Deep Learning in Quantitative Finance

Table of Contents

1. Cover
2. Table of Contents
3. Title Page
4. Copyright
5. Dedication
6. Acknowledgements
7. Part One: Introducing Deep Neural Networks
   1. Chapter 1: Introduction
      1. 1.1 WHAT THIS BOOK IS ABOUT
      2. 1.2 THE RISE OF AI
      3. 1.3 THE PROMISE OF AI IN QUANTITATIVE FINANCE
      4. 1.4 PRACTICALITIES
      5. 1.5 READING THIS BOOK
      6. NOTES
8. Part Two: Foundations
   1. Chapter 2: Feedforward Neural Networks
      1. 2.1 INTRODUCING NEURAL NETWORKS
      2. 2.2 REGRESSION AND CLASSIFICATION
      3. 2.3 ACTIVATION FUNCTIONS
      4. 2.4 THE UNIVERSAL FUNCTION APPROXIMATION THEOREM
      5. 2.5 CONCLUSIONS
      6. NOTES
   2. Chapter 3: Training Neural Networks
      1. 3.1 BACKPROPAGATION AND ADJOINT ALGORITHMIC DIFFERENTIATION
      2. 3.2 DATA PREPARATION AND SCALING
      3. 3.3 WEIGHT INITIALISATION
      4. 3.4 THE CHOICE OF LOSS FUNCTION
      5. 3.5 OPTIMISATION ALGORITHMS
      6. 3.6 COMMON TRAINING PROBLEMS
      7. 3.7 BATCH NORMALISATION
      8. 3.8 EVALUATION AND VALIDATION
      9. 3.9 SOBOLEV TRAINING: USING FUNCTION DERIVATIVES
      10. 3.10 CONCLUSIONS
      11. NOTES
   3. Chapter 4: Regularisation
      1. 4.1 INTRODUCTION: REGULARISATION AND GENERALISATION
      2. 4.2 WEIGHT DECAY
      3. 4.3 EARLY STOPPING
      4. 4.4 ENSEMBLE METHODS AND DROPOUT
      5. 4.5 DATA AUGMENTATION
      6. 4.6 OTHER REGULARISATION METHODS
      7. 4.7 CONCLUSIONS: REGULARISATION STRATEGY
      8. NOTE
   4. Chapter 5: Hyperparameter Optimisation
      1. 5.1 INTRODUCTION
      2. 5.2 MANUAL
      3. 5.3 GRID SEARCH
      4. 5.4 RANDOM SEARCH
      5. 5.5 BAYESIAN OPTIMISATION
      6. 5.6 BANDIT-BASED
      7. 5.7 POPULATION-BASED TRAINING (PBT)
      8. 5.8 CONCLUSION
   5. Chapter 6: Convolutional Neural Networks
      1. 6.1 INTRODUCTION
      2. 6.2 CONVOLUTIONS
      3. 6.3 DOWNSAMPLING
      4. 6.4 DATA AUGMENTATION
      5. 6.5 TRANSFER LEARNING: USING PRE-TRAINED NETWORKS