Artificial General Intelligence through Large-Scale, Multimodal Bayesian Learning
Author: 
Brian MilchAuthors Info & Claims
Pages 248 - 255
Abstract
An artificial system that achieves human-level performance on open-domain tasks must have a huge amount of knowledge about the world. We argue that the most feasible way to construct such a system is to let it learn from the large collections of text, images, and video that are available online. More specifically, the system should use a Bayesian probability model to construct hypotheses about both specific objects and events, and general patterns that explain the observed data.
References
[1]
D. B. Lenat. CYC: A large-scale investment in knowledge infrastructure. Communications of the ACM, 38(11):33-38, 1995.
[2]
P. Singh, T. Lin, E. T. Mueller, G. Lim, T. Perkins, and W. L. Zhu. Open Mind Common Sense: Knowledge acquisition from the general public. In Proc. 1st Int'l Conf. on Ontologies, Databases, and Applications of Semantics for Large Scale Information Systems, 2002.
[3]
J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Francisco, revised edition, 1988.
[4]
M. I. Jordan, editor. Learning in Graphical Models. MIT Press, Cambridge, MA, 1998.
[5]
E. Segal, B. Taskar, A. Gasch, N. Friedman, and D. Koller. Rich probabilistic models for gene expression. Bioinformatics, 17(Suppl 1):S243-252, 2003.
[6]
S. Thrun, M. Montemerlo, and A. Aron. Probabilistic terrain analysis for high-speed desert driving. In Proc. Robotics Science and Systems Conf., 2006.
[7]
M. Collins. Three generative, lexicalised models for statistical parsing. In Proc. 35th Annual Meeting of the Assoc. for Computational Linguistics, 1997.
[8]
G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology, 2007.
[9]
B. Goertzel. Patterns, hypergraphs and embodied general intelligence. In IEEE World Congress on Computational Intelligence: Panel Discussion on "A Roadmap to Human-Level Intelligence", 2006.
[10]
M. Banko, M. J. Cafarella, S. Soderland, M. Broadhead, and O. Etzioni. Open information extraction from the Web. In Proc. 20th Int'l Conf. on Artificial Intelligence, 2007.
[11]
W. Pentney, M. Philipose, J. Bilmes, and H. Kautz. Learning large-scale common sense models of everyday life. In Proc. 22nd AAAI Conf. on Artificial Intelligence, 2007.
[12]
C. P. Robert. The Bayesian Choice. Springer, New York, 2nd edition, 2001.
[13]
E. T. Jaynes. Inference, method and decision: Towards a Bayesian philosophy of science (book review). J. Amer. Stat. Assoc., 74(367):740-741, 1979.
[14]
M. Li and P. Vitanyi. An Introduction to Kolmogorov Complexity and Its Applications. Springer, 2nd edition, 1997.
[15]
J. Rissanen. Information and Complexity in Statistical Modeling. Springer, 2007.
[16]
C. Howson and P. Urbach. Scientific Reasoning: The Bayesian Approach. Open Court, La Salle, IL, 1989.
[17]
A. Gopnik and J. B. Tenenbaum. Bayesian networks, Bayesian learning, and cognitive development. Developmental Science, 10(3):281-287, 2007.
[18]
M. Hutter. Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, 2005.
[19]
R. Fagin and J. Y. Halpern. Reasoning about knowledge and probability. J. Assoc. for Computing Machinery, 41(2):340-367, 1994.
[20]
D. Koller and B. Milch. Multi-agent influence diagrams for representing and solving games. Games and Economic Behavior, 45(1):181-221, 2003.
[21]
T. S. Ferguson. Bayesian density estimation by mixtures of normal distributions. In M. H. Rizvi, J. S. Rustagi, and D. Siegmund, editors, Recent Advances in Statistics: Papers in Honor of Herman Chernoff on His Sixtieth Birthday, pages 287-302. Academic Press, New York, 1983.
[22]
R. M. Neal. Markov chain sampling methods for Dirichlet process mixture models. J. Computational and Graphical Statistics, 9:249-265, 2000.
[23]
Y.W. Teh, M. I. Jordan, M. J. Beal, and D. M. Blei. Hierarchical Dirichlet processes. J. Amer. Statist. Assoc. , 101:1566-1581, 2006.
[24]
C. Kemp, J. B. Tenenbaum, T. L. Griffiths, T. Yamada, and N. Ueda. Learning systems of concepts with an infinite relational model. In Proc. 21st AAAI National Conf. on Artificial Intelligence, 2006.
[25]
D. Heckerman, D. Geiger, and D. Chickering. Learning Bayesian networks: The combination of knowledge and statistical data. Machine Learning, 20:197-243, 1995.
[26]
L. Getoor and B. Taskar, editors. Introduction to Statistical Relational Learning. MIT Press, 2007.
[27]
N. Friedman, L. Getoor, D. Koller, and A. Pfeffer. Learning probabilistic relational models. In Proc. 16th International Joint Conference on Artificial Intelligence, pages 1300-1307, 1999.
[28]
S. Kok and P. Domingos. Learning the structure of Markov logic networks. In Proc. 22nd International Conf. on Machine Learning, pages 441-448, 2005.
[29]
B. Milch, B. Marthi, S. Russell, D. Sontag, D. L. Ong, and A. Kolobov. BLOG: Probabilistic models with unknown objects. In Proc. 19th International Joint Conference on Artificial Intelligence, pages 1352-1359, 2005.
[30]
W. R. Gilks, S. Richardson, and D. J. Spiegelhalter, editors. Markov Chain Monte Carlo in Practice. Chapman and Hall, London, 1996.
[31]
M. Jordan, Z. Ghahramani, T. Jaakkola, and L. Saul. Introduction to variational methods for graphical models. Machine Learning, 37:183-233, 1999.
[32]
E. P. Xing, M. I. Jordan, and S. Russell. A generalized mean field algorithm for variational inference in exponential families. In Proc. 19th Conf. on Uncertainty in Artificial Intelligence, pages 583-591, 2003.
[33]
K. P. Murphy, Y. Weiss, and M. I. Jordan. Loopy belief propagation for approximate inference: An empirical study. In Proc. 15th Conf. on Uncertainty in Artificial Intelligence, pages 467-475, 1999.
[34]
J. S. Yedidia, W. T. Freeman, and Y. Weiss. Generalized belief propagation. In Advances in Neural Information Processing Systems 13, pages 689-695. MIT Press, Cambridge, MA, 2001.
[35]
B. Milch and S. Russell. General-purpose MCMC inference over relational structures. In Proc. 22nd Conf. on Uncertainty in Artificial Intelligence, pages 349-358, 2006.
[36]
D. Poole. First-order probabilistic inference. In Proc. 18th International Joint Conference on Artificial Intelligence, pages 985-991, 2003.
[37]
R. de Salvo Braz, E. Amir, and D. Roth. Lifted first-order probabilistic inference. In Proc. 19th International Joint Conference on Artificial Intelligence, pages 1319-1325, 2005.
[38]
T. Sang, P. Beame, and H. Kautz. Performing Bayesian inference by weighted model counting. In Proc. 20th AAAI National Conf. on Artificial Intelligence, pages 475-482, 2005.
[39]
H. Poon and P. Domingos. Sound and efficient inference with probabilistic and deterministic dependencies. In Proc. 21st AAAI National Conf. on Artificial Intelligence, pages 458-463, 2006.
[40]
E. M. Voorhees. Overview of TREC 2004. In The Thirteenth Text Retrieval Conference. NIST, 2004.
[41]
I. Dagan, O. Glickman, and B. Magnini. The PASCAL recognising textual entailment challenge. In Proc. PASCAL Challenges Workshop on Recognising Textual Entailment, 2005.
[42]
C. Fellbaum, editor. WordNet: An Electronic Lexical Database. MIT Press, 1998.
- Artificial General Intelligence through Large-Scale, Multimodal Bayesian Learning
Recommendations
Bayesian Methods for Artificial Intelligence and Machine Learning
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial IntelligenceBayesian methods provide a framework for representing and manipulating uncertainty, for learning from noisy data, and for making decisions that maximize expected utility----components which are important to both AI and Machine Learning. However, ...
Large scale nonparametric Bayesian inference: data parallelisation in the Indian Buffet Process
NIPS'09: Proceedings of the 23rd International Conference on Neural Information Processing SystemsNonparametric Bayesian models provide a framework for flexible probabilistic modelling of complex datasets. Unfortunately, the high-dimensional averages required for Bayesian methods can be slow, especially with the unbounded representations used by ...
GENERAL: GENerative, Explainable and Reasonable Artificial Learning
CHItaly '23: Proceedings of the 15th Biannual Conference of the Italian SIGCHI ChapterThe GENERAL (GENerative, Explainable and Reasonable Artificial Learning) workshop, held at CHITALY 2023, delves into the advancements in General and Generative Artificial Intelligence (GGAI), with a focus on breakthroughs in natural language processing ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Publisher
IOS Press
Netherlands
Publication History
Published: 20 June 2008
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 02 Mar 2025