University of Toronto

8 Posts

A new framework that helps models “unlearn” information selectively and incrementally
University of Toronto

Deep Unlearning: AI Researchers Teach Models to Unlearn Data

Privacy advocates want deep learning systems to forget what they’ve learned. What’s new: Researchers are seeking ways to remove the influence of particular training examples, such as an individual’s personal information, from a trained model without affecting its performance, Wired reported.
Face detection being used on a person during assault on the U.S. Capitol
University of Toronto

AI Truths, AI Falsehoods

Face recognition is being used to identify people involved in last week’s assault on the U.S. Capitol. It’s also being misused to support their cause.
Data related to a system that purportedly identified breast cancer
University of Toronto

Pushing for Reproducible Research

Controversy erupted over the need for transparency in research into AI for medicine. Google Health introduced a system that purportedly identified breast cancer more accurately than human radiologists.
Data and information related to shortcut learning
University of Toronto

When Models Take Shortcuts

Neuroscientists once thought they could train rats to navigate mazes by color. Rats don’t perceive colors at all. Instead, they rely on the distinct odors of different colors of paint. New work finds that neural networks are prone to this sort of misalignment between training goals and learning.
Replica of the video game Pac-Man generated by a GAN
University of Toronto

Playing With GANs

Generative adversarial networks don’t just produce pretty pictures. They can build world models, too. A GAN generated a fully functional replica of the classic video game Pac-Man.
Association for the Advancement of Artificial Intelligence conference in New York
University of Toronto

Meeting of the Minds

Geoffrey Hinton, Yoshua Bengio, and Yann LeCun presented their latest thinking about deep learning’s limitations and how to overcome them.
Information related to Implicit Reinforcement without Interaction at Scale (IRIS)
University of Toronto

Different Skills From Different Demos

Reinforcement learning trains models by trial and error. In batch reinforcement learning (BRL), models learn by observing many demonstrations by a variety of actors. But what if one doctor is handier with a scalpel while another excels at suturing?
Information related to a model that predicts a chemical's smell
University of Toronto

Nose Job

Predicting a molecule’s aroma is hard because slight changes in structure lead to huge shifts in perception. Good thing deep learning is developing a sense of smell.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox