Deep-Learning-with-python

1. Building First Neural Network using Keras

• Load Model
• Define Model
• Compile Model
• Fit Model
• Evaluate Model

2. Evaluating performance of DL models

• Using Automatic Verification dataset
• Using Manual Verification dataset
• Using k-fold cross validation

3. Using Keras with Sklearn for General Machine Learning

• Evaluate Models with Cross Validation
• Grid Search Deep Learning Parameters

4. Regression Of Boston House Prices

• Developing a Baseline Neural Network Model
• Lifting Performance By Standardizing The Dataset
• Tuning The Neural Network Topology
  • Evaluating a Deeper Network Topology
  • Evaluating a Wider Network Topology

5. Saving Models with Serialization

• Saving and Loading Keras model weights to HDF5 formatted files
• Saving and Loading Keras model structure to JSON files
• Saving and Loading Keras model structure to YAML files

6. Checkpointing Neural Network Models

• Checkpointing Neural Network Model Improvements
• Checkpointing Best Neural Network Model Only
• Loading a Saved Neural Network Model

7. Understanding Model Behaviour By Plotting History

• A plot of accuracy on the training and validation datasets over training epochs
• A plot of loss on the training and validation datasets over training epochs

8. Reducing Overfitting with Dropout Regularization

• Using a Dropout on Visible Layer
• Using a Dropout on Hidden Layers

9. Learning Rate Schedules for training neural network model

• Time-Based Learning Rate Schedule
• Drop-Based Learning Rate Schedule

10. Image Augmentation for improving model performance

• Feature-wise standardization.
• ZCA whitening.
• Random rotation,shifts,shear and flips.
• Dimension reordering.
• Save augmented images to disk.