The long term vision in BAYFLEX is to create a radically new technology that uses low cost, green organic electronics for probabilistic computing in order to allow continuous and private monitoring of bio-signals on flexible substrates. The vision of flexible green AI sensors with on chip classification extends well beyond biomedical devices and the democratization of health care, with the possibility to transform sensor data at the edge of large networks. To achieve our goal, BAYFLEX will demonstrate a patch using active physiological sensors based on organic materials that interface with the soft human body and that also includes classification circuits (~ 100 transistors) fabricated using Thin Organic Large Area Electronics (TOLAE) processes. These circuits use spiking neurons realized in Organic Thin Film Transistors (OTFTs) to transform the non-stationary electrical signals from the sensors into stochastic bit streams. Bayesian inference is then used to classify the data using circuits of cascaded Muller C-elements. Taking advantage of the unique properties of organic electrochemical transistors (OECTs), low transistor count dynamic Muller C-elements are targeted. The patch will be tested on a simple task using healthy humans. The project brings together an interdisciplinary consortium with expertise in modeling emerging devices, biologically inspired circuit design, experts in machine learning involving electrophysiological data (including an SME) and teams with expertise in OTFT and OECT fabrication. BAYFLEX targets dissemination to a variety of publics including: scientists via publications in (open access) high impact journals and conferences; industrials and end-users through an industrial advisory board, a workshop and demonstrations at targeted conferences; the general public with the creation of a transferable workshop for non-scientific communities and training the next generation of experts through specialized schools and workshops.

Five leading European supercomputing centres are committed to develop, within their respective national programs and service portfolios, a set of services that will be federated across a consortium. The work will be undertaken by the following supercomputing centres, which form the High Performance Analytics and Computing (HPAC) Platform of the Human Brain Project (HBP): ▪ Barcelona Supercomputing Centre (BSC) in Spain, ▪ The Italian supercomputing centre CINECA, ▪ The Swiss National Supercomputing Centre CSCS, ▪ The Jülich Supercomputing Centre in Germany, and ▪ Commissariat à l'énergie atomique et aux énergies alternatives (CEA), France (joining in April 2018). The new consortium will be called Fenix and it aims at providing scalable compute and data services in a federated manner. The neuroscience community is of particular interest in this context and the HBP represents a prioritised driver for the Fenix infrastructure design and implementation. The Interactive Computing E-Infrastructure for the HBP (ICEI) project will realise key elements of this Fenix infrastructure that are targeted to meet the needs of the neuroscience community. The participating sites plan for cloud-like services that are compatible with the work cultures of scientific computing and data science. Specifically, this entails developing interactive supercomputing capabilities on the available extreme computing and data systems. Key features of the ICEI infrastructure are: ▪ Scalable compute resources; ▪ A federated data infrastructure; and ▪ Interactive Compute Services providing access to the federated data infrastructure as well as elastic access to the scalable compute resources. The ICEI e-infrastructure will be realised through a coordinated procurement of equipment and R&D services. Furthermore, significant additional parts of the infrastructure and R&D services will be realised within the ICEI project through in-kind contributions from the participating supercomputing centres.

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.

More than half of the persons with spinal cord injuries (SCI) are suffering from impairments of both hands, which results in a tremendous decrease of quality of life (QoL) and represents a major barrier for inclusion in society. Functional restoration is possible with neuroprostheses based on functional electrical stimulation (FES). However, current systems are non-intelligent, non-intuitive open loop systems without sensory feedback. MoreGrasp aims at developing a multi-adaptive, multimodal user interface including brain-computer interfaces (BCIs) for intuitive control of a semi-autonomous motor and sensory grasp neuroprosthesis to support activities of daily living in individuals with SCI. With such a system a bilateral grasp restoration may become reality. The multimodal interfaces will be based on non-invasive BCIs for decoding of movements intentions with gel-less electrodes and wireless amplifiers. The neuroprosthesis will include FES electrode arrays and different sensors to allow for implementation of predefined or autonomously learned sequences. MoreGrasp will consequently follow the concept of the user-centered design by providing a scalable, modular, user-specific neuroprosthesis together with personalized EEG recording technology. Novel multimodal software architectures including interoperability standards will be defined to integrate neuroprostheses into the field of assistive technology. Long-term end user studies will demonstrate the reliability, usefulness and impact on QoL of the MoreGrasp technology. A web-based service infrastructure including a discussion forum will be set up for assessing user priorities and screening of users’ status. The evaluation of the training and patterns of use will allow for user modeling to identify factors for successful use. The highly interdisciplinary MoreGrasp consortium consists of members from universities, industry and rehabilitation centers, which have a long history of successful cooperation.