Class 1: Introductions

Introductions & Goals

Course Admin

  • Brightspace

  • Zoom

  • Google docs or markdown in the future?

  • Website

Learning outcomes

knowledge research

  • identify common problems and solutions in scientific application of ML

  • identify common challenges and solutions for social applications: fairness,

  • implement and extend research papers

Activities

  • reading and evaluating ML research papers

  • facilitating and participating in class discussions of the papers

  • producing a replication, demo, or illustration of one concept covered for a broader audience

  • completing a project using ML in a scientific or social domain

  • reflect on methodologies used in this type of research

  • writing a CS conference style (short & concise) final paper on their project

Model Based ML and this course

https://www.mbmlbook.com/toc.html

  • missing data

  • noisy or missing labels

  • multiple objectives

We will look at a range of strategies for identifying and mitigating these problems including:

  • robust evaluation

  • model inspection

  • explanations

  • interpretable models