Deep learning with PyTorch [online, IA102]

How do ChatGPT, autonomous cars, and image recognition work? Discover the basics of deep learning, a fundamental concept of artificial intelligence. In this workshop, you'll create neural networks capable of automatically learning from raw data. You'll also learn to train your own models, using PyTorch, the library used by the largest research labs.

Prerequisites

• Good knowledge of statistics (functions and derivatives)
• Have a good knowledge of Python programming or have completed the workshops “Introduction to programming with Python (PYT101)” and “Enhancing your Python programming skills (PYT102)”
• Have good knowledge of data analysis and visualization with Python or have completed the “Data analysis with Python (DAT201)” and “Data visualization with Python (DAT203)” workshops
• Be comfortable with Python libraries like NumPy and MatplotLib
• Basic knowledge of machine learning or have completed the workshop “Machine Learning with scikit-learn (IA101)”

Agenda

• IA101 review
• Introduction to neural networks
• Training neural networks with PyTorch
• Introduction to high-performance training

Registration

• Academic: $10 (anyone who studies, teaches, or works at a university, CEGEP, CCTT, or university-affiliated research institute)
• NPO: $10 (anyone who works for a non-profit organization)
• Other: $250 (any other profile)

Instructor

Lucas Nogueira, analyst in advanced research computing at Calcul Québec.

Language

English

Technical prerequisites

We will use the Zoom platform. Because this event is a practical workshop, it is very useful having a secondary screen where you would get the instructor window on one screen and your own window on your main screen.

We will use the Jupyter Lab interface. Make sure you have a modern Web browser like Google Chrome, Firefox, Edge or Safari.

Notes

• A certificate of participation will be send to each participant who attends at least 60% of the workshop.
• The workshop is not recorded.
• The workshop could be canceled if the number of registrations is too low.

Contact

For any question, please write us to training@calculquebec.ca

To stay up to date on our upcoming events, subscribe to our Eventbrite page!