Amir-Hossein Karimi
Login
Amir-Hossein Karimi/Machine Learning Essentials: from Theory to Practice
Buy now

  • $297

Machine Learning Essentials: from Theory to Practice

  • Course
  • 196 Lessons

AI and Machine Learning are transforming industries—but diving into these fields can feel overwhelming, with surface-level tutorials and dense theory leaving you stuck. This 24-hour course is your guide to cutting through the noise. Tailored for professionals and students eager to stand out, we help you confidently master ML concepts and their real-world applications.
Enroll Now

The interactive course you've always sought

What makes this course truly unique is the opportunity to learn not only from Prof. Karimi, a world-renowned AI expert, but also from an intimate cohort of 10 highly engaged participants—ranging from undergraduates to postdocs in fields like engineering, biology, and physics (including string theory). Together, you’ll ask and answer questions, engage in meaningful discussions, and share insights that enrich the learning experience for everyone involved. Listen to what previous students had to say 👇🏼

  • Why did you enrol in this course?

  • How did this course help you?

  • To whom would you recommend this course?

About the instructor

Amir-Hossein Karimi, PhD (ETH Zurich, Max Planck)

Professor Karimi is an award-winning educator and sought-after speaker known for his engaging and impactful teaching in Machine Learning and AI. He is a Professor of Computer Engineering and Computer Science at the University of Waterloo and a faculty affiliate at Toronto’s Vector Institute. He has delivered talks and presentations at MIT, Harvard, ETH Zurich, DeepMind, and Google Brain, and tutorials on Causal Explainable AI (KDD 2023) and Algorithmic Recourse (Toronto ML Summit 2024). With over 15 years of experience at Meta, DeepMind, and Google Brain, Prof. Karimi specializes in translating foundational machine learning concepts into practical applications and providing expert consulting services to startups worldwide. In his very first term teaching, Prof. Karimi received the prestigious Igor Ivkovic Teaching Excellence Award, and he is also among a handful Google PhD Fellowship recipients globally.

Linked_inYoutubeXInstagramWebsite

Contents

Move beyond surface-level tutorials to gain deep insights into core concepts, historical developments, and the pioneers shaping the field since the 1950s. Each lesson is designed to help you discover the intuition behind algorithms, connect theory to real-world applications, and gain the tools to stand out in a rapidly evolving landscape.

🎯 Start here

The ideal student for this course has a working knowledge of linear algebra, calculus, probability, statistics, programming, and a bit of optimization.

To help you determine if this course is right for you, we’ve included a self-assessment exercise. This exercise will allow you to test your knowledge and identify areas you may want to brush up on.

For those who need a refresher, the exercise includes a PDF with free resources to help you revisit and strengthen these foundational topics.

Once you purchase the course, you’ll gain access to the solutions for the self-assessment exercise, providing deeper insights and guidance.

Start here to ensure you're fully prepared to maximize your learning experience!

Self-assessment exercise - questions.pdf
Preview
Self-assessment exercise - solutions.pdf

👋🏼 Introductions, History of ML, and Course Overview

lec 01 - handout.pdf
Welcome 🤗
Who are we?
What is intelligence?
What is machine learning?
What machine learning is not
Types of machine learning
A brief history of machine learning
Preview
An overview of machine learning applications
Timetable and course logistics
Quiz

🏘️ Nearest Neighbors

lec 02 - handout.pdf
Overview
What is data?
Redundancies in data
How is data represented?
Datasets of training and testing
Overview of the nearest neighbors algorithm
L-p norms and cosine similarity
Preview
The nearest neighbor algorithm
The k-nearest neighbors algorithm
Cross-validation & generalization
On the pitfalls of k-NN & summary
Quiz

🌲 Decision Trees

lec 03 - handout.pdf
Introduction
An overview of decision trees
On the decision boundaries of decision trees
Discrete decision trees
On the expressiveness of decision trees
Intuition for learning decision trees
Preview
Uncertainty quantification, entropy, & information gain
Preview
Learning decision trees in action
Summary of decision trees
Quiz

🌐 Generalization & Ensembling

lec 04 - handout.pdf
Motivation
The bias-variance tradeoff
Preview
Ensembling overview & discussion
Preview
Bagging
Boosting
Summary & discussion
Quiz

📈 Linear Regression

lec 05 - handout.pdf
Motivation
A modular approach to learning
Regression step #1 - defining the model
Loops vs vectorized code
Regression step #2 - defining the loss
Regression step #3 - optimizing the loss
Analytical solution to regression
Iterative solution to regression (gradient descent)
Preview
Polynomial and regularized regression
Summary & discussion
Quiz

🕵🏼‍♂️ Linear Classification & Perceptron

lec 06 - handout.pdf
Motivation
Formulating linear classifiers
Loss functions for linear classification
Precision and recall
Preview
The Perceptron algorithm
On the existence and identification of nonlinear transformations
Preview
Multi-class classification + discussion
Quiz

〰️ Logistic Regression

lec 07 - handout.pdf
Review of linear regression and linear classification
Linear classification via thresholded activations
Linear classification via sigmoidal activations
Preview
Summary of attempts to linear classification
Probabilistic interpretation of logistic regression
Maximum Likelihood Estimation for logistic regression
Summary & discussion
Quiz

📏 Support Vector Machines

lec 08 - handout.pdf
Introducing Bernhard Schölkopf
Motivation (what makes a good linear classifier?)
Intuition for max-margin classification
Formulating max-margin classification
Preview
Duality and Lagrangian multipliers
Learning linear SVMs
SVMs with slack variables
Nonlinear SVMs
Summary
Quiz

🧠 Neural Networks

lec 09 & 10 - handout.pdf
Motivation
On the linear separability of NOT, AND, & XOR logic gates
Hand-designed feature engineering
Biological, computational, and artificial neurons
Preview
Feed-forward neural networks
Hierarchical feature learning
Discussion
Quiz

🔄 Backpropogation

lec 09 & 10 - handout.pdf
Mid-class review
On the expressivity of neural networks
Solving XOR using neural networks
Preview
An overview of backpropogation
Backpropogation example #1
Multivariate chain rule
Backpropogation example #2
Putting it all together: the backpropogation algorithm
Discussion
Quiz

📷 Convolutional Neural Networks - part I

lec 11 - handout.pdf
Introduction
Neural networks for computer vision
1D convolutions
2D convolutions
An intuition for convolutions
Preview
Mid-class review
Convolutions as layers
Example convolutions & Toeplitz matrices
On the hyperparameters of convolutions hparams
Pooling layers
1x1 convolutions and their usecases
Quiz

📸 Convolutional Neural Networks - part II

lec 12 - handout.pdf
Motivation
Data for computer vision
Compute for computer vision
Architectures for computer vision
Preview
Metrics for computer vision
Training tips & tricks
Discussion
Quiz

💭 Natural Language Processing - part I

lec 13 - handout.pdf
Motivation
N-gram language models
Preview
Distributional embeddings
Neural n-gram models
Evaluations
Discussion
Quiz

💬 Natural Language Processing - part II

lec 14 - handout.pdf
Review & overview
Recurrent Neural Networks example #1
Recurrent Neural Networks example #2
Recurrent Neural Networks over words & characters
Exploding and vanishing gradients
Long Short-Term Memory models (LSTMs)
Chaining recurrent cells
Preview
Transformers and their applications
Summary
Quiz

🌤️ Probabilistic Models: Discriminative vs Generative

lec 15 - handout.pdf
Introduction
Probability vs likelihood
Maximum Likelihood Estimation for Bernoullis
Preview
Maximum Likelihood Estimation for Gaussians
Preview
Maximum Likelihood Estimation in past models
Discriminative vs generative models
An overview of Bayes classifiers
On the risk of a classifier
Gaussian discriminant analysis intuition
Gaussian discriminant analysis learning, inference, and decision boundaries
Naive Bayes & summary
Quiz

🔗 Clustering and Density Estimation: k-Means and Mixtures of Gaussians

lec 16 - handout.pdf
Motivation
K-means overview
K-means for segmentation & quantization
K-means objective, loss, and challenges
Preview
Soft K-means
Mixture of Gaussians intuition
Preview
Mixture of Gaussians in higher dimensions
Mixture of Gaussians formalities
Expectation Maximization & discussion
Quiz

🔥 Dimensionality Reduction: Principal Component Analysis

lec 17 - handout.pdf
Motivation
Formalizing dimensionality reduction
Vectors, spaces, norms, orthogonality, and independence
Preview
Matrices as linear transformations
Eigenvalues and eigenvectors
Eigendecomposition of the covariance matrix
Step-by-step Principal Component Analysis (PCA)
Two interpretations of PCA
Applications of PCA
Random projections & discussion
Quiz

🤖 Reinforcement Learning

lec 18 - handout.pdf
Motivation for Reinforcement Learning (RL)
Formulating RL - part 1 (policies)
Formulating RL - part 2 (value functions)
Preview
Examples of RL systems
Preview
Formulating and solving example MDPs
Solving MDPs: value iteration and policy iteration
Exploration & exploitation & discussion
Quiz
Student Course Perceptions & class photo

✍️ Self-guided Assignments

The course includes self-guided assignments designed to reinforce your understanding of key concepts. While solutions are not provided, you can collaborate, discuss, and share insights with fellow learners in the Discord community, fostering a supportive and interactive learning environment. These assignments are a great way to deepen your knowledge and apply what you've learned!

Assignment 1/3.pdf
Assignment 2/3.pdf
Assignment 3/3.pdf

Frequently asked questions

You've got questions. We've got answers.

What is the price of the course?

The course is just $475, which is less than the price of a coffee per lesson for over 175 lessons! ☕📚

What is the format of the course?

The course offers 24 hours of on-demand video content, allowing you to learn at your own pace. Review, take notes, and revisit any of the 175+ engaging lessons, quizzes, and assignments.

Do I get lifetime access to the videos?

Yes, once you purchase the course, you will have lifetime access to all the video content, slides, quizzes, among others.

Are there any prerequisites?

Yes, you should have a working knowledge of linear algebra, calculus, probability, statistics, programming, and a bit of optimization.

Not sure if you're ready? 🤔

Even if you're new to some topics, or would like to brush up on others, our free self-assessment exercise and free curated resources will help you get started!

What additional material will I get with the course?

  • Top-notch slides for all lessons.

  • 30 in-depth, hands-on assignment questions to solidify your understanding.

  • 100+ targeted quizzes to ensure you’re ready to ace interviews with confidence.

  • The history of the ML field, including key researchers and breakthroughs.

  • Interactive content, featuring Q&A and discussions with global peer insights.

  • A 1:1 session with Prof. Karimi (valued at $375), offering personalized guidance.

Is this course right for me?

This course is designed for professionals and students who are serious about:

  • Standing out in the competitive ML field.

  • Gaining deep, foundational knowledge grounded in theory and intuition.

  • Moving beyond surface-level tutorials to truly understand the concepts.

Still not sure? 🤔

Try the course risk-free—if it’s not for you, we offer a hassle-free, 14-day refund guarantee.

What past students said about the course...

💡 “The reasoning behind ML algorithm designs was covered really well. The assignments were long but extremely helpful in understanding the concepts. Fantastic course overall!”

💡 “The perfectly designed lecture slides, in the form of interrogative content, helped me understand better.”

💡 “I learned how ML is rooted in linear algebra and statistics. The professor’s attitude, engaging lectures, and relevant assignments made all the difference!”

💡 “Never really paid attention to ML before, but the overall learning experience created by Prof. Karimi influenced me to dig deeper into the subject. The lectures were passionate, engaging, and easy to understand.”

💡 “This course helped me understand the fundamentals of ML, AI, and Deep Learning, as well as how algorithms work under the hood. Prof. Karimi did an amazing job conveying the material through examples, class interactions, and engaging slides.”

💡 “The fundamentals of ML were explained clearly, and the focus on deep learning and individual model mechanisms was incredibly insightful. The mix of math and practical exercises helped me truly grasp how models work.”

This photo captures my very first class as a professor at the University of Waterloo, where I was honored to be nominated by my students and receive the prestigious Igor Ivkovic Teaching Excellence Award. Together, we built a vibrant learning community that valued curiosity, collaboration, and growth. Now, it’s your turn to become part of this revolution in Machine Learning education.

Don’t miss out— accelerate your career in AI us today!