iTunes

Opening the iTunes Store.If iTunes doesn't open, click the iTunes application icon in your Dock or on your Windows desktop.Progress Indicator
Opening the iBooks Store.If iBooks doesn't open, click the iBooks app in your Dock.Progress Indicator
iTunes

iTunes is the world's easiest way to organize and add to your digital media collection.

We are unable to find iTunes on your computer. To download from the iTunes Store, get iTunes now.

Already have iTunes? Click I Have iTunes to open it now.

I Have iTunes Free Download
iTunes for Mac + PC

Machine Learning

by Caltech

To subscribe to an iTunes U course, click View in iTunes.

Course Description

A real Caltech course, not a watered-down version

This is an introductory course on machine learning that can be taken at your own pace. It covers the basic theory, algorithms and applications. Machine learning (Scientific American introduction) is a key technology in Big Data, and in many financial, medical, commercial, and scientific applications. It enables computational systems to adaptively improve their performance with experience accumulated from the observed data. Machine learning is one of the hottest fields of study today, taken up by graduate and undergraduate students from 15 different majors at Caltech.

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; what is learning? can we learn? how to do it? how to do it well? what are the take-home lessons? The technical terms that go with that include linear models, the VC dimension, neural networks, regularization and validation, support vector machines, Occam's razor, and data snooping.

The focus of the course is understanding the fundamentals of machine learning. If you have the discipline to follow the carefully-designed lectures, do the homeworks, and discuss the material with others on the forum, you will graduate with a thorough understanding of machine learning, and will be ready to apply it correctly in any domain. Welcome aboard!

Tips on taking the course:

Prerequisites: Basic probability, matrices, and calculus. Familiarity with some programming language or platform will help with the homework.

The lectures: The 18 lectures use incremental viewgraphs to simulate the pace of blackboard teaching. Detailed explanations and insights will guide you through the difficult parts of the theory and make you understand where the techniques came from. Our focus is on real understanding, not just "knowing."

Homework: After every 2 lectures, there is a homework based on what was covered in these lectures. We recommend that you complete the homework then check your answers before you move on to the next lecture.

Forum: You can discuss the course material and ask questions on the course forum where there is a dedicated section for each homework.
 
Live lectures: This course was broadcast live from the lecture hall at Caltech, including Q&A sessions with online audience participation. Here is a sample of a live lecture as the online audience saw it in real time.

Customer Reviews

Great insights, high-quality production

Animation in slides are perfect. Instructor gives lots of great insights. The course covers some topics in machine learning in details, but skims or does not discuss some others. That would need more lectures. The q/a session is boring and I usually skip it. Great course overall for sure.

Informative and funny

Gives you strong foundations for ML

Cools

Cool

Machine Learning
View in iTunes

Customer Ratings