Aloha project

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

Horizon 2020

This project is funded by the European Union’s Horizon 2020 programme, grant agreement No. 780788

Consortium

We are a team of 13 partners from 6 countries

Deep Learning (DL) algorithms are an extremely promising instrument in artificial intelligence. To foster their adoption in new applications and markets, a step forward is needed towards the implementation of DL inference on low-power embedded systems, enabling a shift to the edge computing paradigm. The main goal of ALOHA is to facilitate implementation of DL algorithms on heterogeneous low-energy computing platforms providing automation for optimal algorithm selection, resource allocation and deployment.

Architecture-awareness

The features of the architecture that will execute the inference are taken into account during the whole development process, starting from the early stages such as pre-training hyperparameter optimization and algorithm configuration.

Productivity

The tool flow implements support for agile development methodologies, to be easily adopted by SMEs and midcaps.

Adaptivity

The development process considers that the system should adapt to different operating modes at runtime.



Extensibility

The development process is conceived to support novel processing platforms to be exploitable beyond the end of the project.

Security

The development process automates the introduction of algorithm features and programming techniques improving the resilience of the system to attacks.


Parsimonious inference

In DL, good precision levels can be also obtained using algorithms with reduced complexity. All the optimization utilities in the ALOHA tool flow will consider the effects of algorithm simplification on precision, execution time, energy and power.

Latest News & Events

Deep Learning in Edge Computing Platforms. ALOHA tutorial at HIPEAC 2020. Registration available

The HiPEAC conference (High Performance and Embedded Architecture and Compilation) is a prestigious annual European forum for experts in computer architecture, programming models, compilers and operating systems for embedded and general-purpose systems. The HiPEAC 2020 conference will take place in Bologna, Italy (Polo congressuale).

The ALOHA consortium will held a tutorial during HiPEAC 2020, on January 21th, SALA AVORIO (from 2:00 p.m. to 5:30 p.m.). The tutorial is meant to offer an overview how to use the ALOHA framework and its different functionalities.

Read more...

 

Speech recognition in Smart Industry - Video demonstrator

The video presents the initial version of the smart industry demonstrator, where Deep Learning is used for speech recognition. Santer Reply, responsible for this this use case, realized, using the ALOHA toolflow, an embedded keyword spotting system to control a robot without relying on a cloud backend.

Video by Cristina Chesta, Santer Reply.

Read more...

ALOHA at SINNOVA 2019 (Cagliari - October 3-4)

SINNOVA is the most important Sardinian exhibition dedicated to innovation, organized every year in Cagliari (Italy). More than 150 exhibitors, among innovative ICT companies, universities, investors, present their products and the results of their research activities.

UNICA and Pluribus One presented their research activities and the goals of the ALOHA project at the 7thrd edition of SINNOVA (Cagliari, Italy, October 3-4, 2019).

Read more and see the pictures...

 

Contacts

Project Coordinator
Giuseppe Desoli - STMicroelectronics
giuseppe(dot)desoli(at)st(dot)com

Scientific Coordinator
Paolo Meloni - University of Cagliari, EOLAB
paolo(dot)meloni(at)diee(dot)unica(dot)it

Dissemination Manager
Francesca Palumbo - University of Sassari, IDEA Lab
fpalumbo(at)uniss(dot)it

Twitter

Linkedin