News Overview

Index  〉News overview page  〉Show item

Research: Solving Complex Learning Tasks in Brain-Inspired Computers

STRUC­TURES members Andreas Baumbach, Akos Ferenc Kungl, Johannes Schemmel and Mihai Petrovici develop a new training approach for spiking neural networks with their co-workers.

Developing a ma­chine that processes information as efficiently as the human brain has been a long-standing re­search goal towards true artificial intelligence. The interdisciplinary re­search team at Hei­del­berg Uni­ver­si­ty and the Uni­ver­si­ty of Bern (Switzerland) led by Mihai Petrovici is tackling this problem with the help of biologically-inspired artificial neural networks. Spiking neural networks, which mimic the structure and function of a natural nervous system, represent promising candidates because they are powerful, fast, and energy-efficient. One key challenge is how to train such complex systems. The German-Swiss re­search team has now developed and successfully implemented an algorithm that achieves such training.

See press release from October 29, 2021 (in English) or from October 29, 2021 (in German).

Original publication in Nature Ma­chine Intelligence from September 17, 2021 (in English).


STRUCTURES Contact

STRUCTURES Project Management Office
Philosophenweg 12 & Berliner Str. 47
D-69120 Heidelberg

+49 (0) 6221-54 9186

office@structures.uni-heidelberg.de

Connect With STRUCTURES on Social Media