Contributo in atti di convegno, 2019, ENG, 10.1109/PDP.2019.00055
V. Giansanti, S. Beretta, D. Cesini, D. D'Agostino, and I. Merelli
CNR-ITB, CNR-ITB, CNAF-INFN, CNR-IMATI, CNR-ITB
In the last two decades deep learning has attracted a lot of attention internationally, solving problems in different application domains and achieving results beyond expectations. For example it has been applied in bioinformatics, game playing, imaging processing, object detection, robotic and drug discovery. One of the main reasons for the incremented use of deep learning algorithms is the need to implement approaches for the analysis of the large amount of data produces in every field, bringing researchers to dedicate their work to deep learning development. One of the main topics discussed up today is the possibility to run the training of deep models in a parallel fashion, so to reduce the time otherwise needed to find the hyperparameters and to make the achievement of the result faster.
27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 329–333, Pavia (Italy), 13-15/02/2019
deep learning, bioinformatic, parallel computing
Beretta Stefano, Giansanti Valentina, D Agostino Daniele, Merelli Ivan
IMATI – Istituto di matematica applicata e tecnologie informatiche "Enrico Magenes", ITB – Istituto di tecnologie biomediche
ID: 399801
Year: 2019
Type: Contributo in atti di convegno
Creation: 2019-02-13 14:36:05.000
Last update: 2019-09-05 12:00:51.000
External IDs
CNR OAI-PMH: oai:it.cnr:prodotti:399801
DOI: 10.1109/PDP.2019.00055
ISI Web of Science (WOS): 000467257000046