#unsupervisedlearning; #nextAIrevolution; #MITTechnologyReview
Massachusetts (U.S.), July 28 (Canadian-Media): Yann LeCun, Facebook’s chief AI scientist, believes unsupervised learning will bring about the next AI revolution, MIT Technology Review reports said.
“Nobody tells the baby that objects are supposed to fall,” said Yann LeCun, the chief AI scientist at Facebook and a professor at NYU, during a webinar on Thursday organized by the Association for Computing Machinery, an industry body. And because babies don’t have very sophisticated motor control, he hypothesizes, “a lot of what they learn about the world is through observation.”
That theory could could ;ead researchers to advance the boundaries of artificial intelligence.
Deep learning, the category of AI algorithm, has increased the possibility of giving machines perceptual abilities like vision. The next step is to instill them with sophisticated reasoning.
New techniques of giving machines a kind of working memory are helping to overcome this limitation.
“Obviously we’re missing something,” LeCun said.
The answer, he thinks, is in deep-learning subcategory known as unsupervised learning. LeCun prefers the term “self-supervised learning” because it essentially uses part of the training data to predict the rest of the training data.
In recent years, such algorithms have facilitated in natural-language processing because of their ability to find the relationships between billions of words.
“Everything we learn as humans—almost everything—is learned through self-supervised learning. There’s a thin layer we learn through supervised learning, and a tiny amount we learn through reinforcement learning,” he said. “If machine learning, or AI, is a cake, the vast majority of the cake is self-supervised learning.”
What does this look like in practice? Researchers should begin by focusing on temporal prediction.
“This is kind of a simulation of what’s going on in your head, if you want,” LeCun said.
“It's a good idea to do video prediction in the context of self-driving cars because you might want to know in advance what other cars on the streets are gonna do,” he said.
Ultimately, unsupervised learning will help machines develop a model of the world that can then predict future states of the world, he said. LeCun is confident: “The next revolution of AI will not be supervised.”