Enhanced Neural Network Design and Optimization

Deep learning and artificial intelligence (AI) technologies are transforming industry by way of automation, connectivity and availability of information technologies. However, AI remains incredibly challenging and costly to implement, often requiring massive data centers and cloud computing to operate. This research seeks to develop optimization methods to create faster, smaller and more energy-efficient AI algorithms that can operate on edge devices, such as battery-powered cars, sensors and phones. The work will have a major impact on the accessibility and environmental footprint of AI as a new and fast-growing technology.

Faculty Supervisor:

Quentin Cappart

Student:

Partner:

Deeplite Inc.

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Polytechnique Montréal

Program: