Dive into Deep Learning

Table Of Contents

2. A Taste of Deep Learning

If you are in a hurry, this chapter has all the details you need to get a taste of deep learning. If you like to take the scenic route, we still recommend that you read it, since it will explain how to set up Apache MXNet, how to use automatic differentiation and how to manipulate data and memory. We also provide quick primers on linear algebra and statistics, designed to help readers to get up to speed on the basics.

• 2.1. Introduction
  • 2.1.1. A motivating example
  • 2.1.2. The dizzying versatility of machine learning
  • 2.1.3. Basics of machine learning
  • 2.1.4. Supervised learning
  • 2.1.5. Unsupervised learning
  • 2.1.6. Interacting with an environment
  • 2.1.7. Conclusion
  • 2.1.8. Discuss on our Forum
• 2.2. Getting started with Gluon
  • 2.2.1. Conda
  • 2.2.2. GPU Support
  • 2.2.3. Conda Environment
  • 2.2.4. Updating Gluon
  • 2.2.5. Summary
  • 2.2.6. Exercise
  • 2.2.7. Discuss on our Forum
• 2.3. Manipulating Data with ndarray
  • 2.3.1. Getting Started
  • 2.3.2. Operations
  • 2.3.3. Broadcast Mechanism
  • 2.3.4. Indexing and Slicing
  • 2.3.5. Saving Memory
  • 2.3.6. Mutual Transformation of NDArray and NumPy
  • 2.3.7. Problems
  • 2.3.8. Discuss on our Forum
• 2.4. Linear algebra
  • 2.4.1. Scalars
  • 2.4.2. Vectors
  • 2.4.3. Length, dimensionality and shape
  • 2.4.4. Matrices
  • 2.4.5. Tensors
  • 2.4.6. Basic properties of tensor arithmetic
  • 2.4.7. Sums and means
  • 2.4.8. Dot products
  • 2.4.9. Matrix-vector products
  • 2.4.10. Matrix-matrix multiplication
  • 2.4.11. Norms
  • 2.4.12. Norms and objectives
  • 2.4.13. Intermediate linear algebra
  • 2.4.14. Conclusions
  • 2.4.15. Discuss on our Forum
• 2.5. Automatic Differentiation
  • 2.5.1. A Simple Example
  • 2.5.2. Training Mode and Prediction Mode
  • 2.5.3. Computing the Gradient of Python Control Flow
  • 2.5.4. Head gradients and the chain rule
  • 2.5.5. Summary
  • 2.5.6. Problems
  • 2.5.7. Discuss on our Forum
• 2.6. Probability and statistics
  • 2.6.1. Basic probability theory
  • 2.6.2. Dealing with multiple random variables
  • 2.6.3. Conditional independence
  • 2.6.4. Summary
  • 2.6.5. Problems
  • 2.6.6. Discuss on our Forum
• 2.7. Naive Bayes Classification
  • 2.7.1. Optical Character Recognition
  • 2.7.2. Summary
  • 2.7.3. Problems
  • 2.7.4. Discuss on our Forum
• 2.8. Sampling
  • 2.8.1. Uniform Distribution
  • 2.8.2. The categorical distribution
  • 2.8.3. The Normal distribution
  • 2.8.4. More distributions
  • 2.8.5. Discuss on our Forum
• 2.9. Documentation
  • 2.9.1. Finding all the functions and classes in the module
  • 2.9.2. Finding the usage of specific functions and classes
  • 2.9.3. API Documentation
  • 2.9.4. Exercise
  • 2.9.5. Discuss on our Forum

Previous

1.2. Using this Book

Next

2.1. Introduction