Published in Science · View the paper (DOI)
Researchers developed a Bayesian Program Learning framework that captures human learning abilities, allowing computers to recognize and generate new visual concepts. The algorithm achieved impressive results in visual Turing tests, with only 25% of judges performing better than chance.
Coverage from 2 institutions
- Scientists teach machines to learn like humans New York University · Dec 10, 2015 · first to report
- When machines learn like humans American Association for the Advancement of Science (AAAS) · Dec 10, 2015