Neuromorphic Cognitive Systems

The NCS group was established in early 2009 to study and develop computational models, hybrid analog/digital VLSI circuits, and multi-chip event-based systems for implementing Neuromorphic Cognitive Systems.

Our work is aimed at bridging the gap from simple reactive real-time behaving sensory-motor systems to ones that are cognitive in quality.

We are involved in multiple projects, whose overarching goal is to build physical artifacts that use neuromorphic architectures to interact with the environment in real-time and reason about the actions to take, in response to the combinations of external stimuli, internal states, and behavioral objectives.

In our group we study spike-based probabilistic processing, we design hybrid analog/digital microelectronic circuits that exploit the physics of silicon to reproduce the biophysics of biological neural systems, we investigate the use of emerging nanotechnologies integrated in neuromorphic architectures and we develop multi-chip systems that process and communicate signals using real-time asynchronous events (spikes).

Examples of recent developments include low-power silicon neuron circuits, dynamic silicon synapses, hybrid analog/digital spike-based (STDP) learning mechanisms, soft Winner-Take-All (WTA) networks, and asynchronous digital communication circuits and systems. Check out our publications for more details.