Google
Representative image.Reuters

Search giant Google has developed a new Deep Learning course that will help engineers solve the "thorniest problems in computing" with tools and best practices.

The new free course will see Google engineers sharing their knowledge via a free online course for a period of three months with six hours of work every week. Google promises this course will "show you how to train and optimise basic neural networks, convolutional neural networks, and long and short-term memory networks. Complete learning systems in TensorFlow will be introduced via projects and assignments."

Time reported that Google used deep learning in its Photos app product, which lets the picture of the user automatically categorise objects in them.

Vincent Vanhoucke, Principal Scientist at Google, and technical lead in the Google Brain team, helped develop this course.

"This new course is geared toward those of you who are eager to try deep learning in the real world, but have not made the jump yet. Perhaps because you need concrete solutions to concrete problems, and want just enough theory to feel confident exploring what this approach to machine learning can do for you," he wrote in a blog.

Deep learning is helpful in areas like drug discovery, natural language processing and web analytics.

The course offers following lessons as its syllabus:

  • Lesson 1: From Machine Learning to Deep Learning
  • Lesson 2: Deep Neural Networks
  • Lesson 3: Convolutional Neural Networks
  • Lesson 4: Deep Models for Text and Sequences

Among its set of prerequisites and requirements, Google noted that applicants must have a minimum of two years of programming experience, with Python as the preferred language. It also recommended applicants to have some knowledge of basic machine learning, basic statistics, linear algebra, calculus, and Git and GitHub experience.

It said this is an intermediate-to-advanced-level course. Students can choose to complete it at their own pace.