Overview
This course aims to introduce machine learning — a complex and quickly evolving subject deserving of far more intensive study than a single semester allows.
The goal is a preliminary investigation of the conceptual and technical workings of a few key machine learning models: their underlying mathematics, application to real-world problems, and philosophical value in understanding the general phenomena of learning and experience.
Portions of the course materials were excerpted from Machine Learning for Designers, published with O'Reilly Media, Inc. in 2016, and are reprinted here with permission from the publisher.
Course Syllabus
Week 1
- What is Learning?
- Experience as Data Visualization
- Boolean Logic vs Fuzzy Logic
- Explicit Programming vs Experiential Training
- Procedural Precision vs Intuitive Approximation
- Inductive and Deductive Reasoning
- Mechanical Induction
- Categories of Machine Learning Algorithms
- Performing Rote Tasks
- Getting Started in Python
Week 2
Week 3
Week 4
Week 5
Week 6
- Stages of Machine Learning Workflow
- Special Tools and Workflows for Machine Learning
- Streamlining Machine Learning Workflows with Docker
- Getting Started with TensorFlow
- TensorFlow Graphs and Sessions
- TensorFlow Basic Operations
- TensorFlow Working with Data
- TensorFlow Simple Neural Network
- TensorFlow Saving and Restoring
Previous Editions
Required Text
Anderson, Britt. Computational Neuroscience and Cognitive Modelling: A Student's Introduction to Methods and Procedures. Los Angeles: SAGE, 2014.
Additional Resources
Machine Learning Tutorials
- A Dozen Times Artificial Intelligence Startled The World
- 150+ Machine Learning Tutorials
- Awesome Deep Learning Resources
- Machine Learning From Scratch
- Deep Learning Tutorials
- Effective TensorFlow Tutorials
- Aymeric Damien's TensorFlow Examples
- Deep Learning by Yoshua Bengio, Ian Goodfellow, and Aaron Courville
- Rules of Machine Learning: Best Practices for ML Engineering
- Distributed Representations of Words and Phrases and their Compositionality — Mikolov et al.
- The Unreasonable Effectiveness of Recurrent Neural Networks — Andrej Karpathy
- An Intuitive Explanation of Convolutional Neural Networks
- UFLDL Tutorial: Convolutional Neural Networks
Machine Learning Courses
- Neural Networks for Machine Learning — Geoffrey Hinton (Coursera)
- Machine Learning — Andrew Ng (Coursera)
Math for Machine Learning
- Some Basic Mathematics for Machine Learning — Iain Murray & Angela J. Yu
- Math for Machine Learning — Hal Daume
- Immersive Linear Algebra — J. Ström, K. Åström, and T. Akenine-Möller
- Linear Algebra — Khan Academy
- Probability and Statistics — Khan Academy
- Differential Calculus — Khan Academy
Python Resources
General Interest
- As We May Think — Vannevar Bush
- A Personal Computer for Children of All Ages — Alan Kay
- The Myth of AI — Jaron Lanier
- Deb Roy: The Birth of a Word
- Physiognomy's New Clothes
- Why is Machine Learning Hard?