Mathematics

Main

• COMPSCI 109A: Data Science 1: Introduction to Data Science github.io

• COMPSCI 109B: Data Science 2: Advanced Topics in Data Science github.io

• Neural Networks and Deep Learning
  • Using neural nets to recognize handwritten digits
  • How the backpropagation algorithm works
  • Improving the way neural networks learn
  • A visual proof that neural nets can compute any function
  • Why are deep neural networks hard to train?
  • Deep learning

Books by Tensorflow

• Deep Learning with Python
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition

Getting into Data Science

1. Machine Learning
2. Linear Algebra
3. Calculus
4. Statistics
5. Optimisation
6. Algebra
7. Discrete Math

• How to Start Learning Deep Learning

Linear Algebra

• MIT Linear Algebra 2010
  • Strang, Gilbert. Introduction to Linear Algebra. 5th ed.
  • Video Lectures

Calculus

• MIT Single Variable Calculus 2006
  • Simmons, George F. Calculus with Analytic Geometry. 2nd ed.
  • Video Lectures
• MIT Multivariate Calculus 2007
  • Edwards, Henry C., and David E. Penney. Multivariable Calculus. 6th ed.
  • Video Lectures

Statistics

• MIT Introduction to Probability and Statistics 2014
• Stat 110 Probability

---

Harvard Prerequisites

Stat 110 recommended.

• Stat 100 Introduction to Quantitative Methods
• Stat 110 Probability
• Stat 111 Introduction to Statistical Inference

American Institute of Mathematics

• OpenIntro Statistics

The four technical core courses:

• AC 209a “Data Science 1: Introduction to Data Science”
• AC 209b “Data Science 2: Advanced Topics in Data Science”
• AM 207 “Advanced Scientific Computing: Stochastic Methods for Data Analysis, Inference, and * Optimization”

• CS 207 “Systems Development for Computational Science”

• AC221 “Critical Thinking in Data Science”