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
Fields of science
- natural sciencesphysical sciencesastronomyspace exploration
- natural sciencescomputer and information sciencesinternetinternet of things
- social sciencessociologyindustrial relationsautomation
- natural sciencescomputer and information sciencessoftwaresoftware development
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
Programme(s)
Topic(s)
Funding Scheme
RIA - Research and Innovation actionCoordinator
20864 Agrate Brianza
Italy
See on map
Participants (15)
09124 Cagliari
See on map
1012WX Amsterdam
See on map
2311 EZ Leiden
See on map
8092 Zuerich
See on map
07100 Sassari
See on map
1100 Wien
See on map
Participation ended
08940 Cornella De Llobregat Barcelona
Legal entity other than a subcontractor which is affiliated or legally linked to a participant. The entity carries out work under the conditions laid down in the Grant Agreement, supplies goods or provides services for the action, but did not sign the Grant Agreement. A third party abides by the rules applicable to its related participant under the Grant Agreement with regard to eligibility of costs and control of expenditure.
Participation ended
SL3 9LL Slough
4232 Hagenberg
See on map
20152 Milano
See on map
49527 Petach Tikva
See on map
26500 Rio
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
09128 Cagliari
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
6706701 Tel Aviv
See on map
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
08002 Barcelona
See on map