Experience-driven formation of parts-based representations in a model of layered visual memory

Autor: Jenia Jitsev, Christoph V. Der Malsburg

Publikováno v: Frontiers in Computational Neuroscience, Vol 3 (2009)

Growing neuropsychological and neurophysiological evidence suggests that the visual cortex uses parts-based representations to encode, store and retrieve relevant objects. In such a scheme, objects are represented as a set of spatially distributed lo

Externí odkaz: https://doaj.org/article/9f80563430114bea97805618af22e703

Convolutional neural networks for high throughput screening of catalyst layer inks for polymer electrolyte fuel cells

Autor: Mohammad J, Eslamibidgoli, Fabian P, Tipp, Jenia, Jitsev, Jasna, Jankovic, Michael H, Eikerling, Kourosh, Malek

Publikováno v: RSC advances. 11(51)

The performance of polymer electrolyte fuel cells decisively depends on the structure and processes in membrane electrode assemblies and their components, particularly the catalyst layers. The structural building blocks of catalyst layers are formed

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=pmid________::f3bd1229e906a5cfe2d633533c4c90fd
https://pubmed.ncbi.nlm.nih.gov/35495497

Super-Resolution of Large Volumes of Sentinel-2 Images with High Performance Distributed Deep Learning

Autor: Run Zhang, Jenia Jitsev, Gabriele Cavallaro

Publikováno v: IGARSS
617-620 (2020). doi:10.1109/IGARSS39084.2020.9323734
2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, Online event, Hawaii, 2020-09-26-2020-10-02
IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Online event, Online event, 2020-09-26-2020-10-02

This work proposes a novel distributed deep learning model for Remote Sensing (RS) images super-resolution. High Performance Computing (HPC) systems with GPUs are used to accelerate the learning of the unknown low to high resolution mapping from larg

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78a5ca6642c19e3b492ca0d76a91b011
https://doi.org/10.1109/igarss39084.2020.9323734

Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning

Autor: Marco Pleines, Jenia Jitsev, Mike Preuss, Frank Zimmer

Publikováno v: IEEE 447-454 (2020). doi:10.1109/CoG47356.2020.9231802
2020 IEEE Conference on Games (CoG) : [Proceedings]-IEEE, 2020
2020 IEEE Conference on Games (CoG) : [Proceedings]-IEEE, 20202020 IEEE Conference on Games (CoG), Osaka, Japan, 2020-08-24-2020-08-27
CoG

The Obstacle Tower Challenge is the task to master a procedurally generated chain of levels that subsequently get harder to complete. Whereas the most top performing entries of last year's competition used human demonstrations or reward shaping to le

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1db47f86a987e2db89eb848dbfd3c91d
http://arxiv.org/abs/2004.00567

Prediction of Acoustic Fields Using a Lattice-Boltzmann Method and Deep Learning

Autor: Jenia Jitsev, Seong-Ryong Koh, Andreas Lintermann, Mario Rüttgers, Wolfgang Schröder

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030598501
ISC Workshops
Cham : Springer, Lecture Notes in Computer Science 12321, 81-101 (2020). doi:10.1007/978-3-030-59851-8_6
High Performance Computing. ISC High Performance 2020. Lecture Notes in Computer Science
High Performance Computing. ISC High Performance 2020. Lecture Notes in Computer ScienceISC High Performance 2020, ISC 2020, Frankfurt, Germany, 2020-06-22-2020-06-25
High Performance Computing

Using traditional computational fluid dynamics and aeroacoustics methods, the accurate simulation of aeroacoustic sources requires high compute resources to resolve all necessary physical phenomena. In contrast, once trained, artificial neural networ

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33e7cc93e97c1996ae51420e6b7cfc30
https://doi.org/10.1007/978-3-030-59851-8_6