SC1 Neuromorphic Computing – Sensors and Deep Learning Networks


First session: We start with a history of neuromorphic engineering; the analogues between neuronal physics and transistor physics, and the building blocks of neuromorphic systems

Second session: We will cover the circuit basics for the Dynamic Vision retina sensor, simple neuron models, and the use of this sensor in different applications

Third session: We will cover the circuit basics for the Dynamic Auditory Sensor, the similarity of the circuits to the biophysics of hearing

Fourth session: We will cover the basics of deep networks, the modifications of the architectures to incorporate bio-inspired features, and the use of these networks with the sensors


Conceptual: To provide an understanding of how biological organizing principles are incorporated into electronics

Methodological: To show how transistor circuits are used to form bio-inspired models and how spiking sensors are used to solve practical applications.


Carver Mead, “Neuromorphic electronic systems”, Proceedings of IEEE, 1990
Misha Mahowald and Carver Mead, “The silicon retina,” Scientific American, 1991
Kwabena Boahen “Neuromorphic microchips”, Scientific American, 2005
Liu and Delbruck, “Neuromorphic sensory systems”, Current opinion in neurobiology, 2010
O’Connor, Neil, Delbruck, Liu, and Pfeiffer, “Real-time classification and sensor fusion with a spiking deep belief network”, Frontiers, 2013

Course location


Course requirements


Instructor information.

Shih-Chii Liu


University of Zurich and ETH Zurich


Shih-Chii Liu ( is at the Institute of Neuroinformatics, University of Zurich and ETH Zurich. Starting out as a trained electrical engineer from MIT, she worked at various companies in Silicon Valley before returning for her doctoral studies at California Institute of Technology. Currently, she is co-leading the Sensors group that develops low-power neuromorphic silicon auditory and vision sensory systems; VLSI event-driven bio-inspired processing circuits, event-driven sensory processing algorithms, and deep neural networks. Applications of the research include speech applications such as voice activity detection and object tracking.