README.md

Why this course?

• Background on "The Nature of Code"

Structure / Overview

• "Research" presentations
• 3 exercises
• 1 project

What is Artificial Intelligence?

• "Models for Thinking, Perception, Action" -- Patrick Winston, MIT, Artificial Intelligence, MIT Open CourseWare
• "many things can be AI, including simple programming. AI is the automation of thought" @fchollet
• Artificial Intelligence: A Modern Approach

What is Machine Learning?

• "A field of study that gives computers the ability to learn without being explicitly programmed." Arthur Samuel, 1957 "Samuel Checkers": the world's first self-learning program.
• Data --> Meaning
• Types of Machine Learning
  • Rule-based Systems
  • Supervised Learning
    • Classification, Regression
  • Unsupervised Learning
    • Clustering
  • Reinforcement Learning
  • Generative output

What is Deep Learning?

• Machine learning with "deep" neural networks.
• Deep meaning "many layers" deep.

Ok, what about Artificial General Intelligence?

• DeepMind and Q-Learning

Being Critical

• AINOW led by Kate Crawford and Meredith Whittaker
• "What happened to "making the world a better place"?" @hardmaru
• Automated Inference on Criminality using Face Images
• Facebook Restores Iconic Vietnam War Photo It Censored for Nudity

Main references I'm using for today (and beyond)

• Machine Learning for Artists by Gene Kogan and collaborators
• Machine Learning for Musicians and Artists by Rebecca Fiebrink
• Not yet released book by @AndrewGlassner
• Grokking Algorithms
• More and more and more references

Overview of Syllabus and Topics

What languages / tools?

• I will mostly be using Processing and p5.js.
• You can use anything and everything you like for this course.
• We will likely branch out into python when using some machine learning frameworks (like tensorflow).

Glossary of terms

Statistics and machine learning glossary from the repo wiki.

Wikipedia links:

• Sample
• Feature
• Label
• Prediction
• Cost / loss
• Training
• Training set, test set, validation set
• Model
• Learning rate (step size) aka Gradient Descent

Project References

• Moved to this wiki

Algorithms

• Big-O notation
  • CS50 video
  • Wikipedia article
• Binary Search Tree
  • Coding Train video on binary trees
  • FreeCodeCamp video
  • CS50 video
  • Wikipedia article
• Breadth-First Search
  • Wikipedia article
  • Coding Train BFS tutorial: Part 1, Part 2
• Depth-First Search
  • Wikipedia article
  • Coding Train DFS Maze Generation: Part1, Part2, Part3, Part4
• Dijkstra's Algorithm
  • Computerphile video
  • Wikipedia article
• A star
  • Coding Train videos: Part1 Part2 Part3
  • Computerphile video
• Traveling Salesperson Problem
  • Coding Train videos: Part1 Part2 Part3

Misc Technical Discussion

• What is "Prototype"? Coding Train tutorial
• What is an "associative array"? Coding Train tutorial
• Animating algorithm progress vs. "all at once"

Examples and Homework

• All code examples
• Week 1 Homework