Reload - Selective Data Forgetting and Replacement - Vector Intern Talks
Machine Unlearning is an important task in machine learning surrounding making a model selectively ‘forget’ part of its training data. In some cases, the data may be unavailable, and conventional methods require access to unlearn. Those that do not, do not perform well. In this talk I introduce Reload, a new method I developed with Dr. Rahul Krishnan which is inspired by memorization in neural networks and gradient-based input saliency maps to retrain part of the network. I justify the need for Reload, and the theoretical motivations and justifications for its design, as well as demonstrate its state-of-the-art performance on unlearning tasks. I also introduce an extension of the unlearning problem to selective data replacement, to correct or update part of the training data. I define the problem, empirical evaluation tasks, justify the use of Reload for this task, and demonstrate its performance on replacing part of the training set. My presentation wraps up with a discussion of my next steps to complete this project.
Advance your career in AI with Vector's internship program. Collaborate with leading AI developers on cutting-edge projects, gain invaluable insights through daily research talks, and benefit from professional development opportunities. Vector offers diverse internship tracks including Applied AI, Research, and specialized programs for Black and Indigenous students.
Enhance your professional growth through Vector's Mentorship Program, pairing you with an AI expert from a sponsor organization to strengthen your technical and interpersonal skills.
Take the next step in your AI journey. Learn more at: https://vectorinstitute.ai/programs/i...
Watch video Reload - Selective Data Forgetting and Replacement - Vector Intern Talks online without registration, duration hours minute second in high quality. This video was added by user Vector Institute 10 September 2024, don't forget to share it with your friends and acquaintances, it has been viewed on our site 34 once and liked it 0 people.