Teaching

Undergraduate/Graduate Teaching Assistant:

• GU STAT 4203 Probability Theory (Fall 2021, Summer 2021, Fall 2020, Fall 2018) | Updated Notes.
• GU STAT 5204 Statistical Inference (Fall 2021) | Updated (handwritten) Notes, Recitation here.

Pre-college Teaching Appointments:

• Pre-College Big Data, Machine Learning, and Real World Application (Summer 2021, Summer 2022), Course Github | Orientation | Session Survey | Previous Lectures | Student Presentation | These are the main resources I use for high school and pre-college level AI education.
• Machine Learning General | Please feel free to check out the ML General repo I have been using for undergraduate teaching.
• Lead Curriculum Design at Veritas AI | Please feel free to check out the company’s website. It’s founded by Harvard PhD students.
• LaTex Paper Template (adapted from Neurips template) | This is a base template. Update is required for different journals/conferences.

AI4ALL – General Machine Learning and Artificial Intelligence FREE Sources:

• The Fundamentals in Machine Learning | Link | This is an introduction course of machine learning: The Fundamentals of Machine Learning. The course will cover a wide range of topics to teach you step by step from handling a dataset to model delivery. The course assumes no prior knowledge of the students. However, some prior training in python programming and some basic calculus knowledge is definitely helpful for the course. The expectation is to provide you the same knowledge and training as that is provided in an intro Machine Learning or Artificial Intelligence course at a credited undergraduate university computer science program. | Lectures are made FREE on YouTube.
  Fundamentals of Neural Newtorks | This is a detailed technical and coding walkthrough of each and every building block of a variety of neural network models. | Link | Selected lectures are made FREE on YouTube.
• AI4ALL | Github: 💻
  • Basics in Artificial Neural Networks | Link | The course introduces the fundamental building blocks of an Artificial Neural Network (ANN) model. With ANN being the leading milestone, the course lays the ground work for the audience into the field of Representation Learning.
  • Basics in Convolutional Neural Networks | Link | The course expands from ANN and introduces the fundamental building blocks of a Convolutional Neural Network (CNN). Advanced CNN models are also introduced to lead audience to the field of Representation Learning.
  • Image-to-Image Network Models | Link | The course investigates a higher level of network models that learn the intrinsic representation of image data. Such models learn to produce images rather than annotations or labels, which is different from previous courses. The materials lead the audience into the field of unsupervised learning.

For more teaching materials, please refer to this page.