In METASPIN we envision a radically new low-power artificial synapse technology based on spintronics nanodevices that will prevent catastrophic forgetting, i.e. the loss of memory of previously learned tasks upon learning new ones, a major flaw currently faced by all artificial intelligence applications. We will develop a new class of neuromorphic hardware that will use magneto-ionics to support synaptic metaplasticity, i.e. a feature inspired by the human brain based on assigning a ‘hidden value’ to the states of artificial synapses to encode how important each state is. This will make it easier or harder to reconfigure the synaptic state upon learning a new task, giving a hierarchy to previously learned information and thus preventing catastrophic forgetting. The synaptic states will be given by the two magnetisation orientations in ferromagnets with perpendicular magnetic anisotropy, and by ferro/antiferromagnetic order in materials where the two phases coexist. In all cases, magneto-ionic gating will be used to locally modulate intrinsic magnetic properties to assign ‘hidden states’ to each synaptic state. The magneto-ionic hidden states will translate into a modulation of the switching probability between synaptic states, introducing the metaplasticity functionality. In parallel, we will develop ANNs learning schemes, adapted to our device physics and inspired by biological synaptic activity, that can learn with mitigated catastrophic forgetting. The ultimate goal of this project is to integrate this advanced synaptic technology and learning algorithms into an ANN demonstrator to test multitask learning on proof-of-concept tasks inspired by medical AI, and assess the impact of metaplasticity in catastrophic forgetting.

This proposal describes the third core project of the Graphene Flagship. It forms the fourth phase of the FET flagship and is characterized by a continued transition towards higher technology readiness levels, without jeopardizing our strong commitment to fundamental research. Compared to the second core project, this phase includes a substantial increase in the market-motivated technological spearhead projects, which account for about 30% of the overall budget. The broader fundamental and applied research themes are pursued by 15 work packages and supported by four work packages on innovation, industrialization, dissemination and management. The consortium that is involved in this project includes over 150 academic and industrial partners in over 20 European countries.

The goal of the PRIME project is to establish an open Ultra Low Power (ULP) Technology Platform containing all necessary design and architecture blocks and components which could enable the European industry to increase and strengthen their competitive and leading eco-system and benefit from market opportunities created by the Internet of Things (IoT) revolution. Over 3 years the project will develop and demonstrate the key building blocks of IoT ULP systems driven by the applications in the medical, agricultural, domestics and security domains. This will include development of high performance, energy efficient and cost effective technology platform, flexible design ecosystem (including IP and design flow), changes in architectural and power management to reduced energy consumption, security blocks based on PUF and finally the System of Chip and System in Package memory banks and processing implementations for IoT sensor node systems. Developped advanced as 22nm FDSOI low power technologies with logic, analog, RF and embedded new memory components (STT RAM and RRAM) together with innovative design and system architecture solutions will be used to build macros and demonstrate functionality and power reduction advantage of the new IoT device components. The PRIME project will realize several demonstrators of IoT system building blocks to show the proposed low power wireless solutions, functionality and performance of delivered design and technology blocks. The consortium semiconductor ecosystem (IDMs, design houses, R&D, tools & wafer suppliers, foundries, system/product providers) covers complementarily all desired areas of expertise to achieve the project goals. The project will enable an increase in Europe’s innovation capability in the area of ULP Technology, design and applications, creation of a competitive European eco-system and help to identify market leadership opportunities in security, mobility, healthcare and smart cost competitive manufacturing.

The 2D Experimental Pilot Line (2D-EPL) project will establish a European ecosystem for prototype production of Graphene and Related Materials (GRM) based electronics, photonics and sensors. The project will cover the whole value chain including tool manufacturers, chemical and material providers and pilot lines to offer prototyping services to companies, research centers and academics. The 2D-EPL targets to the adoption of GRM integration by commercial semiconductor foundries and integrated device manufacturers through technology transfer and licensing. The project is built on two pillars. In Pillar 1, the 2D-EPL will offer prototyping services for 150 and 200 mm wafers, based on the current state of the art graphene device manufacturing and integration techniques. This will ensure external users and customers are served by the 2D-EPL early in the project and guarantees the inclusion of their input in the development of the final processes by providing the specifications on required device layouts, materials and device performances. In Pillar 2, the consortium will develop a fully automated process flow on 200 and 300 mm wafers, including the growth and vacuum transfer of single crystalline graphene and TMDCs. The knowledge gained in Pillar 2 will be transferred to Pillar 1 to continuously improve the baseline process provided by the 2D-EPL. To ensure sustainability of the 2D-EPL service after the project duration, integration with EUROPRACTICE consortium will be prepared. It provides for the European actors a platform to develop smart integrated systems, from advanced prototype design to small volume production. In addition, for the efficiency of the industrial exploitation, an Industrial Advisory Board consisting mainly of leading European semiconductor manufacturers and foundries will closely track and advise the progress of the 2D-EPL. This approach will enable European players to take the lead in this emerging field of technology.