Multi-task deep neural network for multi-label learning

80 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

DOC: Deep Open Classification of Text Documents (2017, background): “DOC is also related to multi-task learning (Huang et al., 2013; Caruana, 1998), where each label li is related to a 1-vs-rest binary classification task with shared representations from CNN and fully connected layers.”
Learning Semantic Concepts and Order for Image and Sentence Matching (2017, background): “Many effective models on this problem have been proposed recently [8, 11, 13, 33, 35, 36, 37], which mostly learn various CNN-based models as nonlinear mappings from images to the desired multiple labels.”
Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition (2015, methodology): “A simpler solution is to abandon the phone-based models and employ graphemes as the basic acoustic units because grapheme modeling [2], [3], [4], [5], [6] does not require a phonetic dictionary1.”