Information theory, multivariate dependence, and genetic network inference Export

@misc{citeulike:574, abstract = {We define the concept of dependence among multiple variables using maximum entropy techniques and introduce a graphical notation to denote the dependencies. Direct inference of information theoretic quantities from data uncovers dependencies even in undersampled regimes when the joint probability distribution cannot be reliably estimated. The method is tested on synthetic data. We anticipate it to be useful for inference of genetic circuits and other biological signaling networks.}, archivePrefix = {arXiv}, author = {Nemenman, Ilya}, citeulike-article-id = {574}, citeulike-linkout-0 = {http://arxiv.org/abs/q-bio.QM/0406015}, citeulike-linkout-1 = {http://arxiv.org/pdf/q-bio.QM/0406015}, day = {7}, eprint = {q-bio.QM/0406015}, keywords = {graph, machine-learning}, month = {June}, posted-at = {2008-08-13 21:03:53}, priority = {2}, title = {Information theory, multivariate dependence, and genetic network inference}, url = {http://arxiv.org/abs/q-bio.QM/0406015}, year = {2004} }

TY - ELEC ID - citeulike:574 L3 - citeulike-article-id:574 N2 - We define the concept of dependence among multiple variables using maximum entropy techniques and introduce a graphical notation to denote the dependencies. Direct inference of information theoretic quantities from data uncovers dependencies even in undersampled regimes when the joint probability distribution cannot be reliably estimated. The method is tested on synthetic data. We anticipate it to be useful for inference of genetic circuits and other biological signaling networks. TI - Information theory, multivariate dependence, and genetic network inference KW - graph KW - machine-learning AU - Nemenman, Ilya PY - 2004/06/07/ UR - http://arxiv.org/abs/q-bio.QM/0406015 ER -