Archive

Matthieu ARZEL

Poste

Enseignant-chercheur

Département

Département Electronique

Localisation

Brest

Coordonnées :

Tél.

+33 2 29 00 13 11
Publications HAL
Communication dans un congrès
Libessart Erwan, Arzel Matthieu, Lahuec Cyril, Andriulli Francesco
40 Gop/S/mm² Fixed-Point Operators for Brain Computer Interface in 65nm CMOS
2018 IEEE International Symposium on Circuits and Systems (ISCAS), May 2018, Florence, Italy. 2018, 〈10.1109/ISCAS.2018.8351028〉
Bibtext :
@inproceedings{libessart:hal-01813164,
TITLE = {{40 Gop/S/mm${}^2$ Fixed-Point Operators for Brain Computer Interface in 65nm CMOS}},
AUTHOR = {Libessart, Erwan and Arzel, Matthieu and Lahuec, Cyril and Andriulli, Francesco},
URL = {https://hal.archives-ouvertes.fr/hal-01813164},
BOOKTITLE = {{ 2018 IEEE International Symposium on Circuits and Systems (ISCAS)}},
ADDRESS = {Florence, Italy},
HAL_LOCAL_REFERENCE = {18759},
PAGES = {.},
YEAR = {2018},
MONTH = May,
DOI = {10.1109/ISCAS.2018.8351028},
KEYWORDS = {BCI ; Fixed-Point Operators ; ASIC ; Reciprocal ; Inverse square root},
PDF = {https://hal.archives-ouvertes.fr/hal-01813164/file/iscas18.pdf},
HAL_ID = {hal-01813164},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T 40 Gop/S/mm² Fixed-Point Operators for Brain Computer Interface in 65nm CMOS
%+ Lab-STICC_IMTA_MOM_PIM
%+ Département Electronique (ELEC)
%+ Lab-STICC_IMTA_CACS_IAS
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%+ Département Micro-Ondes (MO)
%A Libessart, Erwan
%A Arzel, Matthieu
%A Lahuec, Cyril
%A Andriulli, Francesco
%< avec comité de lecture
%Z 18759
%B 2018 IEEE International Symposium on Circuits and Systems (ISCAS)
%C Florence, Italy
%P .
%8 2018-05-27
%D 2018
%R 10.1109/ISCAS.2018.8351028
%K BCI
%K Fixed-Point Operators
%K ASIC
%K Reciprocal
%K Inverse square root
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X The performance of non-invasive Brain-Computer Interface (BCI) depends on the computing performance of the system which solves the inverse problem. So the number of basic operations computed per second determines the BCI's resolution. An architecture with pipelined and parallelized flow is then required, and each operator in this architecture must be optimised to reach the highest possible computing performance. This paper presents the implementation of a fixed-point reciprocal and an inverse square root operators for the STMicroelectronics 65 nm CMOS technology. This paper follows previous works that optimise these operators on FPGA target. Each operator reaches a computing performance of about 40 Gop/s/mm², which improves the literature results by a factor of 5. Thus, this works fits well for portable and high performance BCI applications.
%G English
%2 https://hal.archives-ouvertes.fr/hal-01813164/document
%2 https://hal.archives-ouvertes.fr/hal-01813164/file/iscas18.pdf
%L hal-01813164
%U https://hal.archives-ouvertes.fr/hal-01813164
%~ INSTITUT-TELECOM
%~ TELECOM-BRETAGNE
%~ CNRS
%~ UNIV-UBS
%~ ENIB
%~ LAB-STICC
%~ UNIV-BREST
%~ LAB-STICC_IMTA_MOM_PIM
%~ IMTA_ELEC
%~ IMTA_MO
%~ LAB-STICC_IMTA_CACS_IAS
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA
Communication dans un congrès
Larras Benoît, Chollet Paul, Lahuec Cyril, Seguin Fabrice, Arzel Matthieu
A fully flexible circuit implementation of clique-based neural networks in 65-nm CMOS
ISCAS 2018 : IEEE International Symposium on Circuits and Systems (ISCAS), May 2018, Firenze, Italy. Proceedings ISCAS 2018 : IEEE International Symposium on Circuits and Systems (ISCAS), 2018, 〈10.1109/ISCAS.2018.8350954〉
Bibtext :
@inproceedings{larras:hal-01849349,
TITLE = {{A fully flexible circuit implementation of clique-based neural networks in 65-nm CMOS}},
AUTHOR = {Larras, Beno{\^i}t and Chollet, Paul and Lahuec, Cyril and Seguin, Fabrice and Arzel, Matthieu},
URL = {https://hal.archives-ouvertes.fr/hal-01849349},
BOOKTITLE = {{ISCAS 2018 : IEEE International Symposium on Circuits and Systems (ISCAS)}},
ADDRESS = {Firenze, Italy},
HAL_LOCAL_REFERENCE = {18608},
PAGES = {.},
YEAR = {2018},
MONTH = May,
DOI = {10.1109/ISCAS.2018.8350954},
KEYWORDS = {Analogue integrated circuit ; Neural Networks ; Energy effciency},
HAL_ID = {hal-01849349},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T A fully flexible circuit implementation of clique-based neural networks in 65-nm CMOS
%+ Institut supérieur de l'électronique et du nunérique (ISEN)
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%A Larras, Benoît
%A Chollet, Paul
%A Lahuec, Cyril
%A Seguin, Fabrice
%A Arzel, Matthieu
%< avec comité de lecture
%Z 18608
%( Proceedings ISCAS 2018 : IEEE International Symposium on Circuits and Systems (ISCAS)
%B ISCAS 2018 : IEEE International Symposium on Circuits and Systems (ISCAS)
%C Firenze, Italy
%P .
%8 2018-05-27
%D 2018
%R 10.1109/ISCAS.2018.8350954
%K Analogue integrated circuit
%K Neural Networks
%K Energy effciency
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Micro and nanotechnologies/Microelectronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X Clique-based neural networks implement low- complexity functions working with a reduced connectivity be- tween neurons. Thus, they address very specific applications operating with a very low energy budget. This paper proposes a flexible and iterative neural architecture able to implement multiple types of clique-based neural networks of up to 3968 neurons. The circuit has been integrated in a ST 65-nm CMOS ASIC and validated in the context of ECG classification. The network core reacts in 83ns to a stimulation and occupies a 0.21mm 2 silicon area.
%G English
%L hal-01849349
%U https://hal.archives-ouvertes.fr/hal-01849349
%~ INSTITUT-TELECOM
%~ TELECOM-BRETAGNE
%~ CNRS
%~ UNIV-UBS
%~ ENIB
%~ LAB-STICC
%~ UNIV-BREST
%~ IMT-ATLANTIQUE
%~ IMTA_ELEC
%~ LAB-STICC_IMTA_CACS_IAS
%~ LAB-STICC_IMTA
Communication dans un congrès
Boukli Hacene Ghouthi, Gripon Vincent, Farrugia Nicolas, Arzel Matthieu, Jezequel Michel
Incremental Learning on Chip
GlobalSIP 2017 : 5th IEEE Global Conference on Signal and Information Processing - Symposium on Signal Processing for Accelerating Deep Learning, Nov 2017, Montréal, Canada. Proceedings GlobalSIP 2017 : 5th IEEE Global Conference on Signal and Information Processing - Symposium on Signal Processing for Accelerating Deep Learning, 2017
Bibtext :
@inproceedings{bouklihacene:hal-01754847,
TITLE = {{Incremental Learning on Chip}},
AUTHOR = {Boukli Hacene, Ghouthi and Gripon, Vincent and Farrugia, Nicolas and Arzel, Matthieu and Jezequel, Michel},
URL = {https://hal.archives-ouvertes.fr/hal-01754847},
BOOKTITLE = {{GlobalSIP 2017 : 5th IEEE Global Conference on Signal and Information Processing - Symposium on Signal Processing for Accelerating Deep Learning}},
ADDRESS = {Montr{\'e}al, Canada},
HAL_LOCAL_REFERENCE = {18093},
PAGES = {.},
YEAR = {2017},
MONTH = Nov,
KEYWORDS = {Field programmable gate arrays ; Convolutional Neural Network ; Transfer Learning ; Incremental Learning ; Learning on Chip},
PDF = {https://hal.archives-ouvertes.fr/hal-01754847/file/GlobalSip_HAL.pdf},
HAL_ID = {hal-01754847},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Incremental Learning on Chip
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%A Boukli Hacene, Ghouthi
%A Gripon, Vincent
%A Farrugia, Nicolas
%A Arzel, Matthieu
%A Jezequel, Michel
%< avec comité de lecture
%Z 18093
%( Proceedings GlobalSIP 2017 : 5th IEEE Global Conference on Signal and Information Processing - Symposium on Signal Processing for Accelerating Deep Learning
%B GlobalSIP 2017 : 5th IEEE Global Conference on Signal and Information Processing - Symposium on Signal Processing for Accelerating Deep Learning
%C Montréal, Canada
%P .
%8 2017-11-14
%D 2017
%K Field programmable gate arrays
%K Convolutional Neural Network
%K Transfer Learning
%K Incremental Learning
%K Learning on Chip
%Z Computer Science [cs]/Machine Learning [cs.LG]
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X Learning on chip (LOC) is a challenging problem, which allows an embedded system to learn a model and use it to process and classify unknown data, adapting to new obser- vations or classes. Incremental learning of chip (ILOC) is more challenging. ILOC needs intensive computational power to train the model and adapt it when new data are observed, leading to a very difficult hardware implementation. We adress this issue by introducing a method based on the combination of a pre-trained Convolutional Neural Network (CNN) and majority vote, using Product Quantizing (PQ) as a bridge between them. We detail a hardware implementation of the proposed method validated on an FPGA target, with substantial processing acceleration with few hardware resources.
%G English
%2 https://hal.archives-ouvertes.fr/hal-01754847/document
%2 https://hal.archives-ouvertes.fr/hal-01754847/file/GlobalSip_HAL.pdf
%L hal-01754847
%U https://hal.archives-ouvertes.fr/hal-01754847
%~ INSTITUT-TELECOM
%~ TELECOM-BRETAGNE
%~ CNRS
%~ UNIV-UBS
%~ ENIB
%~ LAB-STICC
%~ UNIV-BREST
%~ LAB-STICC_IMTA_CACS_IAS
%~ IMTA_ELEC
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA
Communication dans un congrès
Gripon Vincent, Hacene Ghouthi Boukli, Farrugia Nicolas, Arzel Matthieu, Jezequel Michel
Incremental learning on chip
2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Nov 2017, Montreal, France. IEEE, 〈10.1109/GlobalSIP.2017.8309068〉
Bibtext :
@inproceedings{gripon:hal-01875912,
TITLE = {{Incremental learning on chip}},
AUTHOR = {Gripon, Vincent and Hacene, Ghouthi Boukli and Farrugia, Nicolas and Arzel, Matthieu and Jezequel, Michel},
URL = {https://hal.archives-ouvertes.fr/hal-01875912},
BOOKTITLE = {{2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)}},
ADDRESS = {Montreal, France},
PUBLISHER = {{IEEE}},
YEAR = {2017},
MONTH = Nov,
DOI = {10.1109/GlobalSIP.2017.8309068},
HAL_ID = {hal-01875912},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Paper
%F Oral
%T Incremental learning on chip
%+ Département Electronique (ELEC)
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Lab-STICC_TB_CACS_IAS
%A Gripon, Vincent
%A Hacene, Ghouthi Boukli
%A Farrugia, Nicolas
%A Arzel, Matthieu
%A Jezequel, Michel
%< avec comité de lecture
%B 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
%C Montreal, France
%I IEEE
%8 2017-11-14
%D 2017
%R 10.1109/GlobalSIP.2017.8309068
%Z Computer Science [cs]/Machine Learning [cs.LG]
%Z Computer Science [cs]/Artificial Intelligence [cs.AI]
%Z Computer Science [cs]/Signal and Image Processing
%Z Computer Science [cs]/Computer Science and Game Theory [cs.GT]Conference papers
%G English
%L hal-01875912
%U https://hal.archives-ouvertes.fr/hal-01875912
%~ CNRS
%~ UNIV-BREST
%~ UNIV-UBS
%~ INSTITUT-TELECOM
%~ ENIB
%~ LAB-STICC
%~ LAB-STICC_TB
%~ IMT-ATLANTIQUE
%~ IMTA_ELEC
%~ LAB-STICC_IMTA_CACS_IAS
Communication dans un congrès
Cornevaux-Juignet Franck, Arzel Matthieu, Horrein Pierre-Henri, Groleat Tristan, Person Christian
Open-source flexible packet parser for high data rate agile network probe
CNS 2017 : IEEE Conference on Communications and Network Security, Oct 2017, Las Vegas, États-Unis. Actes CNS 2017 : IEEE Conference on Communications and Network Security, 2017
Bibtext :
@inproceedings{cornevauxjuignet:hal-01740903,
TITLE = {{Open-source flexible packet parser for high data rate agile network probe}},
AUTHOR = {Cornevaux-Juignet, Franck and Arzel, Matthieu and Horrein, Pierre-Henri and Groleat, Tristan and Person, Christian},
URL = {https://hal.archives-ouvertes.fr/hal-01740903},
BOOKTITLE = {{CNS 2017 : IEEE Conference on Communications and Network Security}},
ADDRESS = {Las Vegas, United States},
HAL_LOCAL_REFERENCE = {18101},
PAGES = {.},
YEAR = {2017},
MONTH = Oct,
PDF = {https://hal.archives-ouvertes.fr/hal-01740903/file/ieee_cns_2017_workshop_pub.pdf},
HAL_ID = {hal-01740903},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Open-source flexible packet parser for high data rate agile network probe
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%+ OVH (Entreprise) (OVH)
%+ Lab-STICC_IMTA_MOM_DIM
%+ Direction de le Recherche et de l'Innovation (DRI)
%A Cornevaux-Juignet, Franck
%A Arzel, Matthieu
%A Horrein, Pierre-Henri
%A Groleat, Tristan
%A Person, Christian
%< avec comité de lecture
%Z 18101
%( Actes CNS 2017 : IEEE Conference on Communications and Network Security
%B CNS 2017 : IEEE Conference on Communications and Network Security
%C Las Vegas, United States
%P .
%8 2017-10-09
%D 2017
%Z Computer Science [cs]/Cryptography and Security [cs.CR]
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X The development of a network centered life has increased overall data rates in core networks. Thus, data centers face the challenge to provide always more services at higher data rates while reacting quickly to complex failures and more powerful attacks thanks to efficient network forensics. Moreover, Software-Defined Networking (SDN) becomes a standard which offers agility but also requires forensic devices able to handle multiple configurations. Although conventional software probes are programmable and thus agile, they cannot support high data rate packet processing any more. Probes could benefit from Application Specific Integrated Circuits (ASIC) to cope with high data rates, but ASICs development time of many months makes them unable to satisfy agility requirements. With reconfiguration ability and high throughput processing without packet loss, Field Programmable Gate Arrays (FPGA) are the key technology chosen by some companies, such as Microsoft, Amazon and OVH, to be integrated into smart Network Interface Cards (NIC). Nevertheless, while high performance criteria is fulfilled, current FPGA probes benefit from an agility still limited to their conventional firmware upgrades which require proprietary tools and hardware-design time and knowledge. This paper proposes the first solution to offer FPGA probes with runtime agility thanks to a flexible packet parser which can be parameterized continuously by a software, endorsing complex tasks and SDN control. This allows a live adaptation of protocol processings from computer host alongside handling packets at line rate without data loss. The proposed parser is open-source and easily usable by network engineers through a Python software API. Benchmark results illustrate the performance of the agile high-level probe implemented on a NetFPGA SUME board, with XC7VX690T FPGA. 60 millions of 64-byte packets are counted based on features provided at runtime. These are selected by the software part, allowing the detection of different volumetric attacks within a few tens of microseconds. This represents a 40 Gb/s traffic of smallest Ethernet packets with no packet loss. With adequate boards, the generic design of the probe offers 160 Gb/s data rates and beyond on modern hardware, assuring probe scalability.
%G French
%2 https://hal.archives-ouvertes.fr/hal-01740903/document
%2 https://hal.archives-ouvertes.fr/hal-01740903/file/ieee_cns_2017_workshop_pub.pdf
%L hal-01740903
%U https://hal.archives-ouvertes.fr/hal-01740903
%~ TELECOM-BRETAGNE
%~ INSTITUT-TELECOM
%~ LAB-STICC_IMTA_CACS_IAS
%~ IMTA_ELEC
%~ LAB-STICC_IMTA_MOM_DIM
%~ LAB-STICC
%~ UNIV-UBS
%~ CNRS
%~ UNIV-BREST
%~ ENIB
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA
Communication dans un congrès
Cornevaux-Juignet Franck, Arzel Matthieu, Horrein Pierre-Henri, Groleat Tristan, Person Christian
Combining FPGAs and processors for high-throughput forensics
CNS 2017 : IEEE Conference on Communications and Network Security, Oct 2017, Las Vegas, États-Unis. IEEE, 2017
Bibtext :
@inproceedings{cornevauxjuignet:hal-01742964,
TITLE = {{Combining FPGAs and processors for high-throughput forensics}},
AUTHOR = {Cornevaux-Juignet, Franck and Arzel, Matthieu and Horrein, Pierre-Henri and Groleat, Tristan and Person, Christian},
URL = {https://hal.archives-ouvertes.fr/hal-01742964},
BOOKTITLE = {{CNS 2017 : IEEE Conference on Communications and Network Security}},
ADDRESS = {Las Vegas, United States},
HAL_LOCAL_REFERENCE = {18100},
PUBLISHER = {{IEEE}},
PAGES = {.},
YEAR = {2017},
MONTH = Oct,
PDF = {https://hal.archives-ouvertes.fr/hal-01742964/file/ieee_cns_2017_poster_sub.pdf},
HAL_ID = {hal-01742964},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Combining FPGAs and processors for high-throughput forensics
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%+ OVH (Entreprise) (OVH)
%+ Lab-STICC_IMTA_MOM_DIM
%+ Direction de le Recherche et de l'Innovation (DRI)
%A Cornevaux-Juignet, Franck
%A Arzel, Matthieu
%A Horrein, Pierre-Henri
%A Groleat, Tristan
%A Person, Christian
%< avec comité de lecture
%Z 18100
%B CNS 2017 : IEEE Conference on Communications and Network Security
%C Las Vegas, United States
%I IEEE
%P .
%8 2017-10-09
%D 2017
%Z Computer Science [cs]/Cryptography and Security [cs.CR]
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X Data centers availability is mandatory and is conditioned by a quick response to failures and attacks thanks to efficient live forensics. However, this task is lately impossible to complete with classic systems because of encountered data rates and service diversity. Moreover, Software-Defined Networking (SDN) devices agility requirements prevent the use of Application Specific Integrated Circuits (ASIC) solutions due to long development time. New solutions of smart Network Interface Cards (NIC) with embedded Field Programmable Gate Arrays (FPGA) are considered, as in Microsoft Azure solution. FPGAs ensure high throughput processings without packet loss to offload CPU processing, but their configurations support only sparse firmware upgrades and shut down processings. This paper proposes an hybrid architecture to realize agile high performance traffic forensics. This work combines hardware performance, high throughput, and software high flexibility to achieve data rates beyond 40 Gb/s while being configurable at runtime through parameters. A software API allows a user-friendly configuration without stopping processings. The implementation of a flexible packet parser, first block of the packet processing chain, demonstrates the viability of the concept.
%G French
%2 https://hal.archives-ouvertes.fr/hal-01742964/document
%2 https://hal.archives-ouvertes.fr/hal-01742964/file/ieee_cns_2017_poster_sub.pdf
%L hal-01742964
%U https://hal.archives-ouvertes.fr/hal-01742964
%~ TELECOM-BRETAGNE
%~ INSTITUT-TELECOM
%~ CNRS
%~ UNIV-UBS
%~ ENIB
%~ LAB-STICC
%~ UNIV-BREST
%~ LAB-STICC_IMTA_CACS_IAS
%~ LAB-STICC_IMTA_MOM_DIM
%~ IMTA_ELEC
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA
Communication dans un congrès
Boukli Hacene Ghouthi, Gripon Vincent, Farrugia Nicolas, Arzel Matthieu, Jezequel Michel
Budget Restricted Incremental Learning with Pre-Trained Convolutional Neural Networks and Binary Associative Memories
SIPS 2017 : IEEE International Workshop on Signal Processing Systems, Oct 2017, Lorient, France. Proceedings SIPS 2017 : IEEE International Workshop on Signal Processing Systems, pp.1 - 4, 2017, 〈10.1109/SiPS.2017.8109978〉
Bibtext :
@inproceedings{bouklihacene:hal-01656152,
TITLE = {{Budget Restricted Incremental Learning with Pre-Trained Convolutional Neural Networks and Binary Associative Memories}},
AUTHOR = {Boukli Hacene, Ghouthi and Gripon, Vincent and Farrugia, Nicolas and Arzel, Matthieu and Jezequel, Michel},
URL = {https://hal.archives-ouvertes.fr/hal-01656152},
BOOKTITLE = {{SIPS 2017 : IEEE International Workshop on Signal Processing Systems}},
ADDRESS = {Lorient, France},
HAL_LOCAL_REFERENCE = {18094},
PAGES = {1 - 4},
YEAR = {2017},
MONTH = Oct,
DOI = {10.1109/SiPS.2017.8109978},
KEYWORDS = {Incremental Learning ; Transfer Learning ; Convolutionnal Neural Neworks ; Associative memory},
PDF = {https://hal.archives-ouvertes.fr/hal-01656152/file/SIPS.pdf},
HAL_ID = {hal-01656152},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Budget Restricted Incremental Learning with Pre-Trained Convolutional Neural Networks and Binary Associative Memories
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%A Boukli Hacene, Ghouthi
%A Gripon, Vincent
%A Farrugia, Nicolas
%A Arzel, Matthieu
%A Jezequel, Michel
%< avec comité de lecture
%Z 18094
%( Proceedings SIPS 2017 : IEEE International Workshop on Signal Processing Systems
%B SIPS 2017 : IEEE International Workshop on Signal Processing Systems
%C Lorient, France
%P 1 - 4
%8 2017-10-03
%D 2017
%R 10.1109/SiPS.2017.8109978
%K Incremental Learning
%K Transfer Learning
%K Convolutionnal Neural Neworks
%K Associative memory
%Z Computer Science [cs]/Machine Learning [cs.LG]
%Z Computer Science [cs]/Signal and Image Processing
%Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X Thanks to their ability to absorb large amounts of data, Convolutional Neural NetThanks to their ability to absorb large amounts of data, Convolutional Neural Networks (CNNs) have become state- of-the-art in numerous vision challenges, sometimes even on par with biological vision. They rely on optimization routines that typically require intensive computational power, thus the question of embedded architectures is a very active field of research. Of particular interest is the problem of incremental learning, where the device adapts to new observations or classes. To tackle this challenging problem, we propose to combine pre-trained CNNs with binary associative memories, using product random sampling as an intermediate between the two methods. The obtained architecture requires significantly less computational power and memory usage than existing counterparts. Moreover, using various challenging vision datasets we show that the proposed architecture is able to perform one-shot learning - and even use only a small portion of the dataset - while keeping very good accuracy.works (CNNs) have become state- of-the-art in numerous vision challenges, sometimes even on par with biological vision. They rely on optimisation routines that typically require intensive computational power, thus the question of embedded architectures is a very active field of research. Of particular interest is the problem of incremental learning, where the device adapts to new observations or classes. To tackle this challenging problem, we propose to combine pre-trained CNNs with binary associative memories, using product random sampling as an intermediate between the two methods. The obtained architecture requires significantly less computational power and memory usage than existing counterparts. Moreover, using various challenging vision datasets we show that the proposed architecture is able to perform one-shot learning - and even use only a small portion of the dataset - while keeping very good accuracy.
%G English
%2 https://hal.archives-ouvertes.fr/hal-01656152/document
%2 https://hal.archives-ouvertes.fr/hal-01656152/file/SIPS.pdf
%L hal-01656152
%U https://hal.archives-ouvertes.fr/hal-01656152
%~ UNIV-BREST
%~ LAB-STICC_IMTA
%~ IMTA_ELEC
%~ LAB-STICC_IMTA_CACS_IAS
%~ LAB-STICC
%~ ENIB
%~ TELECOM-BRETAGNE
%~ UNIV-UBS
%~ CNRS
%~ INSTITUT-TELECOM
%~ IMT-ATLANTIQUE
Communication dans un congrès
Morvan Michel, Vinouze Bruno, Adam Marie-Pierre, Creach Priscillia, Arzel Matthieu, Baux Didier, Beugnard Antoine, Coupez Jean-Philippe, Le Goff-Pronost Myriam, Kärnfelt Camilla
How to apprehend leadership related skills in a project management experiment?
SEFI 2017 : 45th Conference on Education Excellence For Sustainable Development, Sep 2017, Azores, Portugal. Proceedings SEFI 2017 : 45th Conference on Education Excellence For Sustainable Development, pp.536 - 543, 2017
Bibtext :
@inproceedings{morvan:hal-01661642,
TITLE = {{How to apprehend leadership related skills in a project management experiment?}},
AUTHOR = {Morvan, Michel and Vinouze, Bruno and Adam, Marie-Pierre and Creach, Priscillia and Arzel, Matthieu and BAUX, Didier and Beugnard, Antoine and Coupez, Jean-Philippe and LE GOFF-PRONOST, Myriam and K{\"a}rnfelt, Camilla},
URL = {https://hal.archives-ouvertes.fr/hal-01661642},
BOOKTITLE = {{SEFI 2017 : 45th Conference on Education Excellence For Sustainable Development}},
ADDRESS = {Azores, Portugal},
HAL_LOCAL_REFERENCE = {18319},
PAGES = {536 - 543},
YEAR = {2017},
MONTH = Sep,
KEYWORDS = {Leadership ; Project management ; Return of experience},
HAL_ID = {hal-01661642},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T How to apprehend leadership related skills in a project management experiment?
%+ Lab-STICC_IMTA_MOM_DIM
%+ Département Optique (OPT)
%+ Direction du développement et des relations entreprises (DEVRE)
%+ Direction de la communication (DIRCOM)
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%+ Didier Baux Communication (Entreprise)
%+ Process for Adaptative Software Systems (PASS)
%+ Département Informatique (INFO)
%+ Département Micro-Ondes (MO)
%+ Département Logique des Usages, Sciences sociales et Sciences de l'Information (LUSSI)
%A Morvan, Michel
%A Vinouze, Bruno
%A Adam, Marie-Pierre
%A Creach, Priscillia
%A Arzel, Matthieu
%A BAUX, Didier
%A Beugnard, Antoine
%A Coupez, Jean-Philippe
%A LE GOFF-PRONOST, Myriam
%A Kärnfelt, Camilla
%< avec comité de lecture
%Z 18319
%( Proceedings SEFI 2017 : 45th Conference on Education Excellence For Sustainable Development
%B SEFI 2017 : 45th Conference on Education Excellence For Sustainable Development
%C Azores, Portugal
%P 536 - 543
%8 2017-09-18
%D 2017
%K Leadership
%K Project management
%K Return of experience
%Z Computer Science [cs]/Human-Computer Interaction [cs.HC]
%Z Computer Science [cs]/Computers and Society [cs.CY]
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]
%Z Humanities and Social Sciences/Education
%Z Humanities and Social Sciences/Business administration
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Optics / Photonic
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X The ambition of our engineering school is to train competitive engineers who are able to manage complex projects in fast-changing environments. To this end, we have developed a project based course, controlled by teachers (Steering Committee), where students are confronted with a practical long term assignment which includes unexpected events. Over the six years of experience gained in running the course, the important question of leadership has emerged, even though it was not an a priori explicit objective of the course. In a large group, if responsibilities can be relatively easily identified and assigned, the group dynamic often relies on the presence of one or several leaders. The Steering Committee puts pressure on the student groups to highlight the capacities of the leader(s) and those around him/her/them. The bounds of the exercise are established by the natural peer-to-peer relationships between fellow students in each year group. Even if the project does not run well, even if the project leader makes mistakes, leadership skills are understood by the whole group and students still acquire skills. We debrief with the students in order to relativize the success of their production in relation to the organization of the group. Different leadership situations are analysed and discussed in this paper.
%G English
%L hal-01661642
%U https://hal.archives-ouvertes.fr/hal-01661642
%~ INSTITUT-TELECOM
%~ TELECOM-BRETAGNE
%~ TICE
%~ CNRS
%~ UNIV-UBS
%~ IRISA_SET
%~ ENIB
%~ TDS-MACS
%~ LAB-STICC
%~ UNIV-RENNES1
%~ INRIA
%~ UR1-HAL
%~ UNIV-BREST
%~ IRISA
%~ INRIA2017
%~ SHS
%~ UR1-MATH-STIC
%~ UR1-UFR-ISTIC
%~ TEST-UNIV-RENNES
%~ TEST-UR-CSS
%~ LAB-STICC_IMTA_CACS_IAS
%~ LAB-STICC_IMTA_MOM_DIM
%~ IMTA_ELEC
%~ IMTA_INFO
%~ IMTA_LUSSI
%~ IMTA_MO
%~ IMTA_OPT
%~ IRISA-PASS-IMTA
%~ UNIV-RENNES
%~ CENTRALESUPELEC
%~ INRIA-AUT
%~ IMT-ATLANTIQUE
%~ IRISA_IMTA
%~ LAB-STICC_IMTA
Communication dans un congrès
Libessart Erwan, Arzel Matthieu, Lahuec Cyril, Andriulli Francesco
Implantation en virgule fixe d'un opérateur de calcul d'inverse à base de Newton-Raphson, sans normalisation et sans bloc mémoire
GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images, Sep 2017, Juan-Les-Pins, France. Actes GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images, 2017
Bibtext :
@inproceedings{libessart:hal-01630144,
TITLE = {{Implantation en virgule fixe d'un op{\'e}rateur de calcul d'inverse {\`a} base de Newton-Raphson, sans normalisation et sans bloc m{\'e}moire}},
AUTHOR = {Libessart, Erwan and Arzel, Matthieu and Lahuec, Cyril and Andriulli, Francesco},
URL = {https://hal.archives-ouvertes.fr/hal-01630144},
BOOKTITLE = {{GRETSI 2017 : 26{\`e}me colloque du Groupement de Recherche en Traitement du Signal et des Images}},
ADDRESS = {Juan-Les-Pins, France},
HAL_LOCAL_REFERENCE = {18096},
PAGES = {.},
YEAR = {2017},
MONTH = Sep,
HAL_ID = {hal-01630144},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Implantation en virgule fixe d'un opérateur de calcul d'inverse à base de Newton-Raphson, sans normalisation et sans bloc mémoire
%+ Lab-STICC_IMTA_MOM_PIM
%+ Département Electronique (ELEC)
%+ Lab-STICC_IMTA_CACS_IAS
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%+ Département Micro-Ondes (MO)
%A Libessart, Erwan
%A Arzel, Matthieu
%A Lahuec, Cyril
%A Andriulli, Francesco
%< avec comité de lecture
%Z 18096
%( Actes GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images
%B GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images
%C Juan-Les-Pins, France
%P .
%8 2017-09-05
%D 2017
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X La division est une opération courante dans le domaine du traitement du signal. Dans le cas de l'implantation matérielle, il est préférable de calculer dans un premier temps l'inverse du diviseur, puis de multiplier ce résultat au dividende. L'algorithme de Newton-Raphson peut être utilisé pour calculer cet inverse, que ce soit en représentation flottante ou fixe. Ce papier propose une implantation en virgule fixe d'un opérateur de calcul d'inverse utilisant l'algorithme de Newton-Raphson. Cette implantation se démarque par l'absence de blocs mémoire et d'une normalisation des entrées et cherche à maximiser le débit sur FPGA.
%G French
%L hal-01630144
%U https://hal.archives-ouvertes.fr/hal-01630144
%~ INSTITUT-TELECOM
%~ TELECOM-BRETAGNE
%~ CNRS
%~ UNIV-UBS
%~ ENIB
%~ LAB-STICC
%~ UNIV-BREST
%~ IMTA_ELEC
%~ IMTA_MO
%~ LAB-STICC_IMTA_MOM_PIM
%~ LAB-STICC_IMTA_CACS_IAS
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA
Communication dans un congrès
Haroun Ali, Abdel Nour Charbel, Arzel Matthieu, Jego Christophe
Architecture de détecteur MIMO-BP itératif associé à un décodeur LDPC non binaire
GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images, Sep 2017, Juan Les Pins, France. Actes GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images, 2017
Bibtext :
@inproceedings{haroun:hal-01617324,
TITLE = {{Architecture de d{\'e}tecteur MIMO-BP it{\'e}ratif associ{\'e} {\`a} un d{\'e}codeur LDPC non binaire}},
AUTHOR = {Haroun, Ali and ABDEL NOUR, Charbel and Arzel, Matthieu and Jego, Christophe},
URL = {https://hal.archives-ouvertes.fr/hal-01617324},
BOOKTITLE = {{GRETSI 2017 : 26{\`e}me colloque du Groupement de Recherche en Traitement du Signal et des Images}},
ADDRESS = {Juan Les Pins, France},
HAL_LOCAL_REFERENCE = {17964},
PAGES = {.},
YEAR = {2017},
MONTH = Sep,
KEYWORDS = {MIMO ; LDPC non-binaires ; Architecture de d{\'e}codage},
HAL_ID = {hal-01617324},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Architecture de détecteur MIMO-BP itératif associé à un décodeur LDPC non binaire
%+ École Nationale Supérieure d’Électronique, Informatique, Télécommunications, MATMECA de Bordeaux (Institut Polytechnique de Bordeaux (INP Bordeaux)) (ENSEIRB-MATMECA)
%+ Laboratoire de l'intégration, du matériau au système (IMS)
%+ Lab-STICC_IMTA_CACS_IAS
%+ Département Electronique (ELEC)
%+ Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC)
%A Haroun, Ali
%A ABDEL NOUR, Charbel
%A Arzel, Matthieu
%A Jego, Christophe
%< avec comité de lecture
%Z 17964
%( Actes GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images
%B GRETSI 2017 : 26ème colloque du Groupement de Recherche en Traitement du Signal et des Images
%C Juan Les Pins, France
%P .
%8 2017-09-05
%D 2017
%K MIMO
%K LDPC non-binaires
%K Architecture de décodage
%Z Computer Science [cs]/Information Theory [cs.IT]
%Z Engineering Sciences [physics]/Electronics
%Z Engineering Sciences [physics]/Signal and Image processingConference papers
%X Cet article présente une nouvelle architecture pour la détection souple itérative multi-antennes basée sur l'algorithme de propagation de croyance. Cette architecture correspond à une détection simplifiée basée sur les techniques détaillées dans [1]. A l'aide de cette architecture, nous pouvons calculer le rapport de vraisemblance du point initial d'une constellation en considérant la méthode de sous-régions dynamiques [1]. Ainsi, tous les points voisins du point détecté peuvent être obtenus à l'aide d'un calcul récursif. Grâce à un niveau approprié de parallélisme, l'architecture associée au détecteur souple permet des échanges d'information efficaces. Par conséquent, il favorise un bon compromis entre les performances au niveau taux d'erreurs binaires et la complexité calculatoire.
%G French
%L hal-01617324
%U https://hal.archives-ouvertes.fr/hal-01617324
%~ INSTITUT-TELECOM
%~ TELECOM-BRETAGNE
%~ CNRS
%~ UNIV-UBS
%~ ENIB
%~ IMS-BORDEAUX-FUSION
%~ IMS-BORDEAUX
%~ LAB-STICC
%~ UNIV-BREST
%~ LAB-STICC_IMTA_CACS_IAS
%~ IMTA_ELEC
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA
Voir toutes les publications