Three papers accepted for ISCAS 2021

The Bio-inspired Circuits & Systems group is proud that three papers by the BICS group members are accepted for the 2021 IEEE International Symposium on Circuits and Systems (ISCAS).

In the paper 'A Hardware-friendly Neuromorphic Spiking Neural Network for Frequency Detection and Fine Texture Decoding' Michele Mastella and Elisabetta Chicca present a novel approach to the decoding of how the nervous system converts a texture's spatial period into an equivalent spiking frequency. Their approach is based on a spiking neural network which is able to detect the frequency of change in an input signal inspired by biological evidence. This will allow a straightforward implementation on integrated silicon circuits, allowing texture decoding at the edge of sensors.

In their second paper 'Artificial Bio-inspired Tactile Receptive Fields for Edge Orientation Classification' Michele Mastella and Elisabetta Chicca alongside colleagues from Italy and the US present a novel spiking neural network for edge detection in visual and tactile sensory data. This network is inspired by edge encoding found in human's first order tactile afferents. They show that the network is able to learn the appropriate connectivity through unsupervised spike based learning in order to discriminate different edge orientations.

In the paper 'Ferroelectric Tunneling Junctions for Edge Computing ' Philipp Klein, Ole Richter and Elisabetta Chicca discuss how recent advances in the field of ferro-electric tunnel junctions could be used for neuromorphic and edge computing applications. Together with partners from the EU H2020 project 'BeFerroSynaptic' they investigate how specific electrical features of ferro-electric hafnium-zirconium oxide based FTJs can be used for edge computing applications.