Neuromorphic architectures for spiking deep neural networks
Year: 2015
Type: conference-paper
Abstract: We present a full custom hardware implementation of a deep neural network, built using multiple neuromorphic VLSI devices that integrate analog neuron and synapse circuits together with digital asynchronous logic circuits. The deep network comprises an event-based convolutional stage for feature extraction connected to a spike-based learning stage for feature classification. We describe the properties of the chips used to implement the network and present preliminary experimental results that validate the approach proposed.
Authors: Giacomo Indiveri, Federico Corradi, Ning Qiao
Institutions: University of Zurich, ETH Zurich
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2292733612
