Build machines the intellectual capabilities of a human being is still under way, but a team of scientists from the University of Tortonto (Canada), the Moore-Sloan Data Science at the University of New York (USA) and MIT have managed to emulate the ability of people to acquire new concepts from a single instance through a very particular algorithm. The study was published in the journal Science.
The algorithm allows the system to self-program and use previously acquired knowledge to recognize and draw simple visual concepts like humans do. And for a computer, this option requires hundreds or perhaps thousands of continuous directions to precision so simply acquire humans. The study “computational process shortens the learning of new concepts and extends the application of machines to more creative tasks,” says Brenden Lake, leader of the work.
To achieve this technological milestone for the first time in history, the researchers created a Bayesian learning software (BLP, Bayesian Learning Program), in which the concepts are represented as basic software. Unlike standard recognition software patterns, this algorithm learns “generative model” of real processes, increasing their efficiency through better use of data.
In the same way, this algorithm learns to learn, for example, using knowledge of the Latin alphabet to learn the letters of the Greek alphabet. To prove it, the software was applied to more than 1,600 types of handwritten characters with multiple writing systems, including non-existent or invented alphabets, as well as human trials using similar tests to participants known Turing Test.
The results of visual Turing tests revealed that the BPL type model achieved the same performance level as humans and far exceeded any results obtained deep machine learning so far.
“Before entering kindergarten, children know and recognize new concepts from a single example, and can imagine new examples have ever seen. We are still far from building machines as smart as a child, but this is the first time we have achieved a computer to be able to learn and use a large number of real-world concepts, including simple visual concepts such as handwritten characters ” Joshua Tenenbaum explains study co-author.
‘re just scratching the surface, but there will come a day when the machines will be able to learn from their environment as do people.
Source: Very Intersante
YR
No comments:
Post a Comment