# Math for Machine Learning Workshop

Do you feel that you lack the mathematical understanding behind machine learning algorithms?

Are you hesitant in learning data science and machine learning because you are not confident about the mathematical prerequisites?

Do you want to brush up on the mathematical concepts you might have studied during college?

Well, this workshop is all about getting you ready and being confident in understanding the mathematical prerequisites like Calculus, Linear Algebra, Probability and Statistics, and Optimisation required to thrive in the field of machine learning.

This one-month workshop (eight sessions) shall cover all these topics live whiteboarding and include a conceptual explanation with a live python demonstration of the same.

We shall also practice numerical problems together, and you will be asked to do a little bit of homework here and there to solidify your understanding.

The workshop is designed to be interactive with smaller batch size and tailored towards an audience looking to improve their mathematical foundations working in the space of Data Science and Machine Learning.

Why learn mathematics for machine learning or data science?

Models and algorithms in Data Science use mathematical constructs in the background. The necessary understanding would help you move beyond standard implementations and unravel the mystery behind these models. You'll be able to read and understand research papers and take on advanced machine learning courses having this understanding.

Course Curriculum

Week 1: Linear Algebra

1. Vectors, Matrices, and Tensors.
2. Matrix Properties, Inverse, and rank
3. System of Linear Equations and Gaussian Elimination
4. Eigenvalue Decomposition
5. Singular Value Decomposition
6. Principal Component Analysis*

Week 2: Multivariate Calculus and Optimisation

1. Functions
2. Limits and Differentials
4. Chain Rule
5. Taylor Series
6. Integrals and Jacobian
7. Optimisation Basics, local and global minima
8. First-order optimisation methods such as gradient descent
9. Optimisation methods used in machine learning
10. Genetic Algorithms

Week 3: Probability and Statistics

1. Probability Basics and Set Theory
2. Random Variables and Probability Distributions
3. Mean and Variance
4. Discrete Distributions such as Binomial and Poisson
5. Continuous Distributions such as Uniform and Normal
6. Bayes Theorem
7. Covariance and Correlation

Week 4: Statistical Inference & Hypothesis Testing

1. Samples and Populations
2. Sampling Distributions
3. Central Limit Theorem
4. T Distribution
5. Hypothesis Testing Process
6. Errors, confidence interval and p value