Compression and Speed-up of Convolutional Neural Networks Through Dimensionality Reduction for Efficient Inference on Embedded Multiprocessor

L. Fernandez-Brillet; N. Leclaire; Stéphane Mancini; M. Nicolas; S. Cleyet-Merle; J.P. Henriques; C. Delnondedieu

Journal articles

Compression and Speed-up of Convolutional Neural Networks Through Dimensionality Reduction for Efficient Inference on Embedded Multiprocessor

L. Fernandez-Brillet ^{1, 2} N. Leclaire ^{1, 2} Stéphane Mancini ² M. Nicolas ¹ S. Cleyet-Merle ¹ J.P. Henriques ¹ C. Delnondedieu ¹

1 ST-GRENOBLE - STMicroelectronics [Grenoble]

2 CDSI - Circuits, Devices and System Integration

TIMA - Techniques de l'Informatique et de la Microélectronique pour l'Architecture des systèmes intégrés

Document type :

Journal articles

Domain :

Computer Science [cs] / Signal and Image Processing

Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03115158
Contributor : Laurence BEN TITO Connect in order to contact the contributor
Submitted on : Tuesday, January 19, 2021 - 2:21:16 PM
Last modification on : Friday, April 1, 2022 - 3:44:04 AM

Compression and Speed-up of Convolutional Neural Networks Through Dimensionality Reduction for Efficient Inference on Embedded Multiprocessor

Licence

Identifiers

Collections

Citation

Export

Metrics

19

Compression and Speed-up of Convolutional Neural Networks Through Dimensionality Reduction for Efficient Inference on Embedded Multiprocessor

Licence

Identifiers

Collections

Citation

Export

Share

Metrics

19