Skip to main content

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

Objective

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

Field of science

  • /natural sciences/computer and information sciences/software/software development
  • /social sciences/sociology/industrial relations/automation
  • /natural sciences/computer and information sciences/software
  • /natural sciences/computer and information sciences/artificial intelligence
  • /natural sciences/computer and information sciences/artificial intelligence/machine learning/deep learning

Call for proposal

H2020-ICT-2017-1
See other projects for this call

Funding Scheme

RIA - Research and Innovation action

Coordinator

STMICROELECTRONICS SRL
Address
Via C.olivetti 2
20864 Agrate Brianza
Italy
Activity type
Private for-profit entities (excluding Higher or Secondary Education Establishments)
EU contribution
€ 879 950

Participants (14)

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

Participation ended

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