5/23/2023 0 Comments True Nature by Jae![]() When he’s not teaching, Lee is pushing the boundaries of both supervised and self-supervised approaches to CV. It’s a lot to navigate, but an exciting time for students.” “There are frequent surprises, and paradigm shifts every few years. ![]() “The state of the art this month will no longer be so next month,” he says. The blistering rate of success of deep learning means the content of Lee’s graduate teaching evolves from one semester to the next. This learning has been likened to how babies learn about the world, albeit on digital timescales. ![]() In this paradigm, ML algorithms have been developed that can extract pertinent information from enormous amounts of raw, unlabelled data. This shift towards unsupervised (aka self-supervised) learning was brought about by the deep learning revolution, says Lee. “Now, I think almost the entire community believes in this direction. ![]() “Back then, unsupervised learning was not popular, but I had no doubt it was the right problem to work on,” says Lee. Why multimodal identification is a crucial step in automating item identification at Amazon scale. ![]()
0 Comments
Leave a Reply. |