Introduction to Deep Learning (6.S191)

The TensorFlow version

This is an introductory course on deep learning methods, with applications in computer vision, language and biology. Its practical side has you building neural networks in TensorFlow, and the course closes with a project proposal competition.

What you take away

• Foundational knowledge of deep learning algorithms
• Hands-on practice building neural networks
• Feedback from teaching staff and industry sponsors on a project proposal

Entry requirements

Calculus at the level of taking derivatives and linear algebra at the level of matrix multiplication are assumed. Python is helpful but not necessary, and the remaining ideas are explained along the way. The course is a good companion to the more applied introductions, since it focuses on how networks are built and why they work.