Getting started

Many students and instructors find this textbook very easy to read:

• Speech and Language Processing

I would begin your journey by reading through that book and attempting the exercises at the end of each chapter.

If any of the math is confusing, refer to the resources section below.

Resources for math

Everything I've listed here is freely available and largely self-paced study.

Machine learning

• Andrew Ng's Machine learning course
• Overview of machine learning (mathematicalmonk)

Neural Networks

• Neural Networks and Deep Learning
• Neural Networks (3blue1brown)

Statistics and probability theory

• Overview of probability theory (mathematicalmonk)
• Think Bayes

Linear algebra

• Essence of linear algebra (3blue1brown)
• Linear algebra (Khan Academy)
• Linear algebra refresher course (Udacity)

Calculus

• Essence of calculus (3blue1brown)
• Differential calculus (Khan Academy)
• Multivariable calculus (Khan Academy)

Misc

• Khan Academy (all math topics)
• [Information Theory (Khan Academy)](https://www.khanacademy.org/computing/computer-science/informatio= ntheory#moderninfotheory)
• Mathematics of Machine Learning

Intermediate/Advanced

• A Code-First Introduction to Natural Language Processing (fast.ai)
• Neural Network Methods for Natural Language Processing
• Freely available via the library

Resources for programming

• Linux command line basics (Udacity)
• Version control and Git (Udacity)
• Programming basics using Python (Udacity)