Free Math for Machine Learning Learning Path

An interactive deep learning book with code, math, and discussions. It includes a chapter on training on multiple GP Us, covering both from-scratch implementations and concise implementations using deep learning frameworks.

This book provides a practical introduction to exploratory data analysis using Python. It covers topics such as distributions, probability, and hypothesis testing. The book is very hands-on and includes many case studies.

This course covers fundamental mathematical concepts for machine learning, including derivatives, integrals, and optimization techniques like gradient descent.

This course in the DeepLearning.AI specialization covers the essential calculus concepts needed to understand and build machine learning models.

Offered by Duke University, this beginner-level course covers the foundational math skills needed for data science.

A comprehensive introduction to the mathematical principles that form the foundation of artificial intelligence and machine learning, bridging essential concepts with real-world AI applications.

This course covers making inferences from sample data to the broader population. It delves into the principles of significance testing, including p-values, power, and Type I and II errors, and covers a wide range of statistical tests for different data types and research designs.

Part of the DeepLearning.AI specialization, this course teaches the core concepts of linear algebra and how they are applied in machine learning and data science.

The third course in the DeepLearning.AI specialization, focusing on the fundamentals of probability and statistics for machine learning and data science.

This beginner-level course introduces the concepts of linear algebra that are relevant to AI, machine learning, and deep learning.

This course covers the mathematical foundations of optimization and its applications in data science.

This course covers the essential concepts of multivariate calculus required for machine learning, including gradient descent and optimization. It is part of the Mathematics for Machine Learning Specialization.

An intermediate-level course that introduces the mathematical foundations to derive Principal Component Analysis (PCA), a fundamental dimensionality reduction technique. It covers basic statistics of data sets, such as mean values and variances and the computation of distances and angles between vectors using inner products.

This 5-course specialization is intended for professionals seeking to develop a skill set for interpreting statistical results. You will cover descriptive statistics, data visualization, measurement, regression modeling, probability and uncertainty to prepare you to interpret and critically evaluate a quantitative analysis.

This specialization covers the essential mathematical foundations for machine learning, including linear algebra, multivariate calculus, and principal component analysis (PCA). It's designed to provide the necessary mathematical background for a career in ML.

Part of Harvard's Data Science Professional Certificate, this course covers the fundamentals of probability theory needed for a data science career.

This course from Microsoft on edX covers the essential mathematical foundations for machine learning and AI using Python.

This MIT course develops a deep understanding of the principles of statistical inference, including estimation, hypothesis testing, and prediction, on firm mathematical grounds.

A self-paced course that provides a solid knowledge base in statistics, linear algebra, multivariable calculus, and probability for AI.