Home /

Research

Showing 97 - 102 / 897

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning


Authors:  XiaohanChen, ZhangyangWang, SiyuTang....
Published date-12/01/2020
Tasks:  FeatureSelection, Few-ShotLearning, Meta-Learning

Abstract: 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


Authors:  SaschaSaralajew, LarsHoldijk, ThomasVillmann....
Published date-12/01/2020
Tasks:  Quantization

Abstract: 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


Authors:  WenzhengFeng, JieZhang, YuxiaoDong....
Published date-12/01/2020
Tasks:  DataAugmentation, NodeClassification

Abstract: 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


Authors:  ThomasLimbacher, RobertLegenstein....
Published date-12/01/2020
Tasks:  QuestionAnswering

Abstract: 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


Authors:  ArmandComas, ChiZhang, ZlatanFeric....
Published date-12/01/2020

Abstract: 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


Authors:  WenpengHu, MengyuWang, QiQin....
Published date-12/01/2020
Tasks:  AnomalyDetection, ImageClassification

Abstract: 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. …

Filter by

Categories

Tags