Machine Learning with Python: from Linear Models to Deep Learning

Course Description

Machine learning methods are commonly used across engineering and sciences, from computer systems to physics. Moreover, commercial sites such as search engines, recommender systems (e.g., Netflix, Amazon), advertisers, and financial institutions employ machine learning algorithms for content recommendation, predicting customer behavior, compliance, or risk.

As a discipline, machine learning tries to design and understand computer programs that learn from experience for the purpose of prediction or control. 

In this course, students will learn about principles and algorithms for turning training data into effective automated predictions.  We will cover:

• Representation, over-fitting, regularization, generalization, VC dimension;
• Clustering, classification, recommender problems, probabilistic modeling, reinforcement learning;
• On-line algorithms, support vector machines, and neural networks/deep learning.

What you will learn

• Understand principles behind machine learning problems such as classification, regression, clustering, and reinforcement learning


• Implement and analyze models such as linear models, kernel machines, neural networks, and graphical models


• Choose suitable models for different applications


• Implement and organize machine learning projects, from training, validation, parameter tuning, to feature engineering.

Pre-Requesities

• 6.00.1x or proficiency in Python programming 


• 6.431x or equivalent probability theory course


• College-level single and multi-variable calculus


• Vectors and matrices

Syllabus

Lectures:

• Introduction


• Linear classifiers, separability, perceptron algorithm


• Maximum margin hyperplane, loss, regularization


• Stochastic gradient descent, over-fitting, generalization


• Linear regression


• Recommender problems, collaborative filtering


• Non-linear classification, kernels


• Learning features, Neural networks


• Deep learning, back propagation


• Recurrent neural networks


• Recurrent neural networks


• Generalization, complexity, VC-dimension


• Unsupervised learning: clustering


• Generative models, mixtures


• Mixtures and the EM algorithm


• Learning to control: Reinforcement learning


• Reinforcement learning continued


• Applications: Natural Language Processing

• Automatic Review Analyzer


• Digit Recognition with Neural Networks


• Reinforcement Learning