Learning Multiple Related Tasks using Latent Independent Component Analysis Export

@misc{citeulike:2858368, abstract = {We propose a probabilistic model based on Independent Component Analysis for learning multiple related tasks. In our model the task parameters are assumed to be generated from independent sources which account for the relatedness of the tasks. We use Laplace distributions to model hidden sources which makes it possible to identify the hidden, independent components instead of just modeling correlations. Furthermore, our model enjoys a sparsity property which makes it both parsimonious...}, author = {Zhang, J. and Ghahramani, Z. and Yang, Y.}, citeulike-article-id = {2858368}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.6820}, keywords = {bayesian, model\_learning, probabilistic}, posted-at = {2008-06-03 07:53:28}, priority = {2}, title = {Learning Multiple Related Tasks using Latent Independent Component Analysis}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.6820}, year = {2005} }

TY - GEN ID - citeulike:2858368 L3 - citeulike-article-id:2858368 N2 - We propose a probabilistic model based on Independent Component Analysis for learning multiple related tasks. In our model the task parameters are assumed to be generated from independent sources which account for the relatedness of the tasks. We use Laplace distributions to model hidden sources which makes it possible to identify the hidden, independent components instead of just modeling correlations. Furthermore, our model enjoys a sparsity property which makes it both parsimonious... TI - Learning Multiple Related Tasks using Latent Independent Component Analysis KW - bayesian KW - model_learning KW - probabilistic AU - Zhang, J AU - Ghahramani, Z AU - Yang, Y PY - 2005/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.6820 ER -