Human-level concept learning through probabilistic program induction. Lake, B. M, Salakhutdinov, R., & Tenenbaum, J. B Science, 350(6266):1332–1338, 2015. Place: United States ISBN: 1095-9203
doi  abstract   bibtex   
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
@article{Lake2015,
	title = {Human-level concept learning through probabilistic program induction.},
	volume = {350},
	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},
	language = {eng},
	number = {6266},
	journal = {Science},
	author = {Lake, Brenden M and Salakhutdinov, Ruslan and Tenenbaum, Joshua B},
	year = {2015},
	pmid = {26659050},
	note = {Place: United States
ISBN: 1095-9203},
	keywords = {research support, non-u.s. gov't, research support, u.s. gov't, non-p.h.s.},
	pages = {1332--1338},
}

Downloads: 0