Now showing items 1-2 of 2
Learning without labels and nonnegative tensor factorization
(Georgia Institute of Technology, 2010-04-08)
Supervised learning tasks like building a classifier, estimating the error rate of the predictors, are typically performed with labeled data. In most cases, obtaining labeled data is costly as it requires manual labeling. ...
Domain knowledge, uncertainty, and parameter constraints
(Georgia Institute of Technology, 2010-08-24)