A Casual Guide for Artificial Intelligence, Deep Learning, and Python Programmers


What you'll learn:
Conditional probability, Independence, and Bayes' Rule
Use of Venn diagrams and probability trees to visualize probability problems
Discrete random variables and distributions: Bernoulli, categorical, binomial, geometric, Poisson
Continuous random variables and distributions: uniform, exponential, normal (Gaussian), Laplace, Gamma, Beta
Cumulative distribution functions (CDFs), probability mass functions (PMFs), probability density functions (PDFs)
Joint, marginal, and conditional distributions
Multivariate distributions, random vectors
Functions of random variables, sums of random variables, convolution
Expected values, expectation, mean, and variance
Skewness, kurtosis, and moments
Covariance and correlation, covariance matrix, correlation matrix
Moment generating functions (MGF) and characteristic functions
Key inequalities like Markov, Chebyshev, Cauchy-Schwartz, Jensen
Convergence in probability, convergence in distribution, almost sure convergence
Law of large numbers and the Central Limit Theorem (CLT)
Applications of probability in machine learning, data science, and reinforcement learning

Requirements:
College / University-level Calculus (for most parts of the course)
College / University-level Linear Algebra (for some parts of the course)

Description:
Common scenario: You try to get into machine learning and data science, but there's SO MUCH MATH.Either you never studied this math, or you studied it so long ago you've forgotten it all.What do you do?Well my friends, that is why I created this course.Probability is one of the most important math prerequisites for data science and machine learning. It's required to understand essentially everything we do, from the latest LLMs like ChatGPT, to diffusion models like Stable Diffusion and Midjourney, to statistics (what I like to call "probability part 2").Markov chains, an important concept in probability, form the basis of popular models like the Hidden Markov Model (with applications in speech recognition, DNA analysis, and stock trading) and the Markov Decision Process or MDP (the basis for Reinforcement Learning).Machine learning (statistical learning) itself has a probabilistic foundation. Specific models, like Linear Regression, K-Means Clustering, Principal Components Analysis, and Neural Networks, all make use of probability.In short, probability cannot be avoided!If you want to do machine learning beyond just copying library code from blogs and tutorials, you must know probability.This course will cover everything that you'd learn (and maybe a bit more) in an undergraduate-level probability class. This includes random variables and random vectors, discrete and continuous probability distributions, functions of random variables, multivariate distributions, expectation, generating functions, the law of large numbers, and the central limit theorem.Most important theorems will be derived from scratch. Don't worry, as long as you meet the prerequisites, they won't be difficult to understand. This will ensure you have the strongest foundation possible in this subject. No more memorizing "rules" only to apply them incorrectly / inappropriately in the future! This course will provide you with a deep understanding of probability so that you can apply it correctly and effectively in data science, machine learning, and beyond.Are you ready?Let's go!Suggested prerequisites:Differential calculus, integral calculus, and vector calculusLinear algebraGeneral comfort with university/collegelevel mathematics

Who this course is for:
Python developers and software developers curious about Data Science
Professionals interested in Machine Learning and Data Science but haven't studied college-level math
Students interested in ML and AI but find they can't keep up with the math
Former STEM students who want to brush up on probability before learning about artificial intelligence

Homepage

---