Lecture Announcement, Monday August 30, 15 – 17 via Teams & Tuesday August 31, 15 – 17 via Teams, “Neuromorphic Intelligence: brain inspired artificial intelligence circuits and systems for extreme edge computing applications”, by Prof. Giacomo Indiveri – Institute of Neuroinformatics University of Zurich and ETH Zurich

Artificial Intelligence (AI) and deep learning algorithms are revolutionizing our computing landscape, and have demonstrated impressive results in a wide range of applications. However, they still have serious shortcomings for use cases that require closed-loop interactions with the real-world. In particular, current AI systems are still not able to compete with biological ones in tasks that involve real-time processing of sensory data and decision making in complex and noisy settings.
Neuromorphic Intelligence aims to fill this gap by developing ultra-low power Spiking Neural Network (SNNs) architectures using mixed-signal analog/digital electronic circuits and emerging memory technologies.
These neuromorphic systems implement the principles of computation observed in the nervous system by exploiting the physics of their electronic devices to directly emulate the biophysics of real neurons and synapses.
As the analog circuits and their nano-scale devices are affected by high amounts of variability and heterogeneity, neuromorphic systems implement the same computational strategies used by the nervous system to cope with, and even exploit heterogeneity for carrying out efficient computation.
In this lecture series I will present a historical overview of the neuromorphic field, its current state, and its future potential. I will give a tutorial on basic neuromorphic circuit design and describe examples of state-of-the-art silicon neuron and synapse circuits. I will present system-level examples of spiking neural networks and show examples of computational neuroscience strategies that can be used to reduce the effect of device mismatch and variability. Finally, I will demonstrate applications of neuromorphic processing systems to extreme-edge use cases, that require low power, local processing of the sensed data, and that cannot afford to connect to the cloud for running AI algorithms.

The course consists of an overall 4-hours lecture, hence it will grant 0.5 CFU.

All students wishing to attend the course are kindly requested to register at the link: https://forms.gle/S1LCXnyPMMH9cECu5