Read Andrew Ng's New AI Book As He Writes It!
Written by Mike James   
Tuesday, 21 June 2016

Andrew Ng is well known to AI enthusiasts and reading what he has to say about AI project organization as he writes it is an opportunity not to be missed. To receive a draft of each chapter as it is produced sign up to the mailing list by Friday, June 24. 

machinlearningng

Andrew Ng is perhaps best known for his pioneering machine learning course, which he created at Stanford and then turned into one of the most popular ever MOOCs. It continues to be available on Coursera, the MOOC provider he co-founded in 2012.

Since 2014 Ng is also Baidu's chief scientist and responsible for a lot of AI work. His new book isn't a basic introduction to neural networks or machine learning; instead it focuses on organizing an AI project. Not so much project management, more the specific issues that arise in AI: 

  • Should you collect more training data?

  • Should you use end-to-end deep learning?

  • How do you deal with your training set not matching your test set?

  • and many more.

If you think a that this list is a little on the "thin" side, the book is only planned to be 100 pages. The I Programmer team are all agreed that 100 pages represents a lower bound and look with similar scepticism on the target of "many 1 to 2 page chapters"! We could be wrong, but authors generally underestimate the amount they have to write. 

There is some more information about what the book will attempt to teach you: 

  • How to establish your dev and test sets

  • Basic error analysis

  • How you can use Bias and Variance to decide what to do

  • Learning curves

  • Comparing learning algorithms to human-level performance 

  • Debugging inference algorithms

  • When you should and should not use end-to-end deep learning 

  • Error analysis by parts 

It sounds good and the only problem is the short time you have to sign up - the deadline is Friday, June 24.  Another small problem is that the sign-up page doesn't accept email addresses with a dot in the name part, which is a commonly used format.

What are you waiting for? 

machinlearningng

More Information

http://www.mlyearning.org/

Related Articles

Stanford's Free Computer Science Courses 

Top CS MOOCs By the Numbers 

 Coursera's Machine Learning Specialization 

Coursera Commits Cultural Vandalism As Old Platform Shuts - UPDATE

Baidu Hires Andrew Ng 

 

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on, Twitter, FacebookGoogle+ or Linkedin

 

Banner


Gender Differences In Coding Style
13/11/2024

A novel investigation into the gender gap between men and women regarding coding ability was undertaken by Dr Siân Brooke. Her conclusion? There is a difference in the Python code [ ... ]



It Matters What Language AI Thinks In
23/10/2024

We are currently polarized in how we think about Large Language Models. Some say that they are just overgrown autocompletes and some say that they have captured some aspects of intelligence. How well  [ ... ]


More News

 

 

 

 

 

 

 

 

Last Updated ( Tuesday, 21 June 2016 )