[repost ]Learning From Data – Online Course:Caltech Parallel Session: January-March 2013 (details soon)



A real Caltech course, not a watered-down version


  • Free, introductory Machine Learning course
  • Taught by Caltech Professor Yaser Abu-Mostafa [article]
  • Lectures recorded from a live broadcast, including Q&A
  • Prerequisites: Basic probability, matrices, and calculus
  • Homeworks with online grading and ranking
  • Discussion forum for participants

Caltech Parallel Session: January-March 2013 (details soon)

Fall session: October 2 to December 11, 2012


Offer the course at your university


This is an introductory course on machine learning that covers the basictheory, algorithms, and applications. Machine learning enables computational systems to adaptively improve their performance with experience accumulated from the observed data. It has become one of the hottest fields of study today, with applications in engineering, science, finance, and commerce. The course balances theory and practice, and covers the mathematical as well as the heuristic aspects. The lectures follow each other in a story-like fashion, with the main topics listed below.


The lectures are about 60 minutes each plus Q&A. You can also look for a particular topic in the Machine Learning Video Library.


theory; mathematical
technique; practical
analysis; conceptual

The story line from Lecture 1 to Lecture 18 is: 

  • What is learning?
  • Can we learn?
  • How to do it?
  • How to do it well?
  • Take-home lessons.

Live Lectures


This course was broadcast live from the lecture hall at Caltech in April and May 2012. The lectures included live Q&A sessions with online audience participation. Here is a sample of a live lecture as the online audience saw it in real time.