Progetti di ricerca

Computing hardware is facing the urgent challenge of processing massive amounts of data with low power consumption and low latency, in particular because of the rapidly increasing demands from Artificial Intelligence (AI). Our vision is to develop a radically new… Leggi tutto hardware platform for ultra-fast (~1 μs) and energy-efficient (~ 1 μW) edge-AI inference based on a world-first, unique, braininspired hybrid architecture of analogue in-memory computing, realised with nanoscale dopant network processing units (DNPUs) in silicon integrated with silicon/silicon nitride memristors. We apply the principle of material learning to exploit the intrinsic nonlinearity and tunability of a network of dopants in silicon without the need to design tailor-made circuitry for desired functionality. We integrate complex tunable nonlinear functionality with embedded memory to realise colocation of processing and memory, addressing the von Neumann bottleneck. A new unconventional computing paradigm is expected by combining in-materio and neuromorphic computing approaches. Our technology will be validated for all-hardware systems via machine-learning benchmarks and progressively more complex tasks with the MNIST handwritten digits, CIFAR10 and federated learning. Importantly, the silicon-based platform is an innovative, unconventional computing architecture that can nevertheless be realised with conventional CMOS technology. Low power consumption, low latency, and a small footprint make our technology uniquely suitable for edge computing, with unprecedented performance in areas such as autonomous AI and image processing for health and security. DN4UC will thus establish an energy-efficient, fast, nanoscale processing platform to handle societal challenges ranging from personalised health, climate, energy, to security, contributing to the digital and green transition. Moreover, we expect DN4UC to contribute to securing and maintaining the EU’s global leadership in AI.

NEUREKA will bring a paradigm shift in drug discovery for neurological diseases, a sector that suffers multiple, repeated failures exacerbating the economical and societal burden of these incurable diseases. It will do so by addressing a crucial shortcoming: the lack… Leggi tutto of in vitro systems faithfully reproducing brain pathology that enable the functional assessment of candidate compounds at multiple levels: from synapses to neuronal circuits. NEUREKA introduces an innovative, hybrid technology, whereby detailed, computational neuronal networks simulate dysfunction and drive cultured neurons to replicate in-brain disease conditions. Nanoelectrodes mediate the transmission between simulated and biological neurons. Akin to real synapses, nanoelectrodes contact cultured neurons at subcellular locations across the dendritic tree, soma and axonal branches, allowing to control and monitor neural activity with unprecedented accuracy. Biological neuronal responses registered by nanoelectrodes are fed back to simulated neurons, closing the loop and enabling control of activity states across the hybrid population. Complementing molecular deficits already present in culture models of a disease, computational models enable replication of both molecular and physiological deficits of neurodegeneration in vitro. Cultured neurons are driven towards pathological excitability states where deficits emerge, so as to optimize quantification of the impact of drugs, going well beyond standard cellular assays. A proof-of-concept will be provided for Alzheimer’s disease, using human induced pluripotent stem cell (iPSC)-derived neurons exhibiting the pathology. NEUREKA will be used to demonstrate the effect of drug candidates across synaptic, neuronal and network functions.