{"type":"ScholarlyArticle","title":"Local Learning in Probabilistic Networks with Hidden Variables","authors":[{"name":"Stuart J. Russell","slug":"stuart-j-russell","given":"Stuart J.","family":"Russell","affiliation":"Computer Science Division University of California Berkeley , CA 94 720 , USA"},{"name":"John Binder","slug":"john-binder","given":"John","family":"Binder","affiliation":"Computer Science Division University of California Berkeley , CA 94 720 , USA"},{"name":"Daphne Koller","slug":"daphne-koller","given":"Daphne","family":"Koller","affiliation":"Computer Science Division University of California Berkeley , CA 94 720 , USA"},{"name":"Keiji Kanazawa","slug":"keiji-kanazawa","given":"Keiji","family":"Kanazawa","affiliation":"Computer Science Division University of California Berkeley , CA 94 720 , USA"}],"abstract":"Probabilistic networks, which provide compact descriptions of complex stochastic relationships among several random variables, are rapidly becoming the tool of choice for uncertain reasoning in artificial intelligence. We show that networks with fixed structure containing hidden variables can be learned automatically from data using a gradient-descent mechanism similar to that used in neural networks. We also extend the method to networks with intensionally represented distributions, including networks with continuous variables and dynamic probabilistic networks. Because probabilistic networks provide explicit representations of causal structure, human experts can easily contribute prior knowledge to the training process, thereby significantly improving the learning rate. Adaptive probabilistic networks (APNs) may soon compete directly with neural networks as models in computational neuroscience as well as in industrial and financial applications.","doi":null,"url":"https://ijcai.org/proceedings/1995/148","pdf":"https://ijcai.org/proceedings/1995/0148.pdf","markdown":"https://ijcai.org/proceedings/1995/148.md","bibtex":"https://ijcai.org/proceedings/1995/bibtex/148","volume":{"slug":"1995","title":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1995","url":"https://ijcai.org/proceedings/1995/","year":1995,"location":"Montréal, Québec, Canada","dates":"","editors":"Chris S. Mellish","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Learning","track":"Learning","number":148,"pages":{"first":1146,"last":1151},"keywords":[],"videos":[],"references":[{"position":1,"raw":"[Buntine, 1994] Wray L. Buntine. Operations for learning with graphical models. Journal of Artificial Intelligence Research, 2, December 1994.","title":"Operations for learning with graphical models","authors":"L Wray, Buntine","year":"1994","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cooper and Herskovits, 1992] G. Cooper and E. Herskovits. A Bayesian method for the induction of probabilistic net- works from data. Machine Learning, 9:309-347, 1992.","title":"A Bayesian method for the induction of probabilistic networks from data","authors":"G Cooper, E Herskovits","year":"1992","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"Dayan et al., in press] Peter Dayan, Geoffrey E. Hinton, Radford M. Neal, and Richard S. Zemel. The helmholtz machine. Neural Computation, in press.","title":"The helmholtz machine","authors":"Dayan","year":null,"venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dempster et al., 1977] A. Dempster, N. Laird, and D. Ru- bin. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 39 (Series B):l-38, 1977.","title":"Maximum likelihood from incomplete data via the EM algorithm","authors":"A Dempster, N Laird, D Rubin","year":"1977","venue":"Journal of the Royal Statistical Society","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Golmard and Mallet, 1991] J.-L. Golmard and A. Mallet. Learning probabilities in causal trees from incomplete databases. Revue d'Intelligence Artificielle, 5:93-106, 1991.","title":"Learning probabilities in causal trees from incomplete databases","authors":"J.-L Golmard, A Mallet","year":"1991","venue":"Revue d'Intelligence Artificielle","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Heckerman et al., 1994] D. Heckerman, D. Geiger, and M. Chickering. Learning Bayesian networks: The combi- nation of knowledge and statistical data. Technical Report 1162 LEARNING MSR-TR-94-09, Microsoft Research, Redmond, Washing- ton, 1994.","title":"Learning Bayesian networks: The combination of knowledge and statistical data","authors":"D Heckerman, D Geiger, M Chickering","year":"1994","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lauritzen and Spiegelhalter, 1988] Steffen L. Lauritzen and David J. Spiegelhalter. Local computations with prob- abilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society, B 50(2):157-224, 1988.","title":"Local computations with probabilities on graphical structures and their application to expert systems","authors":"Steffen L Lauritzen, David J Spiegelhalter","year":"1988","venue":"Journal of the Royal Statistical Society","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lauritzen and Wermuth, 1989] S. L. Lauritzen and N. Wer- muth. Graphical models for associations between vari- ables, some of which are qualitative and some quantitative. Annals of Statistics, 17:31-57, 1989.","title":"Graphical models for associations between variables, some of which are qualitative and some quantitative","authors":"S L Lauritzen, N Wermuth","year":"1989","venue":"Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lauritzen, 1991] Steffen L. Lauritzen. The EM algorithm for graphical association models with missing data. Tech- nical Report TR-91-05, Department of Statistics, Aalborg University, 1991.","title":"The EM algorithm for graphical association models with missing data","authors":"L Steffen, Lauritzen","year":"1991","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lauritzen, 1995] S. L. Lauritzen. The EM algorithm for graphical association models with missing data. Compu- tational Statistics and Data Analysis, 19:191-201, 1995.","title":"The EM algorithm for graphical association models with missing data","authors":"S L Lauritzen","year":"1995","venue":"Computational Statistics and Data Analysis","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Neal, 1992] R. M. Neal. Connectionist learning of belief networks. Artificial Intelligence, 56:71-113, 1992.","title":"Connectionist learning of belief networks","authors":"R M Neal","year":"1992","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Olesen et al., 1992] K. G. Olesen, S. L. Lauritzen, and F. V. Jensen. aHUGIN: A system for creating adaptive causal probabilistic networks. In Proceedings of the Eighth Con- ference on Uncertainty in Artificial Intelligence (UAI-92), Stanford, California, 1992.","title":"aHUGIN: A system for creating adaptive causal probabilistic networks","authors":"K G Olesen, S L Lauritzen, F V Jensen","year":"1992","venue":"Proceedings of the Eighth Conference on Uncertainty in Artificial Intelligence (UAI-92)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Morgan Kaufmann . [Pearl, 1988] Judea Pearl. Probabilistic Reasoning in Intel- ligent Systems: Networks of Plausible Inference . Morgan Kaufmann, San Mateo, California, 1988.","title":"Pearl","authors":"Morgan Kaufmann","year":"1988","venue":"Judea Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pradhan et al., 1994] M. Pradhan, G . M . Provan, B . Middle- ton, and M. Henrion. Knowledge engineering for large belief networks. In Proceedings of Uncertainty in Artifi- cial Intelligence, Seattle, Washington, 1994.","title":"Knowledge engineering for large belief networks","authors":"M Pradhan, G M Provan, B Middleton, M Henrion","year":"1994","venue":"Proceedings of Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"Morgan Kauf- mann.","title":null,"authors":"Morgan Kaufmann","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Price, 1992] William H . Price. Numerical Recipes in C. Cambridge University Press, Cambridge, 1992.","title":"Numerical Recipes in C","authors":"William H Price","year":"1992","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shachter and Peot, 1989] R. D. Shachter and M. A. Peot. Simulation approaches to general probabilistic inference on belief networks. In Proceedings of the Fifth Conference on Uncertainty in Artificial Intelligence (UAI-89), Wind- sor, Ontario, 1989.","title":"Simulation approaches to general probabilistic inference on belief networks","authors":"R D Shachter, M A Peot","year":"1989","venue":"Proceedings of the Fifth Conference on Uncertainty in Artificial Intelligence (UAI-89)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"Morgan Kaufmann . [Spiegelhalter and Cowell, 1992]","title":"Spiegelhalter and Cowell","authors":"Morgan Kaufmann","year":"1992","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"D. J. Spiegelhalter and R. G. Cowell. Learning in probabilistic expert systems. In J. M. Bernardo, Berger J. 0., Dawid A. P., and Adrian F. M. Smith, editors, Bayesian Statistics 4, 1992.","title":"Learning in probabilistic expert systems","authors":"D J Spiegelhalter, R G Cowell","year":"1992","venue":"Bayesian Statistics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Spiegelhalter et al., 1993] D. Spiegelhalter, P. Dawid , S. Lauritzen, and R. Cowell. Bayesian analysis in expert systems. Statistical Science, 8:219-282, 1993.","title":"Bayesian analysis in expert systems","authors":"D Spiegelhalter, P Dawid, S Lauritzen, R Cowell","year":"1993","venue":"Statistical Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}