Machine learning has become increasingly popular in recent years. However, there has also been a trend in incorporating machine learning in everything, without asking the necessary question of whether it is reasonable to do so. All of a sudden, machine learning becomes this magical black box that can miraculously solve all the problems that one may have.
In this online course, Oxford Global and I want to teach our students that this ought not to be the case. Instead, one should see machine learning as a tool to help to solve a particular problem where the key lies in the framing of the problem, instead of the tools being used. To accentuate this idea, students were asked to develop a project to improve social well-beings, with topics ranging from COVID-19 contact tracing to renewable energy integration and optimization. These projects exposed students to the process of problem-solving and offered them the opportunity to address real-world issues using machine learning as a tool.
For this course, I presented a general overview of various topics in machine learning and held several tutorial sessions to provide students with some hands-on experiences using Python, TensorFlow, and Pytorch. I also mentored students with their final projects.
Below, you can find the slides that I made for the overview session. The overall structure of the presentation comes from Aurélien Géron's Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, a terrific book that introduces you to the world of machine learning with a lot of hands-on practices. I strongly recommend it if you are interested in learning more about machine learning.
Some demos are in a gif format and thus cannot be viewed properly in the PDF. You can go to the Course Demos page to check them out!