Deep Learning from the Foundations | fast.ai Part 2

Gain a deep understanding of deep learning foundations and learn how to implement state-of-the-art models from scratch with fast.ai Part 2.

Introduction

Welcome to Part 2: Deep Learning from the Foundations, which shows how to build a state of the art deep learning model from scratch. It takes you all the way from the foundations of implementing matrix multiplication and back-propagation, through to high performance mixed-precision training, to the latest neural network architectures and learning techniques, and everything in between.

Highlights

• Covers the foundations of implementing matrix multiplication and back-propagation from scratch
• Discusses important software engineering techniques
• Covers many of the most important academic papers that form the foundations of modern deep learning
• Uses a "code-first" teaching approach where each method is implemented from scratch in Python
• Includes lessons using Swift for TensorFlow, co-taught with the original creator of Swift, Chris Lattner

Recommendation

This course is particularly recommended for those who want to gain a deep understanding of the foundations of deep learning and learn how to implement state-of-the-art models from scratch. It is suitable for experienced coders who have completed the prerequisite Part 1 course.