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 efficiently in production, an in-depth appreciation of machine learning theory (pictured as the central, purple floor of the “Machine Learning House”) is required. And, to cultivate such in-depth appreciation of ML, one must possess a working understanding of the four foundational subjects:
- Linear Algebra
- Calculus
- Probability and Statistics
- Computer Science
When these foundations of the “Machine Learning House” are firm, it also makes it much easier to make the jump from general ML principles (purple floor) to specialized ML domains (the top floor, shown in gray) such as deep learning, natural language processing, 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 typically assume an understanding of the four foundational subjects.
It is for the above reasons that I devised my Machine Learning Foundations curriculum.
I initially developed my ML Foundations curriculum as a series of eight 4-hour live trainings in the O’Reilly learning platform from May through September of this year. The classes were some of the most popular in O’Reilly history, with up to 1400 attendees registering per class.
Since, I’ve begun publishing the course as free YouTube videos and a Udemy course. Producing high-quality video lectures takes a tremendous amount of time, however, so I’m thus far only halfway through publishing the videos of the first foundational subject, linear algebra. My plan is to have all of the linear algebra videos published by the end of the year and the videos for the three remaining subjects — calculus, probability/stats, and computer science — published by the end of 2021.
If you’d like to experience the entirety of my ML Foundations curriculum much sooner, starting on Thursday I’ll be offering it as a “mini bootcamp” of 14 live lectures via AI+ Training (a platform launched this summer by the good folks of the Open Data Science Conference). All of the bootcamp details — including lecture dates, a detailed topic-by-topic syllabus, and an introductory video — are available here.
I love offering online lectures because I get to meet intelligent, ambitious people from all over the world. They can also great for students because of the interactivity. Speaking of which, the course will be filled with paper-and-pencil exercises and we’ll work through the solutions together. On top, I’ve included hundreds of hands-on code demos in Python, with a particular focus on low-level operations in the PyTorch and TensorFlow libraries. All of the code is available open-source in GitHub now.
Upcoming Talks
1. Dec 3, 10, and 17 — Linear Algebra for Machine Learning (in three parts), AI+ Training
2. Jan 13, Jan 27, Feb 10, and Feb 24 — Calculus for Machine Learning (in four parts), AI+ Training
More available on the talks page of my website.
