Deep Learning
Program Synthesis and Semantic Parsing with Learned Code Idioms
Eui Chul Shin, Miltiadis Allamanis, Marc Brockschmidt, Alex Polozov
Neural Information Processing Systems http://nips.cc/
Intrinsic dimension of data representations in deep neural networks
Alessio Ansuini, Alessandro Laio, Jakob H. Macke, Davide Zoccolan
Neural Information Processing Systems http://nips.cc/
A Primal-Dual Formulation for Deep Learning with Constraints
Since the constraints are independent of the target labels, our framework easily generalizes to semi-supervised setting.
Self-attention with Functional Time Representation Learning
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan
It detects attention weights from input event sequence and returns the sequence representation.
STAR-Caps: Capsule Networks with Straight-Through Attentive Routing
Karim Ahmed, Lorenzo Torresani
By throwing away information about the precise position of an entity, max-pooling achieves some translation invariance.
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
Sitao Luan, Mingde Zhao, Xiao-Wen Chang, Doina Precup
Recently, neural network based approaches have achieved significant progress for solving large, complex, graph-structured problems.
Gaussian-Based Pooling for Convolutional Neural Networks
The above-mentioned pooling methods are generally described by a convex-hull model which produces the output activation as a convex combination of the input neuron activations (Section 2.1).
A New Defense Against Adversarial Images: Turning a Weakness into a Strength
Shengyuan Hu, Tao Yu, Chuan Guo, Wei-Lun Chao, Kilian Q. Weinberger
While many techniques for detecting these attacks have been proposed, they are easily bypassed when the adversary has full knowledge of the detection mechanism and adapts the attack strategy accordingly.