AAAI 2017 accepted papers on Architectures and efficiency
29 of the 639 papers accepted at AAAI 2017 (4.5%) are on Architectures and efficiency, compared with 3.3% at AAAI 2016. They fall into 5 topics.
See AAAI 2017 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 · 13 papers
- Neural Machine Translation with Reconstruction (186 citations)
- Neural Machine Translation Advised by Statistical Machine Translation (95 citations)
- Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation (86 citations)
- Incrementally Learning the Hierarchical Softmax Function for Neural Language Models (79 citations)
- Definition Modeling: Learning to Define Word Embeddings in Natural Language (77 citations)
- Exploring Normalization in Deep Residual Networks with Concatenated Rectified Linear Units (37 citations)
- Multi-Path Feedback Recurrent Neural Networks for Scene Parsing (31 citations)
- A Context-Enriched Neural Network Method for Recognizing Lexical Entailment (23 citations)
- Learning Unitary Operators with Help From u(n) (23 citations)
- Geometry of Compositionality (19 citations)
- Sparse Boltzmann Machines with Structure Learning as Applied to Text Analysis (14 citations)
- A Dependency-Based Neural Reordering Model for Statistical Machine Translation (8 citations)
and 1 more in the interactive map.
CNN design · 7 papers
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (13,828 citations)
- Understanding the Semantic Structures of Tables with a Hybrid Deep Neural Network Architecture (82 citations)
- Depth CNNs for RGB-D Scene Recognition: Learning from Scratch Better than Transferring from RGB-CNNs (72 citations)
- Deep Learning for Fixed Model Reuse (50 citations)
- Regularization for Unsupervised Deep Neural Nets (26 citations)
- ESPACE: Accelerating Convolutional Neural Networks via Eliminating Spatial and Channel Redundancy (23 citations)
- Patch Reordering: A NovelWay to Achieve Rotation and Translation Invariance in Convolutional Neural Networks (7 citations)
Attention and transformers · 7 papers
- SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents (1,284 citations)
- Coherent Dialogue with Attention-Based Language Models (92 citations)
- BattRAE: Bidimensional Attention-Based Recursive Autoencoders for Learning Bilingual Phrase Embeddings (17 citations)
- Deterministic Attention for Sequence-to-Sequence Constituent Parsing (15 citations)
- Recurrent Attentional Topic Model (15 citations)
- Translation Prediction with Source Dependency-Based Context Representation (14 citations)
- A Dynamic Window Neural Network for CCG Supertagging (13 citations)
Pruning and efficient tuning · 1 paper
- Value Compression of Pattern Databases (6 citations)
Quantization · 1 paper
- How to Train a Compact Binary Neural Network with High Accuracy? (244 citations)
