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.
+49 6151 16-21811
+49 6151 16-
Drucken
Impressum
Sitemap
Suche
