Home /

Research

Showing 565 - 570 / 897

Adversarial Robustness Against Image Color Transformation within Parametric Filter Space


Authors:  ZhengyuZhao, ZhuoranLiu, MarthaLarson....
Published date-11/12/2020

Abstract: We propose Adversarial Color Enhancement (ACE), a novel approach to generating non-suspicious adversarial images by optimizing a color transformation within a parametric filter space. The filter we use approximates human-understandable …

Fit2Form: 3D Generative Model for Robot Gripper Form Design


Authors:  HuyHa, ShubhamAgrawal, ShuranSong....
Published date-11/12/2020

Abstract: The 3D shape of a robot's end-effector plays a critical role in determining it's functionality and overall performance. Many industrial applications rely on task-specific gripper designs to ensure the system's …

Biomedical Named Entity Recognition at Scale


Authors:  VeyselKocaman, DavidTalby....
Published date-11/12/2020
Tasks:  EntityResolution, InformationRetrieval, MedicalNamedEntityRecognition, NamedEntityRecognition, QuestionAnswering, RelationExtraction

Abstract: Named entity recognition (NER) is a widely applicable natural language processing task and building block of question answering, topic modeling, information retrieval, etc. In the medical domain, NER plays a …

Theoretical Knowledge Graph Reasoning via Ending Anchored Rules


Authors:  CanlinZhang, YannisKatsis, YoshikiVazquez-Baeza....
Published date-11/12/2020
Tasks:  KnowledgeGraphCompletion, KnowledgeGraphs, LinkPrediction

Abstract: Discovering precise and specific rules from knowledge graphs is regarded as an essential challenge, which can improve the performances of many downstream tasks and even provide new ways to approach …

Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis


Authors:  Chung-MingChien, Hung-YiLee....
Published date-11/12/2020
Tasks:  SpeechSynthesis

Abstract: Prosody modeling is an essential component in modern text-to-speech (TTS) frameworks. By explicitly providing prosody features to the TTS model, the style of synthesized utterances can thus be controlled. However, …

Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting


Authors:  ZekeXie, FengxiangHe, ShaopengFu....
Published date-11/12/2020

Abstract: Deep learning is often criticized by two serious issues which rarely exist in natural nervous systems: overfitting and catastrophic forgetting. It can even memorize randomly labelled data, which has little …

Filter by

Categories

Tags