Compressing Neural Language Models by Sparse Word RepresentationsAnnual Meeting of the Association for Computational Linguistics (ACL), 2016 |
Impatient DNNs - Deep Neural Networks with Dynamic Time BudgetsBritish Machine Vision Conference (BMVC), 2016 |
Compression of Neural Machine Translation Models via PruningConference on Computational Natural Language Learning (CoNLL), 2016 |
Sequence-Level Knowledge DistillationConference on Empirical Methods in Natural Language Processing (EMNLP), 2016 |
Deep Learning Markov Random Field for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016 |
Convolution by Evolution: Differentiable Pattern Producing NetworksAnnual Conference on Genetic and Evolutionary Computation (GECCO), 2016 |
Mapping Auto-context Decision Forests to Deep ConvNets for Semantic
SegmentationBritish Machine Vision Conference (BMVC), 2015 |
Data-free parameter pruning for Deep Neural NetworksBritish Machine Vision Conference (BMVC), 2015 |
Compression of Fully-Connected Layer in Neural Network by Kronecker
ProductInternational Conference on Advanced Computational Intelligence (ICACI), 2015 Shuchang Zhou Jia-Nan Wu |