My Bootcamp
Lecture 1: Math in AI
AI is math, not magic, Lecture 1 outlines the four main themes of the bootcamp: linear algebra, calculus, probability, and statistics. We also take a quick trip down the history of AI and why AI has accelerated so prominently in recent years.
Lecture 2: Linear Algebra
Lecture 2 dives into the data structures necessary for AI models to operate the way that they do, vectors and matrices. It also goes into the vector and matrix operations that make bulk mathematical calculations possible.
Lecture 3: Calculus
Lecture 3 details how an AI model actually "learns." We set up the supervised machine learning formulation with our data structures and derive the gradient descent algorithm, the process by which every AI model converges to a solution.
Lecture 4: Probability
Every generative AI model explicitly states that it may output incorrect solutions, and this session gives the mathematical reasons why. AI models produce variations of the mathematically most probable output, not necessarily the definitively correct one for your intents and purposes!
Lecture 5: Statistics
An AI model is only as good as the data it is trained upon, and the data is only as good as the subsample of the whole data population it is derived from. This session breaks down the considerations taken when validating the efficacy and generalizability of an AI model along with a few closely related tangents.
Certification
The certification exam is designed to take no more than 20-minutes and has unlimited tries. Go get your certification, and enjoy the mathematics visualization tool you receive with a 100% grade!