Coursera launches new Deep Learning Specialization, taught by its founder, Andrew Ng

The online education platform Coursera is launching a new Deep Learning Specialization that will be taught by its cofounder, Andrew Ng. The aim of the program is to build an AI-powered society.

Image: Wikimedia

The online education platform Coursera is launching a new Deep Learning Specialization that will be taught by its cofounder, Andrew Ng. The aim of the program is to build an AI-powered society.

Andrew Ng, who is now an Adjunct Professor at Stanford, had previously taught a machine learning class in Coursera; since the course was launched, in 2011, more than 1.8 million people have enrolled.

The goal of the new specialization is to disseminate machine learning knowledge, believing that Artificial Intelligence improves every person’s life.

“These courses will help you master Deep Learning, learn how to apply it, and perhaps even find a job in AI. I hope we can build an AI-powered society that gives everyone affordable healthcare, provides every child a personalized education, makes inexpensive self-driving cars available to all, and provides meaningful work for every man and woman,” states Ng on a blog post.

The program is for beginners in the subject and only requires students to have basic programming experience and foundations of the Python language. The specialization consists of five courses:

Neural Networks and Deep Learning. Understand the major technology trends driving Deep Learning and be able to build, train and apply fully connected deep neural networks.

Improving Deep Neural Networks. Hyperparameter tuning, Regularization and Optimization. Understand industry best-practices for building deep learning applications and effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking.

Structuring Machine Learning Projects. Understand how to diagnose errors in a machine learning system and prioritize the most promising directions for reducing errors.

Convolutional Neural Networks. Understand how to build a convolutional neural network and know how to apply convolutional networks to visual detection and recognition tasks.

Sequence Models. Understand how to build and train Recurrent Neural Networks (RNNs) and apply sequence models to natural language problems, including text synthesis.