Abstract: 

To be an outstanding data scientist or ML engineer, it doesn't suffice to only know how to use ML algorithms via the abstract interfaces that the most popular libraries (e.g., scikit-learn, Keras) provide. To train innovative models or deploy them to run performantly in production, an in-depth appreciation of the math subjects underlying ML is required: linear algebra, calculus, and probability.
When these math foundations are firm, it also makes it much easier to make the jump from general ML principles to specialized ML domains such as deep learning, NLP, machine vision, and reinforcement learning. This is because, the more specialized the application, the more likely its details for implementation are available only in academic papers or graduate-level textbooks, either of which assume an understanding of the math foundations.
Via hands-on code demos in Python, this workshop provides an overview of why each of the math subjects is essential in ML.

Session Outline
Module 1: Linear Algebra
Solving systems of linear equations. Python tensor libraries: NumPy, TensorFlow, and PyTorch. Linear algebra applications to ML.

Module 2: Calculus
Differential calculus. Partial derivatives. Gradients of cost. Fitting a regression line with gradient descent. Integral calculus. Finding the area under the ROC curve.

Module 3: Probability and Statistics
Probability theory in ML. Probability distributions. Information theory. Bayesian statistics. Frequentist statistics. (Deep) ML vs frequentist approaches.

Bonus module: Computer Science
Algorithms and data structures in ML. Big O notation. Higher-order optimization.

Code repo for hands-on code demos: github.com/jonkrohn/ML-foundations

Bio: 

Jon Krohn is Chief Data Scientist at the machine learning company untapt. He authored the book Deep Learning Illustrated, which was released by Addison-Wesley in 2019 and became an instant #1 bestseller that was translated into six languages. Jon is renowned for his compelling lectures, which he offers in-person at Columbia University, New York University, and the NYC Data Science Academy, as well as online via O'Reilly, YouTube, and his A4N podcast on A.I. news. Jon holds a doctorate in neuroscience from Oxford and has been publishing on machine learning in leading academic journals since 2010.