Modules Topics covered in this class

Below are the 5 core themes of this course. There is 1 homework assignment corresponding to each theme.

Introduction to Machine Learning

1. Introduction to Machine Learning

Overview of machine learning
Classification and regression
Linear Algebra for ML
Linear regression
Logistic regression
Regularization
Training, validation, and testing sets
Evaluation metrics
Cross validation
Python notebooks
NumPy

Tue, Jan 10 - Thu, Jan 19

Python Coding for Machine Learning

2. Python Coding for Machine Learning

Loading data into Python
Pandas
Matplotlib
Scikit-Learn
Testing ML models

Fri, Jan 20 - Wed, Jan 25

Fundamental Learning Algorithms

3. Fundamental Learning Algorithms

Probability and Calculus for ML
Gradient descent
Naive Bayes
K-Nearest Neighbors
Decision trees
Random forests
Support vector machines
Unsupervised learning
Dimensionality reduction
Reinforcement learning

Wed, Jan 25 - Wed, Feb 8

Practical Topics

4. Practical Topics

Recommender systems
Communicating ML results
Natural language processing
Computer vision
Active learning
Fairness
Explainability
Privacy
Implementing your own ML project

Wed, Feb 8 - Tue, May 2

Deep Learning

5. Deep Learning

Neural networks
Backpropagation
Convolutional neural networks
Recurrent neural networks
Transfer learning
Generative adverserial networks
Deep reinforcement learning

Tue, Mar 7 - Tue, Mar 28