Overview

This is a hands-on class covering artificial neural networks, ranging from historic beginnings and biological inspiration, to modern deep learning.  An understanding of basic linear algebra is needed, as well as programming skills. Python will be used.

Slides

  1. Introduction
  2. Biological Inspiration
  3. Universal Approximation
  4. Perceptron Learning
  5. Historical Neural Network Architectures
  6. Gradient Descent and beyond
  7. Tensorflow
  8. Keras
  9. Machine Learning bare essentials
  10. Convolutional Neural Networks
  11. Data Augmentation & Generators
  12. Representations and Features
  13. Recurrent Neural Networks

Midterm study guide