Skip to main content
1

Watch videos

Khan Academy Probability library, the full probability video series. Work through these core topics: Theoretical probability, probability from equally likely outcomes. Experimental probability, estimating probability from data. Probability with sample spaces, counting outcomes in a sample space. Addition rule, the probability of A or B. Multiplication rule for independent events and dependent events, the probability of A and B. Conditional probability and independence, conditioning and independence, the basis for Bayes’ rule. An experiment on Sum and Product Rules, a hands-on experiment illustrating the sum and product rules of probability. Random variables, discrete random variables. Probability density functions, continuous random variables.
2

Review probability theory

Refresh the probability foundations used throughout the course. See Probability and Stanford’s Probability for Computer Scientists.
3

Review lecture: Introduction to Machine Learning

Course roadmap and how the pieces of a machine learning system fit together. See GÉRON Chapter 1: The Machine Learning Landscape.
4

Read GERON Chapter 2

The end-to-end machine learning project workflow. See Chapter 2: End-to-End Machine Learning Project.
5

Set up your development environment

Follow the Dev Environment guide to install Docker and configure your container.
6

Import the course repository

Import eng-ai-agents to your GitHub account and clone it locally.
7

Clone the Hands-On ML repository

Clone the companion repository for Hands-On Machine Learning with Scikit-Learn and PyTorch by Aurélien Géron: github.com/ageron/handson-mlp. This repository contains all the notebook exercises referenced throughout the course.
1

Watch videos

Statistical learning theory videos in the media library.
2

Review lecture: Supervised Learning

The supervised learning problem: learning a mapping from labeled examples. See The Learning Problem.
3

Review lecture: Linear Regression

Regression fundamentals and empirical risk minimization. See Linear Regression.
4

Review lecture: SGD Optimization

Stochastic gradient descent for minimizing the empirical risk. See SGD.
5

Read GERON Chapter 4, SGD sections

Read the Gradient Descent, Batch Gradient Descent, Stochastic Gradient Descent, and Mini-Batch Gradient Descent sections from Chapter 4: Training Linear Models.
6

Run the GERON Chapter 4 notebook

Work through the Training Linear Models notebook.
7

Run the SGD notebook

Execute the SGD Sinusoidal Dataset notebook in your container.
8

Assignment 1

Assignment 1 is released this week. Start Assignment 1.
1

Watch videos

Statistical learning theory videos in the media library.
2

Review lecture: Entropy

Information theory principles and cross-entropy. See Entropy.
3

Review lecture: Marginal Maximum Likelihood

Marginal likelihood and parameter estimation. See Marginal Maximum Likelihood.
4

Review lecture: Conditional Maximum Likelihood

Conditional likelihood for supervised learning. See Conditional Maximum Likelihood.
5

Review lecture: Classification Introduction

Classification fundamentals and decision boundaries. See Classification Introduction.
6

Review lecture: Logistic Regression

Binary classification with logistic regression. See Logistic Regression.
7

Assignment 2

Assignment 2 is released this week. Start Assignment 2.
1

Watch videos

Dense neural networks videos in the media library.
2

Read GERON Chapter 9 and DL Chapter 6

From Perceptron to MLPs, backpropagation fundamentals. See Chapter 9: Artificial Neural Networks.
3

Review lecture: DNN Introduction

Neural network architectures and forward pass. See DNN Introduction.
4

Review lecture: Backpropagation

Gradient computation and the chain rule. See Backpropagation.
5

Run the GERON Chapter 9 notebook

Work through the Artificial Neural Networks notebook.
6

Read GERON Chapter 10, Classification MLPs

Read the Classification MLPs section from Chapter 10: Neural Nets with PyTorch.
1

Watch videos

Convolutional neural networks videos in the media library.
2

Read DL Chapters 9 & 10, GERON Chapter 12

Convolutional Neural Network architecture and applications. See Chapter 12: Deep Computer Vision with CNNs.
3

Review lecture: CNN Introduction

Convolution operations, pooling, and spatial feature hierarchies. See CNN Introduction.
4

Review lecture: CNN Layers

Layer types and architectural patterns. See CNN Layers.
5

Review lecture: CNN Architectures and ResNets

ResNet, VGG, and other architectures. See CNN Example Architectures and Feature Extraction with ResNet.
6

Read GERON Chapter 12, CNN sections

Read the Convolutional Layers, Pooling Layers, and CNN Architectures sections from Chapter 12: Deep Computer Vision with CNNs.
7

Run the GERON Chapter 12 notebook

Work through the Deep Computer Vision with CNNs notebook.
8

Assignment 3

Assignment 3 is released this week. Start Assignment 3.
1

Watch videos

Natural language processing videos in the media library.
2

Read GERON Chapter 14

Natural language processing problem formulation and component mechanics. See Chapter 14: Natural Language Processing with RNNs and Attention.
3

Review lecture: NLP Pipelines

Tokenization, embeddings, and NLP pipeline components. See NLP Pipelines.
4

Review lecture: Word2Vec

Word embeddings and distributional semantics. See Word2Vec.
5

Assignment 4

Assignment 4 is released this week. Start Assignment 4.
1

Watch videos

Recurrent neural networks and Transformers videos in the media library.
2

Read GERON Chapters 14 & 15, DL Chapter 10

RNN/LSTM architectures, attention mechanisms, Transformer framework. See Chapter 14: Natural Language Processing with RNNs and Attention and Chapter 15: Transformers for NLP and Chatbots.
3

Review lecture: RNNs and LSTMs

Recurrent architectures for sequence modeling. See RNN Introduction.
4

Review lecture: Transformers

Self-attention and the Transformer architecture. See Transformers Introduction.
5

Run the GERON Chapter 13 notebook

Work through the Processing Sequences Using RNNs and CNNs notebook.
1

Data lakehouse project

Build the data lakehouse project.
Edit this page on GitHub or file an issue.