“The first we called compositionality, which is the idea that representations are built up from simpler primitives. “We analyzed these three core principles throughout the paper,” Lake says. He’s joined by Tenenbaum and Ruslan Salakhutdinov, an assistant professor of computer science at the University of Toronto who was a postdoc in Tenenbaum’s group from 2009 to 2011. Lake, who is now a postdoc at New York University, is first author on a paper describing the work in the latest issue of the journal Science. The new system was the thesis work of Brenden Lake, who earned his PhD in cognitive science from MIT last year as a member of Tenenbaum’s group, and who won the Glushko Prize for outstanding dissertations from the Cognitive Science Society. We can understand how to use them in different ways, how to make new ones.”
We can understand what they’re built out of. “Because there are a bunch of things that we do with even much richer, more complex concepts that we can do with these characters. “This is partly why, even though we’re studying hand-written characters, we’re not shy about using a word like ‘concept,’” he adds.
“But what’s been lost is that intelligence isn’t just about classifying or recognizing it’s about thinking.” “In the current AI landscape, there’s been a lot of focus on classifying patterns,” says Josh Tenenbaum, a professor in the Department of Brain and Cognitive sciences at MIT, a principal investigator in the MIT Center for Brains, Minds and Machines, and one of the new system’s co-developers. It thus offers hope, they say, that the type of computational structure it’s built on, called a probabilistic program, could help model human acquisition of more sophisticated concepts as well.
It also mimics the human ability to learn new concepts from few examples. That means that the system in some sense discerns what’s essential to the character - its general structure - but also what’s inessential - the minor variations characteristic of any one instance of it.Īs such, the researchers argue, their system captures something of the elasticity of human concepts, which often have fuzzy boundaries but still seem to delimit coherent categories. Researchers at MIT, New York University, and the University of Toronto have developed a computer system whose ability to produce a variation of a character in an unfamiliar writing system, on the first try, is indistinguishable from that of humans.
0 kommentar(er)
