MLClass
Introduction to Machine Learning class taught at ISU, Fall 2020 to Spring 2021 Syllabus
All materials, except recorded videos uploaded to Canvas due to privacy concerns, are posted in this repository.
Slides
Slides are made in Markdown source code and compiled into PDFs, webpages, etc., using Pandoc An example script to convert from Markdown to PDF is make.sh.
The source files in Markdown are always the latest. There maybe delays in PDF syncing.
Precompiled PDFs are given below:
- Introduction
- Linear classifiers
- Decision trees
- SVMs
- Regression
- Neural networks
- Clustering
- Deep Learning
- Reinforcement Learning
- Ensemble Learning
- CV, NLP, tiny ML
Reading list
Image style generation and transfer in generative networks and generative adversarial networks (GANs)
- Texture Synthesis Using Convolutional Neural Networks, NIPS 2015
- A Learned Representation For Artistic Style, ICLR 2017
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images, ICML 2016
- A Learned Representation For Artistic Style, ICLR 2017
- A Style-Based Generator Architecture for Generative Adversarial Networks, StyleGAN, CVPR 2019
How to audit (for ISU students only)
Now students can request to audit a course electronically by going to AccessPlus, clicking on the Student tab, clicking on Registrar Forms, and clicking "Schedule Change Form". They will need to attach an e-mail from their instructor saying they have permission to audit the course. After attaching documentation, the form can then be routed for approval.
Software needed for this class
Feel free to use your personal computer. Be sure to have Python3.6 or later set up, as well as numpy, scipy, matplotlib and tensorflow 2.x installed.
Alternatively, you can use the university's infra. See here.