Report

Teaser, summary, work performed and final results

Periodic Reporting for period 1 - Bonseyes (Platform for Open Development of Systems of Artificial Intelligence)

Teaser

Artificial Intelligence is projected to add over €13 trillion to the global economy by 2030 but companies outside of the US and China risk being shut out by the ‘data wall’ dominated by internet giants. The goal of the Bonseyes project is to create an Artificial...

Summary

Artificial Intelligence is projected to add over €13 trillion to the global economy by 2030 but companies outside of the US and China risk being shut out by the ‘data wall’ dominated by internet giants. The goal of the Bonseyes project is to create an Artificial Intelligence Marketplace which will help European companies to get over the wall using the new power of edge computing and by leveraging Europe’s leadership in embedded systems.

Bonseyes will enable a platform for open development of systems of artificial intelligence which are emerging as a key growth driver in Smart CPS systems in the next decade. Opposed to monolithic system design methodologies currently used in closed end-to-end solutions, Bonseyes focuses on an open architecture and enables an eco-system of researchers and companies to collaborate in building highly complex distributed systems that are “intelligent”. Its objectives are to:
• Accelerate the design and programming of systems of artificial intelligence
• Reduce the complexity in training deep learning models for distributed embedded systems
• Foster “embedded intelligence” on low power and resource constrained Smart CPSs

Work performed

Major milestones were reached with the development and the ongoing evaluation of proof-of-concepts of the following key-components:
• Bonseyes Marketplace: repository allowing sharing and evaluation of deep learning artifacts (data, models, benchmarks)
• Deep Learning toolbox: a containerized, easy-to-use end-to-end training pipeline, including deployment functionality for the (embedded) target hardware
• Universal developer platform, ensuring efficiency and performance optimization for selected target platforms
• Identifying, building and preliminary demonstration of four challenging proof-of-concept scenarios in the medical, automotive, and consumer verticals.

Final results

• Reduction in development time by 50% compared to monolithic system design methods, through the reuse of data, meta data, and models among separate legal entities made possible by the Bonseyes AI Marketplace, a data marketplace that modularizes the AI systems’ development value-chain.
• Reduction in cost of ownership by a factor of 5 related to training of deep learning models comparing to current training approaches designed for the cloud.
o Deep learning training methods that enable models with near state-of-the-art accuracy that are tailored for embedded, constrained, distributed systems operating in real environments with noisy, sometimes missing data.
• Enabling distributed deep-learning, where part of the training can be achieved in embedded devices themselves, partially alleviating the need to transmit vast amounts of labelled data back to the cloud. This step is a key enabler for eventual unsupervised learning on mobile devices.
o Predictive tools that automate optimal deployment of a model on the target embedded system given a specific power/space/time constraint. Enabling low power “always-on” intelligence on edge devices.
o Low power universal reference developer platforms that are optimized for deep learning and support “always-on” intelligence paradigms.
• Data collection tools for IoT devices that are robust, scalable to a very large number of devices and maintain privacy and data isolation, while enabling real-time data processing on the “edge” device to identify when data is “abnormal”.
• Privacy and data isolation for deep learning methods that can be selected and adapted by the data providers or model owners.

Website & more info

More info: https://www.bonseyes.com.