The fundamental mathematical tools needed to understand machine learning include linear algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability and statistics. These topics are traditionally taught in disparate courses, making it hard for data science or computer science students, or professionals, to efficiently learn the mathematics.
What you'll learn
- Python
- Calculus
- Linear Algebra
- Probability
- Statistics
- Multivariable Calculus
Requirements
- Desktop/ Laptop
- Internet connectivity min 2 Mbps
Target Audience
- Data Scientist
- Data Engineer
- Software Developer
- NLP Engineer
- Machine Learning Engineer
- Introduction to Scalars and Vectors
- Matrices
- Introduction to Vector Spaces
- Norms and Transformation of Vector Spaces
- Why we need calculus for ML
- Multivariable Calculus
- Tangent (hyper) plane, Critical points – The direction of steepest ascent/descent
- Introduction to Optimization
- Why Quantify Risk and Uncertainty with Statistics and Probability
- Types of Data, Introduction to basic terms used in statistics,
- Inferential Statistics
The Pre - Learning course is all about learning and implementing Python from scratch. So, no prior expertise is required in this learning period.
The lectures will be recorded and all of them will be available online at the website.
Anyone, regardless of their field of study, can apply. We do, however, expect you to have a strong interest in the domain and determination throughout the learning period..
