This is a two-day course on Machine Learning. It consists of two major subjects: Machine Learning in Data Science and Deep Learning towards Artificial Intelligence.
Day 1 will provide an introduction to Machine Learning in Data Analytics. Following an overview of Machine Learning in Data Science, we will learn from examples for a full cycle of Machine Learning with real data, including data cleansing, data exploration, and a typical Machine Learning workflow. We will use Pandas and Scikit-Learn APIs in Python with hands-on practices through Jupyter Notebook.
Day 2 will provide an overview of Artificial Intelligence with a focus on Deep Learning (DL) and Deep Neural Networks (DNN). We will have hands-on tutorials on two major different DL frameworks - Tensorflow and PyTorch by running CIFAR-10 image classification example on Compute Canada system. The hands-on labs will focus on how to run a sample case with different hardware resources such as a single-GPU, multi-GPU and multi-GPU nodes while the basic Tensorflow/PyTorch programming is briefly introduced.
Instructors: Jinhui Qin, SHARCNET / Western University (day 1) and Isaac Ye, SHARCNET / York University (day 2)
Prerequisites: Some programming experience in Python and background in statistics would be helpful but not mandatory.
- Teacher: Jinhui Qin
- Teacher: Isaac Ye