Algorithm Lets Computer Learn Like a Person
James Devitt | December 11, 2015
The work, which appears in the journal Science, dramatically shortens the time it takes computers to “learn” new concepts and broadens their application to more creative tasks.
 |
| Source: http://www.laboratoryequipment.com/news/2015/12/teaching-machines-learn-humans |
<more at http://www.futurity.org/machine-learning-algorithm-1068302-2/; related links: http://www.csmonitor.com/Science/2015/1212/AI-breakthrough-How-computers-are-starting-to-learn-like-humans (AI breakthrough: How computers are starting to learn like humans. Artificial intelligence researchers have studied how humans learn and applied it to computers with the goal of helping both. December 12, 2015) and http://www.sciencemag.org/content/350/6266/1332.abstract (Human-level concept learning through probabilistic program induction. Brenden M. Lake, Ruslan Salakhutdinov, and Joshua B. Tenenbaum. Science 11 December 2015: Vol. 350 no. 6266 pp. 1332-1338. DOI: 10.1126/science.aab3050. [Abstract: People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways than conventional algorithms—for action, imagination, and explanation. We present a computational model that captures these human learning abilities for a large class of simple visual concepts: handwritten characters from the world’s alphabets. The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches. We also present several “visual Turing tests” probing the model’s creative generalization abilities, which in many cases are indistinguishable from human behavior.])>
No comments:
Post a Comment