 |
| Pyramid-graph Bayesian Network |
Computational Models of the Neocortex
Our current understanding of the primate cerebral cortex (neocortex) and in particular the posterior, sensory association cortex has matured to a point where it is possible to develop computational models that capture the structure, scale and power of the neocortex for purposes of associative recall, sequence prediction and pattern completion among other functions. Implementing such models using readily available computing clusters is now within our grasp and promises to provide scientists with the opportunity to experiment with statistical inference and pattern recognition algorithms inspired by animal learning and developmental studies. The availability of cortex-scale models will facilitate not only our understanding of the brain but enable researchers to combine lessons learned from biology with state-of-the-art machine-learning techniques to design hybrid systems that combine the best of biological and traditional computing approaches.
Project status: Active
Project Home Page: http://www.cs.brown.edu/people/tld/projects/cortex/
Research Areas
| Artificial Intelligence |
| Computational Neuroscience |
| Machine Learning |
Research Themes
| Brain Science |
| Statistical Approaches |
People
| Thomas Dean |
Publications
Dean, T. A Computational Model of the Cerebral Cortex. In Proceedings of the Twentieth National Conference on Artificial Intelligence (AAAI-05) (Cambridge, Massachusetts, 2005), AAAI, MIT Press, pp. 938-943. [ pdf ]
Dean, T. Hierarchical Expectation Refinement for Learning Generative Perception Models. Tech. rep., Brown University, Providence, Rhode Island, Aug 2005. [ pdf ]
Dean, T. Scalable Inference in Hierarchical Generative Models. In Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics (2005), Annals of Artificial Intelligence and Mathematics. [ pdf ]
| Page Owner: Webmaster | Last Modified: Mon Oct 23 14:57:09 2006 |