Click here if you don’t want to read my little spiel: https://
Over the past year, I’ve been releasing courses on math prerequisites for data science and machine learning, including Calculus and Linear Algebra.
One thing I noticed from students is that even if they had rudimentary knowledge of Calculus and Linear Algebra, they often struggled when it came to combining them.
If you took my Linear Regression course, Logistic Regression course, or Deep Learning in Python (focused on backpropagation) course, and you had difficulties, this means you.
The problem is, there is no course in college/university that teaches this. When you go on to study statistics, finance, control theory, signal processing, digital communications, etc. you are simply expected to know how to do this.
Since this is such a common pain point, I decided to do something about it.
This course is the “lost course” in STEM that bridges the gap between 1st-2nd year math and more advanced applied math in engineering and statistics.
The premise is simple: It covers common matrix and vector derivatives, along with fundamental optimization techniques including gradient descent and Newton’s method in multiple dimensions.
If you previously struggled with these subjects, now is your chance to conquer them!
So what are you waiting for?