DL Book 8 - Hyperparameter Tuning and Model Optimization for Entry-level

Table of Contents

1. Introduction

1.1 What is Hyperparameter Tuning and Why is it Important?

1.2 What are the Common Hyperparameters and How to Choose Them?

1.3 What are the Challenges and Trade-offs of Hyperparameter Tuning?

1.4 What are the Goals and Objectives of this Book?

2. Hyperparameter Tuning Methods

2.1 Grid Search

2.2 Random Search

2.3 Bayesian Optimization

2.4 Gradient-based Optimization

2.5 Evolutionary Algorithms

2.6 Meta-learning and Transfer Learning

3. Model Optimization Techniques

3.1 Pruning and Quantization

3.2 Distillation and Compression

3.3 Knowledge Graphs and Embeddings

3.4 Neural Architecture Search

3.5 AutoML and AutoKeras

4. Hyperparameter Tuning and Model Optimization in Practice

4.1 How to Set Up a Hyperparameter Tuning Pipeline?

4.2 How to Evaluate and Compare Different Models and Methods?

4.3 How to Interpret and Visualize the Results of Hyperparameter Tuning?

4.4 How to Deploy and Monitor the Optimized Models?

5. Fun Challenges and Projects

5.1 Challenge 1: Tune a Linear Regression Model for House Price Prediction 5.2 Challenge 2: Tune a Convolutional Neural Network for Image Classification 5.3 Challenge 3: Tune a Recurrent Neural Network for Text Generation

5.4 Challenge 4: Optimize a Transformer Model for Machine Translation

5.5 Challenge 5: Optimize a GPT-3 Model for Text Summarization