Textbook for Winter and Spring

The book that we will be using for the tutorials on machine learning and neural networks is Hands-On Machine Learning with Scikit-Learn and TensorFlow by Aurélien Géron.

Mathematical Preliminaries for Machine Learning

The machine learning tutorial next term will require a basic knowledge of both linear algebra and probability theory. In almost every case I will be presenting mini-lectures that cover the basics of these topics as we encounter them. Even so, you may find it useful to refresh your knowledge of these topics over the December break before class starts in January.

Here is a list of specific topics you should be familiar with.

Linear Algebra

• Basic vector operations: vector addition, dot product and norm
• Matrix multiplication
• Basis for a vector space and representing a vector as a combination of basis vectors
• Eigenvalues and eigenvectors

There is a free textbook on linear algebra available online at http://linear.ups.edu/html/fcla.html I recommend looking at the chapters on Vectors, Vector Spaces, Eigenvalues, and Representations.

Probality Theory and Statistics

• Discrete and continuous probability distributions
• Computing the probability of an event from a probability distribution
• The normal distribution
• Basic statistics for a set of sample points, including mean and variance

There is a free online book giving an introduction to statistics for Python programmers available at http://greenteapress.com/thinkstats2/html/index.html.

You might also want to check out the review of probability theory for machine learning available at https://see.stanford.edu/materials/aimlcs229/cs229-prob.pdf. (Some of the topics covered here are beyond the scope of what we will cover next term.)