Home /
Research
Showing 637 - 642 / 897
A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning
HanyAbdulsamad, PeterNickl, PascalKlink....
Published date-11/10/2020
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
YikaiWang, WenbingHuang, FuchunSun....
Published date-11/10/2020
Image-to-ImageTranslation, SemanticSegmentation
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
MohammadrezaBaharani, StevenFurgurson, BabakParkhideh....
Published date-11/10/2020
HeartbeatClassification, TimeSeries, TimeSeriesPrediction
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
RaminNabati, HairongQi....
Published date-11/10/2020
3DObjectDetection, AutonomousVehicles, ObjectDetection, SensorFusion
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
ElliottGordon-Rodriguez, GabrielLoaiza-Ganem, GeoffPleiss....
Published date-11/10/2020
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?
YianZhang, AlexWarstadt, Haau-SingLi....
Published date-11/10/2020
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 …