Machine Learning for Big Data and Text Processing: Foundations

Machine learning is a rapidly expanding area with a diverse collection of tools and approaches. Successfully applying such methods to real tasks may seem to require expertise that many do not possess. However, all these methods share the same basic concepts, use the same building blocks.

Understanding these basics, formulations, and when they are appropriate, is key to using machine learning techniques successfully in practice. This foundational course covers the essential concepts and methods in machine learning, providing participants with an entry level expertise they need to get started and quickly move ahead.

COVID-19 Updates: MIT Professional Education fully expects to hold courses on-campus during the Summer of 2023 (only a handful will be delivered in the live virtual or hybrid modality). In the event there is a change in MIT's COVID-19 policies and a course cannot be held on-campus, we will deliver courses via live virtual format. Find the latest information here.

• Understand the basic machine learning concepts and methods including neural networks
• Learn how to formulate/set up problems as machine learning tasks
• Assess which types of methods are likely to be useful for a given class of problems
• Understand strengths and weakness of learning algorithms

Program Outline

Class runs 10:00 am - 3:45pm on Monday and 9:00am - 3:30pm on Tuesday.

Mon: (5.5h)
[10:00am] introduction to ML (1h)
[11:00am] formulation of ML problems (1h)
[12:00pm] lunch break
[ 1:00pm] linear classification/regression (1h)
[ 2:00pm] coffee break (1h)
[ 2:15pm] loss, regularization, gradient algorithms (1.5h)
[ 3:45pm] tutorial on using ML packages (1h)
 
Tue: (6h)
[ 9:00am] features, missing data (1h)
[10:00am] non-linear classification (1h)
[11:00am] coffee break
[11:15am] feed-forward neural networks: representation (1h)
[12:15pm] lunch break (1h)
[ 1:15pm] neural networks: algorithms (1h)
[ 2:15pm] coffee break
[ 2:30pm] convolutional networks (images) (1h)
[ 3:30pm] tutorial on using DNN packages (1h)

Links & Resources

• Speeding up drug discovery with diffusion generative models, MIT News, March 31, 2023
• MIT researchers develop an AI model that can detect future lung cancer risk, MIT News, January 20, 2023
• Unpacking the "black box" to build better AI models, MIT News, January 8, 2023
• Regina Barzilay wins $1M Association for the Advancement of Artificial Intelligence Squirrel AI award, MIT News, September 29, 2020
• How neural networks think: General-purpose technique sheds light on inner workings of neural nets trained to process language. MIT News, September 8, 2017
• Putting data in the hands of doctors: Computer scientist Regina Barzilay empowers cancer treatment with machine learning. MIT News, February 16, 2017

This course is appropriate to obtain a better understanding of machine learning basics. It is most suitable for those with an undergraduate degree in computer science or other related technical areas. A high-level understanding of programming (thinking in terms of programs) is helpful.

The foundational course describes key concepts, formulations, algorithms, and practical knowledge for people who are getting started or need to brush up in machine learning, and provides participants with core knowledge to succeed in the advanced level course. 

Requirements

Laptops are required for this course. Tablets will not be sufficient for the computing activities performed in this course.