Andrew Ng on Advances In Deep Learning
Written by Sue Gee   
Friday, 11 August 2017

A new specialization starting next week on Coursera is special because it comes from Andrew Ng. In Deep Learning, which is intended to allow participants to break into AI, he sets out to explore the current frontier of artificial intelligence.

ANgcoursebanner 

Andrew Ng is one of the co-founders of Coursera, but this course has been created under the auspices of his latest venture Deeplearning.ai, which is:

dedicated to advancing AI by sharing knowledge about the field

strives to provide comprehensive AI education beyond borders

It was in March that we reported Ng's announcement that he was leaving Baidu, where as Chief Scientist he was in charge of three AI labs, one of which Deep Learning Institute is the Industry Partner of this 5-course Deep Learning Specialization. At the time, he didn't make his future plans explicit, other than to continue working in AI and to "keep working hard to get AI to help everyone", Deeplearning.ai and this course, which has the slogan, "Build Your Career in AI" is what has emerged some five months later.

Ng's credentials as an instructor on the course are:

Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain

and of course there is the track record of his previous MOOC, Machine Learning, which still runs on Coursera where it has a popularity rating of 4.9 and has the distinction of being currently #2 in the league table of the The 50 Most Popular MOOCs of All Time in terms of numbers of students, with total enrollment now standing at 1,122,031.

Disclosure: When you make a purchase having followed a link from this article, we may earn an affiliate commission.

Deep Learning Specialization on Coursera

If you've completed that course you'll be more than ready for this new offering which promised to help you to mater deep learning. Its blurb states:

In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach.

The five courses included are:

 1   Neural Networks and Deep Learning  4 weeks at
3-6 hours per week
 2  Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization 3 weeks at
3-6 hours per week
 3 Structuring Machine Learning 2 weeks at
 3-4 hrs per week
 4  Convolutional Neural Networks 4 weeks at
4-5 hours per week
 5  Sequence Models 3 weeks at 
4-6 hrs per week

 

You can enroll on the entire Specialization with a 7-day free trial and a monthly fee of $49 which gives you unlimited access to entire Coursera catalog of over 2000 courses. If you only want to follow along for free, without doing any assignments or quizzes and without a certificate, you need to follow the links to the individual courses and scroll down to find the link in the small print to for the audit option. 

audit

The first course in the series has a great deal of appeal even if you don't want a career, but simply want to understand what has been going on in the few years since the terminology "Deep Learning " first emerged. To quote from the blurb of the first course:

Deep learning is a new "superpower" that will let you build AI systems that just weren't possible a few years ago. In this course, you will learn the foundations of deep learning. When you finish this class, you will

    • Understand the major technology trends driving Deep Learning
    • Be able to build, train and apply fully connected deep neural networks
    • Know how to implement efficient (vectorized) neural networks
    • Understand the key parameters in a neural network's architecture 

If you are already embarked on a career you might be attracted to the third course which covers how to build a successful machine learning project. Ng's course description states:

Much of this content has never been taught elsewhere, and is drawn from my experience building and shipping many deep learning products. This course also has two "flight simulators" that let you practice decision-making as a machine learning project leader. This provides "industry experience" that you might otherwise get only after years of ML work experience.

An optional component of the courses might be the most attractive element - the interview in which Andrew Ng talks individually to his AI heroes explaining:

As part of this course by deeplearning.ai I hope to not just teach you the technical ideas in deep learning, but also introduce you to some of the people, some of the heroes in deep learning. The people that invented so many of these ideas that you learn about in this course or in this specialization. In these videos, I hope to also ask these leaders of deep learning to give you career advice for how you can break into deep learning, for how you can do research or find a job in deep learning.

If you don't want to sign up for any part of the course you can still enjoy this material as the set of seven interviews can be found on Your Tube. The first and longest is with Geoffrey Hinton and it gives an interesting insight in just how far this area of research has come in the past 50 years: 

UPDATE June 2020:
All of these courses are now always available so when you enrol you can start straight away and can probably complete the entire specialiazation in less than its alloted 4 months. It also makes a great precursor  to the second specialization from deeplearning.ai, Natural Language Specialization, which was launched on June 19, 2020 - see New Natural Language Processing Specialization on Coursera. Project-based from the outset, its lead instructor is Younes Bensouda Mourri who will be familar to those who've done the Deep Learning Specialization.

More Information 

Deeplearning.ai

Deep Learning Specialization

 

deeplearningaisq

Related Articles

Machine Learning Superstar Andrew Ng Moving On

Baidu Hires Andrew Ng 

Top CS MOOCs By the Numbers

Coursera's Machine Learning Course Runs Again

 

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, Facebook or Linkedin.

Banner


Hour Of Code Adds Lessons In Unconscious Bias
20/11/2020

Microsoft has announced details a new Hour of Code lesson. In "A Minecraft Tale of Two Villages!" the task will be to bring two villages together with the power of code, learning and practicing inclus [ ... ]



PyTorch Adds New APIs
10/11/2020

PyTorch has been updated with several new APIs including support for NumPy-Compatible FFT operations, profiling tools and major updates to both distributed data parallel (DDP) and remote procedure cal [ ... ]


More News

square

 



 

Comments




or email your comment to: comments@i-programmer.info

 

 

Last Updated ( Friday, 19 June 2020 )