Deep Learning
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
Fanny Yang, Zuowen Wang, Christina Heinze-Deml
Similar relative gains hold for SVHN and CIFAR-100.
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
However, this often comes at a high computational cost and high memory footprint.
Consistent Feature Selection for Analytic Deep Neural Networks
One of the most important steps toward model interpretability is feature selection, which aims to identify the subset of relevant features with respect to an outcome.
Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder
Ji Feng, Qi-Zhi Cai, Zhi-Hua Zhou
Unlike GANs, solving such problem is computationally challenging, we then proposed a simple yet effective procedure to decouple the alternating updates for the two networks for stability.
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
We extend their approach to train scalable, expressive, provably Lipschitz convo-lutional networks.
MixMatch: A Holistic Approach to Semi-Supervised Learning
David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin A. Raffel
Furthermore, data labels may contain private information.
Practical Quasi-Newton Methods for Training Deep Neural Networks
In our proposed methods, we approximate the Hessian by a block-diagonal matrix and use the structure of the gradient and Hessian to further approximate these blocks, each of which corresponds to a layer, as the Kronecker product of two much smaller matrices.
On Power Laws in Deep Ensembles
Ensembles of deep neural networks are known to achieve state-of-the-art performance in uncertainty estimation and lead to accuracy improvement.
Spectral Representations for Convolutional Neural Networks
Oren Rippel, Jasper Snoek, Ryan P. Adams
Neural Information Processing Systems http://nips.cc/
Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
Han Zhu, Daqing Chang, Ziru Xu, Pengye Zhang, Xiang Li, Jie He, Han Li, Jian Xu, Kun Gai
Neural Information Processing Systems http://nips.cc/