MANOLO will deliver a complete stack of trustworthy algorithms and tools to help AI systems reach better efficiency and seamless optimization in their operations, resources and data required to train, deploy and run high-quality and lighter AI models in both centralised and cloud-edge distributed environments. It will push the state of the art in the development of a collection of complementary algorithms for training, understanding, compressing and optimising machine learning models by advancing research in the areas of: model compression, meta-learning (few-shot learning), domain adaptation, frugal neural network search and growth and neuromorphic models. Novel dynamic algorithms for data/energy efficient and policy-compliance allocation of AI tasks to assets and resources in the cloud-edge continuum will be designed, allowing for trustworthy widespread deployment.
To support these activities a data management framework for distributed tracking of assets and their provenance (data, models, algorithms) and a benchmark system to monitor, evaluate and compare new AI algorithms and model deployments will be developed. Trustworthiness evaluation mechanisms will be embedded at its core for explainability, robustness and security of models while using the Z-Inspection methodology for TrustworthyAI assesment, helping AI systems conform to the new AI Act regulation.
MANOLO will be deployed as a toolset and tested in lab environments via Use Cases with different distributed AI paradigms within cloud-edge continuum settings; it will be validated in verticals such as health, manufacturing, and telecommunications aligned with ADRA identified market opportunities, and with a granular set of embedded devices covering robotics, smartphones, IoT as well as using Neuromorphic chips. MANOLO will integrate with ongoing projects at EU level developing the next operating system for cloud-edge continuum, while promoting its sustainability via the AI-on-demand platform and EU portals.