Related projects
Discover more projects across a range of sectors and discipline — from AI to cleantech to social innovation.
Mitacs brings innovation to more people in more places across Canada and around the world.
Learn MoreWe work closely with businesses, researchers, and governments to create new pathways to innovation.
Learn MoreNo matter the size of your budget or scope of your research, Mitacs can help you turn ideas into impact.
Learn MoreThe Mitacs Entrepreneur Awards and the Mitacs Awards celebrate inspiring entrepreneurs and innovators who are galvanizing cutting-edge research across Canada.
Learn MoreDiscover the people, the ideas, the projects, and the partnerships that are making news, and creating meaningful impact across the Canadian innovation ecosystem.
Learn MoreIn recent years, deep learning has led to unprecedented advances in a wide range of applications including natural language processing, reinforcement learning, and speech recognition. Despite the abundance of empirical evidence highlighting the success of neural networks, the theoretical properties of deep learning remain poorly understood and have been a subject of active investigation. One foundational aspect of deep learning that has garnered great intrigue in recent years is the generalization behavior of neural networks, that is, the ability of a neural network to perform on unseen data. Furthermore, understanding better this generalization behavior has significant practical importance as it can provide guidance and intuition on how to design more effective and powerful deep learning algorithms in the future. Our proposal has two primary objectives: (1) develop an algorithm to address the âgeneralization gapâ problem in deep learning: how to decrease the decay in generalization performance when using large-batches in training. (2) Investigate non-vacuous generalization bounds in deep learning through the PAC-Bayes and uniform stability frameworks
Daniel Roy;Murat Erdogdu
Mufan Bill Li
Borealis AI
Statistics / Actuarial sciences
Accelerate
Discover more projects across a range of sectors and discipline — from AI to cleantech to social innovation.
Find the perfect opportunity to put your academic skills and knowledge into practice!
Find ProjectsThe strong support from governments across Canada, international partners, universities, colleges, companies, and community organizations has enabled Mitacs to focus on the core idea that talent and partnerships power innovation — and innovation creates a better future.