University of Toronto

When you’re looking for answers from a large language model, some prompts are better than others. So how can you come up with the best one? A new model automates the process.

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 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.

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.

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.

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.

Geoffrey Hinton, Yoshua Bengio, and Yann LeCun presented their latest thinking about deep learning’s limitations and how to overcome them.

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?

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.