Elisa Donati, ETH Zurich
Neuromorphic processors comprise hybrid analog/digital circuits that implement hardware models of biological systems, using computational principles analogous to the ones used by the nervous systems. The neuromorphic devices exhibit very slow, biologically plausible, time constants to well match the signals they are designed to process, such that they are inherently synchronized with the real-world signals they sense and act on. This leads to the advantage of ultra-low power processing of natural sensory signals, which is particularly important in biomedical and prosthetic applications. In addition, the neuromorphic technology offers the possibility to process the data directly on the sensor side in real-time, extremely useful for wearable solutions for daily life. Despite the slow time-constants, the neuromorphic neural processing chips have extremely fast response times (or extremely low latency). This is made possible with event-based signals (e.g., spikes) that are communicated between sensing and computing nodes in real-time, as they happen, using asynchronous digital logic. Thanks to the low latency, neuromorphic devices can be used for decision making processing. In this presentation a general concept of neuromorphic engineering is introduced, together with some practical use cases. In particular, examples of biomedical applications, such as the EMG gesture classification and the implementation of an adaptive analog pacemaker.