55 citations · 197 across the 20 of their papers we have counts for
3 papers · 1 filter
Multi-task Learning with Weak Class Labels: Leveraging iEEG to Detect Cortical Lesions in Cryptogenic Epilepsy
Bilal Ahmed, Thomas Thesen, Karen E. Blackmon +4
Multi-task learning (MTL) is useful for domains in which data originates from multiple sources that are individually under-sampled. MTL methods are able to learn classification mod…
Evaluating Crowdsourcing Participants in the Absence of Ground-Truth
Ramanathan Subramanian, Romer Rosales, Glenn Fung +1
Given a supervised/semi-supervised learning scenario where multiple annotators are available, we consider the problem of identification of adversarial or unreliable annotators.
Asymptotic Analysis of Objectives based on Fisher Information in Active Learning
Jamshid Sourati, Murat Akcakaya, Todd K. Leen +2
Obtaining labels can be costly and time-consuming. Active learning allows a learning algorithm to intelligently query samples to be labeled for efficient learning. Fisher informati…