Publication at NIPS 2017 (watch video!)

Our paper Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification was accepted at this year's Neural Information Processing Systems (NIPS) Conference. The work extends the framework of probabilistic classifier chains to the case of predicting a sequence of positive labels and solves this re-formulation of the multi-label classification problem by using recurrent neural networks. You can watch a small introduction from the recorded live stream at NIPS (jump to 1:17:25 in the video) given by the main author Jinseok Nam.

Kontakt
small ke-icon

Knowledge Engineering Group

Fachbereich Informatik
TU Darmstadt

S2|02 D203
Hochschulstrasse 10

D-64289 Darmstadt

Sekretariat:
Telefon-Symbol +49 6151 16-21811
Fax-Symbol +49 6151 16-21812
E-Mail-Symbol info@ke.tu-darmstadt.de

 
A A A | Drucken | Impressum | Sitemap | Suche | Mobile Version
zum Seitenanfangzum Seitenanfang