Deep Learning
Training deep learning based denoisers without ground truth data
Shakarim Soltanayev, Se Young Chun
Conventional denoising methods do not usually require noiseless ground truth images to perform denoising, but often require them for tuning parameters of image filters to elicit the best possible results (minimum MSE).
Can We Gain More from Orthogonality Regularizations in Training Deep Networks?
Nitin Bansal, Xiaohan Chen, Zhangyang Wang
As we will explain later, existing works employ the most obvious but not necessarily appropriate option.
A Unified View of Piecewise Linear Neural Network Verification
Rudy R. Bunel, Ilker Turkaslan, Philip Torr, Pushmeet Kohli, Pawan K. Mudigonda
The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models.
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew G. Wilson
The loss functions of deep neural networks are complex and their geometric properties are not well understood.
Transfer Learning with Neural AutoML
We reduce the computational cost of Neural AutoML with transfer learning.
Binary Classification from Positive-Confidence Data
Takashi Ishida, Gang Niu, Masashi Sugiyama
Our work is related to one-class classification which is aimed at "describing" the positive class by clustering-related methods, but one-class classification does not have the ability to tune hyper-parameters
Recurrent Relational Networks
Rasmus Palm, Ulrich Paquet, Ole Winther
Neural Information Processing Systems http://nips.cc/
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang
Neural Information Processing Systems http://nips.cc/
Constrained Graph Variational Autoencoders for Molecule Design
Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander Gaunt
Neural Information Processing Systems http://nips.cc/
Porcupine Neural Networks: Approximating Neural Network Landscapes
Soheil Feizi, Hamid Javadi, Jesse Zhang, David Tse
We show that most local optima of PNN optimizations are global while we have a characterization of regions where bad local optimizers may exist.