Overview

This 5-day workshop is an introductory, short course on deep learning. It is designed for anyone who wishes to obtain basic knowledge of machine learning and explore deep learning from scratch. The workshop provides you with a practical introduction to basic and selected topics on deep learning through the Keras framework in Python.

The outcomes of this workshop include knowledge of:
     - The building blocks of neural networks
     - Introduction to Keras and TensorFlow
     - Classification and regression with neural networks
     - Fundamentals and workflows of machine learning
     - Deep learning for time series (and text)

Prerequisites:
     - Basic Python programming experience. Familiarity with NumPy library would be helpful, however it is not required.
     - High school-level mathematics.

Date: Monday to Friday, 22 to 26 August, 2022.
Time: 10 a.m. to 3:30 p.m. (with a lunch break from 12 to 1:30).
Location: Burnside Hall room 511 (5th floor), inside the Geographic Information Center.
Instructor: Yi Archer Yang, Associate Professor of Statistics, Department of Mathematics and Statistics.

Lesson plan

Day 1
     - Data representations for neural networks: vector, matrix, tensor
     - Tensor operations
     - Gradient-based optimization

Day 2
     - Jupyter notebooks and Colaboratory
     - First steps with Keras and Tensor flow
     - Understanding core Keras APIs

Day 3
     - Getting started with a binary classification example: movie reviews
     - A multiclass classification example: newswires
     - A regression example: predicting house prices

Day 4
     - Evaluating machine learning models
     - Improving model fit and generalization
     - Model development and deployment

Day 5
     - Different kinds of time series tasks
     - A temperature-forecasting example
     - Getting started with recurrent neural networks

Registration

This workshop is offered for free by the Faculty of Science to the McGill community. If demand exceeds capacity, we will give preference to graduate students. Registration closes on July 27. We will be in touch by August 1st to let you know if your registration was accepted. REGISTER HERE.

By registering, you commit to attend and participate actively. In the event that you need to cancel your registration, please notify us as soon as possible so that we can offer your space to another participant. To cancel registration, fill in this form.