E-LIB Suche - Ergebnisse für: Barabasz, Barbara

1

Winograd Convolution for Deep Neural Networks: Efficient Po..:

Alam, Syed Asad ; Anderson, Andrew ; Barabasz, Barbara.
ACM Transactions on Embedded Computing Systems. 21 (2022) 6 - p. 1-28 , 2022

Link: https://doi.org/10.1145/..

2

Error Analysis and Improving the Accuracy of Winograd Convo..:

Barabasz, Barbara ; Anderson, Andrew ; Soodhalter, Kirk M..
ACM Transactions on Mathematical Software (TOMS). 46 (2020) 4 - p. 1-33 , 2020

Link: https://dl.acm.org/doi/1..

3

Error Analysis and Improving the Accuracy of Winograd Convo..:

Barabasz, Barbara ; Anderson, Andrew ; Soodhalter, Kirk M..
ACM Transactions on Mathematical Software. 46 (2020) 4 - p. 1-33 , 2020

Link: https://doi.org/10.1145/..

4

Winograd Convolution for DNNs: Beyond Linear Polynomials:

, In: Lecture Notes in Computer Science; AI*IA 2019 – Advances in Artificial Intelligence,

Barabasz, Barbara ; Gregg, David - p. 307-320 , 2019

Link: https://doi.org/10.1007/..

5

Speeding up multi-objective optimization of liquid fossil f..:

Barabasz, Barbara ; Barrett, Stephen ; Siwik, Leszek...
Journal of Computational Science. 31 (2019) - p. 126-136 , 2019

Link: https://doi.org/10.1016/..

6

Coupled isogeometric Finite Element Method and Hierarchical..:

Barabasz, Barbara ; Łoś, Marcin ; Woźniak, Maciej..
Procedia Computer Science. 108 (2017) - p. 828-837 , 2017

Link: https://doi.org/10.1016/..

7

A hybrid algorithm for solving inverse problems in elastici..:

Barabasz, Barbara ; Gajda-Zagórska, Ewa ; Migórski, Stanisław...
International Journal of Applied Mathematics and Computer Science. 24 (2014) 4 - p. 865-886 , 2014

Link: https://doi.org/10.2478/..

8

Multi-deme, twin adaptive strategyhp-HGS:

Barabasz, Barbara ; Migórski, Stanisław ; Schaefer, Robert.
Inverse Problems in Science and Engineering. 19 (2011) 1 - p. 3-16 , 2011

Link: https://doi.org/10.1080/..

9

Winograd Convolution for Deep Neural Networks: Efficient Po..:

Alam, Syed Asad ; Anderson, Andrew ; Barabasz, Barbara.
http://arxiv.org/abs/2201.10369. , 2022

Link: http://arxiv.org/abs/220..

10

Quantaized Winograd/Toom-Cook Convolution for DNNs: Beyond ..:

Barabasz, Barbara
http://arxiv.org/abs/2004.11077. , 2020

Link: http://arxiv.org/abs/200..

11

Winograd Convolution for DNNs: Beyond linear polynomials:

Barabasz, Barbara ; Gregg, David
http://arxiv.org/abs/1905.05233. , 2019

Link: http://arxiv.org/abs/190..

12

Error Analysis and Improving the Accuracy of Winograd Convo..:

Barabasz, Barbara ; Anderson, Andrew ; Soodhalter, Kirk M.
http://arxiv.org/abs/1803.10986. , 2018

Link: http://arxiv.org/abs/180..

13

A hybrid algorithm for solving inverse problems in elastici..:

Barabasz, Barbara ; Gajda-Zagórska, Ewa ; Migórski, Stanisław...
International Journal of Applied Mathematics and Computer Science, T. 24, nr 4, s. 865-886. , 2014

Link: http://ruj.uj.edu.pl/xml..

14

A hybrid algorithm for solving inverse problems in elastici..:

Barabasz Barbara ; Gajda-Zagórska Ewa ; Migórski Stanisław...
https://doi.org/10.2478/amcs-2014-0064. , 2014

Link: https://doi.org/10.2478/..

15

Improving the Accuracy of the Winograd Convolution for Deep..:

Barabasz, Barbara Maria
Barabasz, Barbara Maria, Improving the Accuracy of the Winograd Convolution for Deep Neural Networks, Trinity College Dublin.School of Computer Science & Statistics, 2022. , 2022

Link: http://hdl.handle.net/22..