• Unit 1: Introduction
• Unit 2: Data
• Unit 3: Data and Ethics
• Unit 4: Models
• Unit 5: Learning and Classification
• Unit 6: Recap and Regularization
• Unit 7: Learned Representations (Embeddings)
• Unit 8: NLP Intro
• Unit 9: NLP Modeling
• Unit 10: Transformers
• Unit 11: Generation
• Unit 12: Review, Neural Architectures
• Unit 13: Generation and Miscellaneous Topics

Unit 1: Introduction

Students who complete this unit will demonstrate that they can:

• Contrast contemporary ML-based numerical AI with classical rule-based symbolic AI
• Describe the overall approach of how modern AI learns from data
• Identify some of the major milestones in the history of AI.
• Implement a simple image classifier on a pre-wrangled dataset using the fastai library.

Preparation

• Read Deep Learning for Coders chapter 1 (open in Colab)
• Watch FastAI Course Lecture 1 - includes extra material so don’t expect mastery.
• optional: Watch Lecture 1 of MIT 6.S191 Deep Learning

Contents

• Discussion 1: What’s AI useful for?
• Lab 1: Warmup