The analysis of electroencephalography and electromyography recordings plays a crucial role in health monitoring, personalized medicine, and brain-computer interfaces (BCIs). However, current technologies rely on inefficient microelectronics and cloud-based artificial intelligence, which limit signal classification accuracy and increase energy consumption.

Neuromorphic computing, which mimics the brain’s neural processing, offers a promising solution to these challenges. The ERC-funded NEURO2D project aims to develop an innovative class of 2D charge trap memory (2D-CTM) neuromorphic devices based on reservoir computing.

This low-power, high-accuracy technology has the potential to revolutionize real-time electrophysiological signal monitoring and classification. By enabling scalable, energy-efficient, implantable, and wearable chips, 2D-CTM technology could transform digital biomarker detection, medical diagnostics, and next-generation BCIs.