The human nervous system is a massively distributed, parallel, and interconnected system, with superior functionality and performance in data processing and adaptive learning compared to digital computers. Neuromorphic computing aims to replicate some of the functionality and architecture of the human brain within artificial machines. Accurate and faithful emulation of neuromorphic functionality requires unconventional materials and devices beyond the standard von Neumann digital architecture. Moreover, the computational primitives of biological neural networks on device and circuit level can be considered a first step towards efficient neuromorphic computing systems that are able to analyze, interpret, perceive and act upon a dynamic, real-world environment. Thus, a new era of smart sensor and actuation applications is emerging with systems that perceive and interact with the world and efficiently couple with biological environments. This approach requires materials, devices and systems that would be able to interface biology in a smart and dynamic way.

The purpose of this symposium is to bring together an interdisciplinary and diverse group of researchers on neuromorphic computing as well as smart sensing, actuation and bio-interfacing, enhancing transdisciplinary interactions and bridging gaps between materials science, computing and neuroscience. The symposium focuses on elements with simultaneous memory and processing capabilities towards "in-memory" computing and local adaptive bio-interfaces and computing paradigms, and highlights fundamental materials properties, discovery of novel inorganic and organic materials, novel devices harnessing physical emergent phenomena, new computing paradigms enabled by unconventional materials, and theory and simulation on materials, devices, and architectures.

devices electronic material machine learning memory modeling nanoelectronics neuromorphic semiconducting