Home /

Research

Showing 637 - 642 / 897

A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning


Authors:  HanyAbdulsamad, PeterNickl, PascalKlink....
Published date-11/10/2020

Abstract: Probabilistic regression techniques in control and robotics applications have to fulfill different criteria of data-driven adaptability, computational efficiency, scalability to high dimensions, and the capacity to deal with different modalities …

Deep Multimodal Fusion by Channel Exchanging


Authors:  YikaiWang, WenbingHuang, FuchunSun....
Published date-11/10/2020
Tasks:  Image-to-ImageTranslation, SemanticSegmentation

Abstract: Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet, current methods including aggregation-based …

ATCN: Agile Temporal Convolutional Networks for Processing of Time Series on Edge


Authors:  MohammadrezaBaharani, StevenFurgurson, BabakParkhideh....
Published date-11/10/2020
Tasks:  HeartbeatClassification, TimeSeries, TimeSeriesPrediction

Abstract: This paper presents a scalable deep learning model called Agile Temporal Convolutional Network (ATCN) for high-accurate fast classification and time series prediction in resource-constrained embedded systems. ATCN is primarily designed …

CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection


Authors:  RaminNabati, HairongQi....
Published date-11/10/2020
Tasks:  3DObjectDetection, AutonomousVehicles, ObjectDetection, SensorFusion

Abstract: The perception system in autonomous vehicles is responsible for detecting and tracking the surrounding objects. This is usually done by taking advantage of several sensing modalities to increase robustness and …

Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning


Authors:  ElliottGordon-Rodriguez, GabrielLoaiza-Ganem, GeoffPleiss....
Published date-11/10/2020

Abstract: Modern deep learning is primarily an experimental science, in which empirical advances occasionally come at the expense of probabilistic rigor. Here we focus on one such example; namely the use …

When Do You Need Billions of Words of Pretraining Data?


Authors:  YianZhang, AlexWarstadt, Haau-SingLi....
Published date-11/10/2020

Abstract: NLP is currently dominated by general-purpose pretrained language models like RoBERTa, which achieve strong performance on NLU tasks through pretraining on billions of words. But what exact knowledge or skills …

Filter by

Categories

Tags