nips nips2008 nips2008-101 nips2008-101-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Rui M. Castro, Charles Kalish, Robert Nowak, Ruichen Qian, Tim Rogers, Xiaojin Zhu
Abstract: We investigate a topic at the interface of machine learning and cognitive science. Human active learning, where learners can actively query the world for information, is contrasted with passive learning from random examples. Furthermore, we compare human active learning performance with predictions from statistical learning theory. We conduct a series of human category learning experiments inspired by a machine learning task for which active and passive learning error bounds are well understood, and dramatically distinct. Our results indicate that humans are capable of actively selecting informative queries, and in doing so learn better and faster than if they are given random training data, as predicted by learning theory. However, the improvement over passive learning is not as dramatic as that achieved by machine active learning algorithms. To the best of our knowledge, this is the first quantitative study comparing human category learning in active versus passive settings. 1
[1] N. Balcan, S. Hanneke, and J. Wortman. The true sample complexity of active learning. to appear in COLT 2008, Helsinki, Finland, 2008.
[2] M. V. Burnashev and K. Sh. Zigangirov. An interval estimation problem for controlled observations. Problems in Information Transmission, 10:223–231, 1974.
[3] S. Carey. Conceptual change in childhood. MIT Press, 1985.
[4] R. Castro and R. Nowak. Minimax bounds for active learning. IEEE Transactions on Information Theory, 54(5):2339–2353, 2008.
[5] D. Cohn, L. Atlas, and R. Ladner. Improving generalization with active learning. Machine Learning, 15(2):201–221, 1994.
[6] R. Gelman and E. M. Williams. Handbook of child psychology, chapter Enabling constraints for cognitive development and learning: A domain-specific epigenetic theory. John Wiley and Sons, 1998.
[7] G. Gigerenzer and R. Selten. Bounded rationality: The adaptive toolbox. The MIT Press, 2001.
[8] M. Horstein. Sequential decoding using noiseless feedback. IEEE Trans. Info. Theory, 9(3):136–143, 1963.
[9] F. Keil. Concepts, kinds, and cognitive development. MIT Press, 1989.
[10] J. K. Kruschke. Bayesian approaches to associative learning: From passive to active learning. Learning & Behavior, 36(3):210–226, 2008.
[11] P. A. Laughlin. Focusing strategy in concept attainment as a function of instructions and task complexity. Journal of Experimental Psychology, 98(2):320–327, May 1973.
[12] C. R. Mynatt, M. E. Doherty, and R. D. Tweney. Confirmation bias in a simulated research environment: An experimental study of scientific inference. The Quarterly Journal of Experimental Psychology, 29(1):85–95, Feb 1977.
[13] J. Nelson. Finding useful questions: On Bayesian diagnosticity, probability, impact, and information gain. Psychological Review, 112(4):979–999, 2005.
[14] M. Oaksford and N. Chater. Bayesian rationality the probabilistic approach to human reasoning. Oxford University Press, 2007.
[15] L. E. Schulz, T. Kushnir, and A. Gopnik. Causal Learning; Psychology, Philosophy and Computation, chapter Learning from doing: Interventions and causal inference. Oxford University Press, 2007.
[16] D. Sobel and T. Kushnir. Interventions do not solely benefit causal learning: Being told what to do results in worse learning than doing it yourself. In Proceedings of the 25th Annual Meeting of the Cognitive Science Society, 2003.
[17] M. Steyvers, J. Tenenbaumb, E. Wagenmakers, and B. Blum. Inferring causal networks from observations and interventions. Cognitive Science, 27:453–489, 2003.
[18] Alexandre B. Tsybakov. Introduction a l’estimation non-param´ trique. Math´ matiques et Applications, e e ` 41. Springer, 2004.
[19] G. Tur, D. Hakkani-T¨ r, and R. E. Schapire. Combining active and semi-supervised learning for spoken u language understanding. Speech Communication, 45:171–186, 2005.
[20] P. C. Wason and P. N. Johnson-Laird. Psychology of reasoning: Structure and content. Harvard U. Press, 1972.
[21] X. Zhu, T. Rogers, R. Qian, and C. Kalish. Humans perform semi-supervised classification too. In Twenty-Second AAAI Conference on Artificial Intelligence, 2007. 8