PGI Colloquium:Prof. Dr. Giacomo Indiveri, ETH Zurich, Switzerland

PGI Lecture Hall, Building 04.8, 2nd Floor, Room 365

Neuromorphic Electronic Circuits for Building Artificial Neural Processing Units

Artificial computing systems are vastly outperformed by biological neural processing ones for many practical tasks that involve sensory perception and real-time interactions with the environment, especially when size and energy consumption are factored in. One of the reasons is that the architecture of nervous systems, in which billions of neurons communicate in parallel mainly via asynchronous action potentials, is very different from that of today's mainly serial and synchornous logic devices and systems.

Recent machine learning algorithms have taken inspiration from the nervous system to develop neuro-computing algorithms that are showing state-of-the-art performance in pattern recognition tasks. In parallel, different types of brain-inspired hardware architectures are being developed that reproduce some of the principles of computation used by the nervous system. These architectures represent a promising technology for both implementing the latest generation of neural networks, and for building faithful models of biological neural processing systems.

In this lecture I will present an overview of spiking neuron circuits, synapses that exhibit biologically plausible dynamics, and spike based learning mechanisms that are compatible with memristive devices. I will present examples of spike-based neural network architectures that can be used to implement real-time models of cortical circuits and show examples of applications that can best exploit their ultra-low power real-time signal processing and learning properties.

Kontakt

Stephan Menzel

Telefon: +49 2461 61-6074

Fax: 

E-Mail: st.menzel@fz-juelich.de