AAAI 2016 accepted papers on Architectures and efficiency
18 of the 548 papers accepted at AAAI 2016 (3.3%) are on Architectures and efficiency. They fall into 4 topics.
See AAAI 2016 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
RNNs and normalization · 15 papers
- Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (1,646 citations)
- Character-Aware Neural Language Models (1,600 citations)
- Siamese Recurrent Architectures for Learning Sentence Similarity (940 citations)
- Deep Learning with S-Shaped Rectified Linear Activation Units (216 citations)
- Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences (189 citations)
- Learning Statistical Scripts with LSTM Recurrent Neural Networks (167 citations)
- How Important Is Weight Symmetry in Backpropagation? (155 citations)
- Efficient Learning of Timeseries Shapelets (81 citations)
- Shakeout: A New Regularized Deep Neural Network Training Scheme (52 citations)
- Morphological Segmentation with Window LSTM Neural Networks (44 citations)
- Agreement on Target-Bidirectional LSTMs for Sequence-to-Sequence Learning (35 citations)
- Visual Learning of Arithmetic Operation (26 citations)
and 3 more in the interactive map.
Quantization · 1 paper
CNN design · 1 paper
- Learning FRAME Models Using CNN Filters (60 citations)
