• 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, Reinforcement Learning
• Unit 13: Human-Centered AI

Unit 2: Data

Students who complete this unit will demonstrate that they can:

• Describe the structure of the data provided as input to an image classifier in terms of batches and labels
• Contrast a training set and validation set; explain appropriate uses of both
• Adapt Python code to load data to be used by an image classifier.
• Implement numerical computing operations on multidimensional arrays using PyTorch

Preparation

• Read Deep Learning for Coders chapter 2 (open in Colab)
  • note: ignore the implementation details of class DataLoaders; you only need to know that it has a .train and a .valid, each of which are DataLoaders that take filenames and give batches of (image, label) pairs.
  • If you want to replicate the code, use duckduckgo instead of trying to get a Bing API key.
• Start reading Deep Learning for Coders chapter 3 (open in Colab)
  • note: you can spread out this reading between this week and next week.
• Watch FastAI Course Lecture 2
  • note: The first hour of FastAI Course Lecture 3 finishes up this chapter’s material. The first 12 or so minutes may be particularly helpful at this point.
• Complete the preparation quiz in Moodle.

Optional Supplemental Material

Read the paper that introduced a well-known dataset: ImageNet, Microsoft COCO, MNIST, etc.

Contents

• Lab 2: Comparing classifiers, image batch structure (Mon Jan 17)
• Wednesday Class: Data (Wed Jan 19)
• Friday Class: Data 2 (Fri Jan 21)
• Homework 2: Train and evaluate a classifier on your own images (Fri Jan 21)
• Reflection 1 (Wed Jan 26)

Due this Week