output
20022022
most citedEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

10.8k citations

Showing 2022Show all

14 papers · 1 filter

math.NA2022

Impact of correlated observation errors on the convergence of the conjugate gradient algorithm in variational data assimilation

Olivier Goux, Selime Gürol, Anthony T. Weaver +2

An important class of nonlinear weighted least-squares problems arises from the assimilation of observations in atmospheric and ocean models. In variational data assimilation, inve…

cs.LG2022

MemSE: Fast MSE Prediction for Noisy Memristor-Based DNN Accelerators

Jonathan Kern, Sébastien Henwood, Gonçalo Mordido +4

Memristors enable the computation of matrix-vector multiplications (MVM) in memory and, therefore, show great potential in highly increasing the energy efficiency of deep neural ne…

cs.SE202212 cited

Understanding the Characteristics of Visual Contents in Open Source Issue Discussions: A Case Study of Jupyter Notebook

Vishakha Agrawal, Yong-Han Lin, Jinghui Cheng

Most issue tracking systems for open source software (OSS) development include features for community members to embed visual contents, such as images and videos, to enhance the di…

cs.SE20229 cited

Characterizing User Behaviors in Open-Source Software User Forums: An Empirical Study

Jazlyn Hellman, Jiahao Chen, Md. Sami Uddin +2

User forums of Open Source Software (OSS) enable end-users to collaboratively discuss problems concerning the OSS applications. Despite decades of research on OSS, we know very lit…

cs.SE202214 cited

How heated is it? Understanding GitHub locked issues

Isabella Ferreira, Bram Adams, Jinghui Cheng

Although issues of open source software are created to discuss and solve technical problems, conversations can become heated, with discussants getting angry and/or agitated for a v…

eess.SP202210 cited

On handwriting pressure normalization for interoperability of different acquisition stylus

Marcos Faundez-Zanuy, Olga Brotons-Rufes, Carles Paul-Recarens +1

In this paper, we present a pressure characterization and normalization procedure for online handwritten acquisition. Normalization process has been tested in biometric recognition…