Opendata, web and dolomites

ALOHA SIGNED

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

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "ALOHA" data sheet

The following table provides information about the project.

Coordinator
STMICROELECTRONICS SRL 

Organization address
address: VIA C.OLIVETTI 2
city: AGRATE BRIANZA
postcode: 20864
website: www.st.com

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Italy [IT]
 Project website https://www.aloha-h2020.eu/
 Total cost 5˙976˙415 €
 EC max contribution 5˙976˙415 € (100%)
 Programme 1. H2020-EU.2.1.1. (INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT))
 Code Call H2020-ICT-2017-1
 Funding Scheme RIA
 Starting year 2018
 Duration (year-month-day) from 2018-01-01   to  2020-12-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    STMICROELECTRONICS SRL IT (AGRATE BRIANZA) coordinator 879˙950.00
2    IBM ISRAEL - SCIENCE AND TECHNOLOGY LTD IL (PETACH TIKVA) participant 838˙675.00
3    UNIVERSITA DEGLI STUDI DI CAGLIARI IT (CAGLIARI) participant 631˙987.00
4    EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZUERICH CH (ZUERICH) participant 481˙250.00
5    SOFTWARE COMPETENCE CENTER HAGENBERG GMBH AT (HAGENBERG) participant 361˙333.00
6    SYSTHMATA YPOLOGISTIKIS ORASHS IRIDA LABS AE EL (RIO) participant 357˙500.00
7    UNIVERSITEIT VAN AMSTERDAM NL (AMSTERDAM) participant 352˙687.00
8    PKE HOLDING AG AT (WIEN) participant 322˙392.00
9    UNIVERSITEIT LEIDEN NL (LEIDEN) participant 321˙625.00
10    SANTER REPLY SPA IT (MILANO) participant 303˙991.00
11    MEDYMATCH TECHNOLOGY LTD IL (TEL AVIV) participant 301˙500.00
12    PLURIBUS ONE SRL IT (CAGLIARI) participant 250˙000.00
13    UNIVERSIDAD POMPEU FABRA ES (BARCELONA) participant 246˙312.00
14    UNIVERSITA DEGLI STUDI DI SASSARI IT (SASSARI) participant 217˙000.00
15    CA TECHNOLOGIES DEVELOPMENT SPAIN SA ES (CORNELLA DE LLOBREGAT BARCELONA) participant 110˙210.00

Map

 Project 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

 Deliverables

List of deliverables.
Report on tool flow integration Documents, reports 2020-01-14 15:01:00
Report on the exploitation activities Documents, reports 2020-01-14 15:01:15
Open Data Management Plan – First Update Open Research Data Pilot 2020-01-14 15:01:02
First release of the automated tool for application partitioning and mapping Demonstrators, pilots, prototypes 2020-01-14 15:01:14
Second progress and management report Documents, reports 2020-01-14 15:00:58
First release of the hardware abstraction layer utilities Demonstrators, pilots, prototypes 2020-01-14 15:01:15
Plan for the dissemination and communication - First Update Documents, reports 2020-01-14 15:01:16
Report on hardware abstraction layer techniques – Update Documents, reports 2020-01-14 15:01:17
Report on automated application partitioning and mapping – Update Documents, reports 2020-01-14 15:01:13
Dissemination and communication report Documents, reports 2020-01-14 15:00:58
Exploitation plan – First Update Documents, reports 2020-01-14 14:24:29
Report on automated algorithm configuration – Update Documents, reports 2020-01-14 15:02:05
First release of the automated algorithm configuration tool Demonstrators, pilots, prototypes 2020-01-14 15:01:14
Report on hardware abstraction layer techniques Documents, reports 2019-10-02 13:38:37
Project quality handbook Documents, reports 2019-10-02 13:38:37
Report on general specifications and interface definition Documents, reports 2019-10-02 13:38:37
Kick-off progress report Documents, reports 2019-10-02 13:38:37
Plan for the dissemination and communication Documents, reports 2019-10-02 13:38:37
Report on automated algorithm configuration Documents, reports 2019-10-02 13:38:37
First progress and management report Documents, reports 2019-10-02 13:38:37
Report on automated application partitioning and mapping Documents, reports 2019-10-02 13:38:37
Project digital presence Demonstrators, pilots, prototypes 2019-10-02 13:38:37
Open Data Management Plan Open Research Data Pilot 2019-10-02 13:38:37
Exploitation plan Documents, reports 2019-10-02 13:38:37

Take a look to the deliverables list in detail:  detailed list of ALOHA deliverables.

 Publications

year authors and title journal last update
List of publications.
2018 Battista Biggio, Fabio Roli
Wild patterns: Ten years after the rise of adversarial machine learning
published pages: 317-331, ISSN: 0031-3203, DOI: 10.1016/j.patcog.2018.07.023
Pattern Recognition 84 2019-10-02
2019 Lin Li, Carlo Sau, Tiziana Fanni, Jingui Li, Timo Viitanen, François Christophe, Francesca Palumbo, Luigi Raffo, Heikki Huttunen, Jarmo Takala, Shuvra S. Bhattacharyya
An integrated hardware/software design methodology for signal processing systems
published pages: 1-19, ISSN: 1383-7621, DOI: 10.1016/j.sysarc.2018.12.010
Journal of Systems Architecture 93 2019-10-02

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "ALOHA" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "ALOHA" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.2.1.1.)

MULTIPOINT (2019)

Multibeam Femtosecond Laser System for High Throughput Micro-drilling of HLFC Structures

Read More  

ACCORDION (2020)

Adaptive edge/cloud compute and network continuum over a heterogeneous sparse edge infrastructure to support nextgen applications

Read More  

CloudButton (2019)

Serverless Data Analytics Platform

Read More