“Machine Learning from Weak Supervision”

Masashi Sugiyama, Director of the RIKEN Center for Advanced Intelligence Project (AIP) started official cooperatiion with TU Darmstadt / Centre for Cognitve Science in 2017. On April 6th he will give a lecture on “Machine Learning from Weak Supervision – Towards Accurate Classification with Low Labeling Costs”

DATE: 6 April 2018

TIME: 11:00-12:00

LOCATION: Room C120 in S2/02

ABSTRACT:

Machine learning from big training data is achieving great success. However, there are various application domains that prohibit the use of massive labeled data. In this talk, Masashi Sugiyama will introduce recent advances in classification from weak supervision, including classification from two sets of unlabeled data, classification from positive and unlabeled data, a novel approach to semi-supervised classification, and classification from complementary labels.