Home /
Research
Showing 97 - 102 / 897
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning
XiaohanChen, ZhangyangWang, SiyuTang....
Published date-12/01/2020
FeatureSelection, Few-ShotLearning, Meta-Learning
Meta-learning improves generalization of machine learning models when faced with previously unseen tasks by leveraging experiences from different, yet related prior tasks. To allow for better generalization, we propose a …
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms
SaschaSaralajew, LarsHoldijk, ThomasVillmann....
Published date-12/01/2020
Quantization
Methods for adversarial robustness certification aim to provide an upper bound on the test error of a classifier under adversarial manipulation of its input. Current certification methods are computationally expensive …
Graph Random Neural Networks for Semi-Supervised Learning on Graphs
WenzhengFeng, JieZhang, YuxiaoDong....
Published date-12/01/2020
DataAugmentation, NodeClassification
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, …
H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks
ThomasLimbacher, RobertLegenstein....
Published date-12/01/2020
QuestionAnswering
The ability to base current computations on memories from the past is critical for many cognitive tasks such as story understanding. Hebbian-type synaptic plasticity is believed to underlie the retention …
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 …
HRN: A Holistic Approach to One Class Learning
WenpengHu, MengyuWang, QiQin....
Published date-12/01/2020
AnomalyDetection, ImageClassification
Existing neural network based one-class learning methods mainly use various forms of auto-encoders or GAN style adversarial training to learn a latent representation of the given one class of data. …