Skip to main content

software framework for runtime-Adaptive and secure deep Learning On Heterogeneous Architectures

Ziel

Deep Learning (DL) algorithms are an extremely promising instrument in artificial intelligence, achieving very high performance in numerous recognition, identification, and classification tasks. To foster their pervasive adoption in a vast scope of new applications and markets, a step forward is needed towards the implementation of the on-line classification task (called inference) on low-power embedded systems, enabling a shift to the edge computing paradigm. Nevertheless, when DL is moved at the edge, severe performance requirements must coexist with tight constraints in terms of power/energy consumption, posing the need for parallel and energy-efficient heterogeneous computing platforms. Unfortunately, programming for this kind of architectures requires advanced skills and significant effort, also considering that DL algorithms are designed to improve precision, without considering the limitations of the device that will execute the inference. Thus, the deployment of DL algorithms on heterogeneous architectures is often unaffordable for SMEs and midcaps without adequate support from software development tools.
The main goal of ALOHA is to facilitate implementation of DL on heterogeneous low-energy computing platforms. To this aim, the project will develop a software development tool flow, automating:
• algorithm design and analysis;
• porting of the inference tasks to heterogeneous embedded architectures, with optimized mapping and scheduling;
• implementation of middleware and primitives controlling the target platform, to optimize power and energy savings.
During the development of the ALOHA tool flow, several main features will be addressed, such as architecture-awareness (the features of the embedded architecture will be considered starting from the algorithm design), adaptivity, security, productivity, and extensibility.
ALOHA will be assessed over three different use-cases, involving surveillance, smart industry automation, and medical application domains

Wissenschaftliches Gebiet

  • /Naturwissenschaften/Informatik und Informationswissenschaften/Software/Softwareentwicklung
  • /Naturwissenschaften/Naturwissenschaften/Astronomie/Weltraumerkundung
  • /Naturwissenschaften/Informatik und Informationswissenschaften/künstliche Intelligenz/maschinelles Lernen/Deep Learning

Aufforderung zur Vorschlagseinreichung

H2020-ICT-2017-1
Andere Projekte für diesen Aufruf anzeigen

Finanzierungsplan

RIA - Research and Innovation action

Koordinator

STMICROELECTRONICS SRL
Adresse
Via C.olivetti 2
20864 Agrate Brianza
Italien
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
EU-Beitrag
€ 879 950

Beteiligte (14)

UNIVERSITA DEGLI STUDI DI CAGLIARI
Italien
EU-Beitrag
€ 631 987,29
Adresse
Via Universita 40
09124 Cagliari
Aktivitätstyp
Higher or Secondary Education Establishments
UNIVERSITEIT VAN AMSTERDAM
Niederlande
EU-Beitrag
€ 352 687,50
Adresse
Spui 21
1012WX Amsterdam
Aktivitätstyp
Higher or Secondary Education Establishments
UNIVERSITEIT LEIDEN
Niederlande
EU-Beitrag
€ 321 625
Adresse
Rapenburg 70
2311 EZ Leiden
Aktivitätstyp
Higher or Secondary Education Establishments
EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZUERICH
Schweiz
EU-Beitrag
€ 481 250
Adresse
Raemistrasse 101
8092 Zuerich
Aktivitätstyp
Higher or Secondary Education Establishments
UNIVERSITA DEGLI STUDI DI SASSARI
Italien
EU-Beitrag
€ 217 000
Adresse
Piazza Universita 21
07100 Sassari
Aktivitätstyp
Higher or Secondary Education Establishments
PKE HOLDING AG
Österreich
EU-Beitrag
€ 322 392,50
Adresse
Computerstrasse 6
1100 Wien
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
CA TECHNOLOGIES DEVELOPMENT SPAIN SA

Beteiligung beendet

Spanien
EU-Beitrag
€ 110 210,63
Adresse
Plaza De La Pau Sn Wtc Alameda Park Edificio 2 Planta 4
08940 Cornella De Llobregat Barcelona
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
SOFTWARE COMPETENCE CENTER HAGENBERG GMBH
Österreich
EU-Beitrag
€ 361 333,33
Adresse
Softwarepark 21
4232 Hagenberg
Aktivitätstyp
Other
SANTER REPLY SPA
Italien
EU-Beitrag
€ 303 991,25
Adresse
Via Robert Koch 1/4
20152 Milano
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
IBM ISRAEL - SCIENCE AND TECHNOLOGY LTD
Israel
EU-Beitrag
€ 838 675
Adresse
94 Derech Em-hamoshavot
49527 Petach Tikva
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
SYSTHMATA YPOLOGISTIKIS ORASHS IRIDA LABS AE
Greece
EU-Beitrag
€ 357 500
Adresse
Magoula
26500 Rio
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
PLURIBUS ONE SRL
Italien
EU-Beitrag
€ 250 000
Adresse
Via Vincenzo Bellini 9
09128 Cagliari
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
MEDYMATCH TECHNOLOGY LTD
Israel
EU-Beitrag
€ 301 500
Adresse
Alon Yigal 76
6706701 Tel Aviv
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
UNIVERSIDAD POMPEU FABRA
Spanien
EU-Beitrag
€ 246 312,50
Adresse
Placa De La Merce, 10-12
08002 Barcelona
Aktivitätstyp
Higher or Secondary Education Establishments