer
- 5. Choosing activation functions
- 6. Initializing weights
- 3 - Tuning Back Propagation
- 1. Vanishing and exploding gradients
- 2. Batch normalization
- 3. Optimizers
- 4. Optimizer experiment
- 5. Learning rate
- 6. Learning rate experiment
- 4 - Overfitting Management
- 1. Overfitting in ANNs
- 2. Regularization
- 3. Regularization experiment
- 4. Dropouts
- 5. Dropout experiment
- 5 - Model Tuning Exercise
- 1. Tuning exercise Problem statement
- 2. Acquire and process data
- 3. Tuning the network
- 4. Tuning backpropagation
- 5. Avoiding overfitting
- 6. Building the final model
- 6 - Conclusion
- 1. Continuing your deep learning journey