Home /
Research
Showing 169 - 174 / 904
Almost Surely Stable Deep Dynamics
NathanLawrence, PhilipLoewen, MichaelForbes....
Published date-12/01/2020
We introduce a method for learning provably stable deep neural network based dynamic models from observed data. Specifically, we consider discrete-time stochastic dynamic models, as they are of particular interest …
Information Maximization for Few-Shot Learning
MalikBoudiaf, ImtiazZiko, JérômeRony....
Published date-12/01/2020
Few-ShotLearning, Meta-Learning
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction …
Model Class Reliance for Random Forests
GavinSmith, RobertoMansilla, JamesGoulding....
Published date-12/01/2020
Variable Importance (VI) has traditionally been cast as the process of estimating each variables contribution to a predictive model's overall performance. Analysis of a single model instance, however, guarantees no …
Learning Disentangled Representations of Videos with Missing Data
ArmandComas, ChiZhang, ZlatanFeric....
Published date-12/01/2020
Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in …
Backpropagating Linearly Improves Transferability of Adversarial Examples
YiwenGuo, QizhangLi, HaoChen....
Published date-12/01/2020
The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the …
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
JayNandy, WynneHsu, MongLiLee....
Published date-12/01/2020
Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types. However, for in-domain examples with high data uncertainties among multiple classes, even a DPN model …