This is an introductory course to Artificial Intelligence (AI). There is no specific pre-requisite for this course. Students are, however, expected to have basic foundation in
mathematics, statistics, linear algebra, calculus and vector calculus.
In this course, students will be introduced to an overall view of AI and why AI is
relevant for everyone across multiple fields. Since this is a data science-oriented AI course,
students will learn about data science ecosystems – Python programming, Numpy (vector
representation), Pandas (data wrangling), Matplotlib (data visualization) and Pytorch (deep
learning library).
At the end of the course, students will be familiar with AI concepts and data science-related tools. Such understanding is a key pre-requisite for more advanced and specialized
courses.
This course is divided into three parts:
– Team Project:
▪ Students will be split into teams consisting of 3-4 students. Each team will have
a unique project assignment. Each team will take the sessions to work as a group
with the supports and mentoring providing by the teacher to guide and give
suggestions when necessary.
▪ The projects will allow students to practice data wrangling and visualization in
Jupyter notebook.
– Finally, there is a presentation and/or demonstration from each group to the class with
the discussion on the results.
LO1: Understand the concepts, definitions and application of Artificial Intelligence
LO2: Understand AI subsets like supervised, unsupervised and reinforcement
learning.
LO3: Understand Python programming fundamentals.
LO4: Use numerical arrays/vectors and Numpy library
LO5: Implement a linear regression with Numpy
LO6: Use Pandas to do data manipulation
LO7: Practice Pandas on a demo dataset
LO8: Visualize data using Matplotlib and Seaborn
LO9: Practice Matplotlib/ Seaborn on a demo dataset
LO10: Understand deep libraries like TensorFlow or Pytorch
LO11: Implement a linear regression with Pytorch
LO12: Build an AI project
LO13: Wrap-up and way forward