Machine Learning & AI

Introduction

This is my journey with this new world of ML & AI.

ML is mathematics centric domain. So first step for me was to get hold of all the mathematical knowledge I will be needing down the line.

Linear Algebra

The first milestone was Linear Algebra.

Before onboarding this journey, I did a lot of research and found out that one has to be exceptionally good with linear algebra to do good in the field of ML & AI.

Now the question came in my mind was, Where to start with?

3Blue1Brown - Essence of linear algebra (link) Duration ( ~= 2.8 hrs )

For the starters, I started with a series of videos by 3Blue1Brown on Essence of linear algebra.

Reason being I was not in touch with core algebraic solution for quite a long time. So wanted to revise stuff before diving deep into this stream.

This playlist goes as follows.

• 1. Vectors, What even are they? (Duration : 9:51 min)

  2. Linear combinations, span, and basis vectors (Duration : 9:59 min)

  3. Linear Transformation and metrices (Duration : 10:59 min)

  4. Matrix multiplication as composition (Duration : 10:03 min)

  5. Three-dimensional linear transformations (Duration : 4:45 min)

  6. The determinant (Duration : 10:02 min)

  7. Inverse matrices, column space and null space (Duration : 12:09 min)

  8. Nonsquare matrices as transformations between dimensions (Duration : 4:27 min)

  9. Dot products and duality (Duration : 14:12 min)

  10. Cross Products (Duration : 8:53 min)

  11. Cross Products in the light of liner transaformation (Duration : 13:10 min)

  12. Cramer's rule explained geometrically (Duration : 12:12 min)

  13. Change of basis (Duration : 12:51 min)

  14. Eigenvectors and eigenvalues (Duration : 17:16 min)

  15. Abstract vector space (Duration : 16:46 min)

Cheat Sheet

• • AB != BA

  • A(BC) == (AB)C

  • A^-1A == I