Impact Factor 3.566

The #1 most cited and #1 largest open-access publisher in the category of Neuroscience.


Original Research ARTICLE

Front. Neurosci. | doi: 10.3389/fnins.2017.00350

An event-based classifier for Dynamic Vision Sensor and synthetic data

  • 1Instituto de Microelectrónica de Sevilla (CSIC and Univ. of Seville), Spain

This paper introduces a novel methodology for training an event-based classifier with synthetic and raw dynamic vision sensor (DVS) data. The proposed supervised method takes advantage of the spiking activity to build histograms and train the classifier in the frame domain using the stochastic gradient descend algorithm. In addition, this approach can cope with neuron leakages, a desirable feature for real-world applications, since it captures the dynamics of the spikes. We tested our method on the MNIST data set using different encodings and DVS-based data sets such as N-MNIST, MNIST-DVS, and Fast-Poker-DVS using the same network topology and feature maps. We demonstrate the effectiveness of our approach by achieving the highest classification accuracy reported on the N-MNIST to date with a spiking convolutional network 97.77%, as well as, 100% on the Fast-Poker-DVS data set. Moreover, by using the proposed method we were able to retrain the output layer of a spiking neural network and increase its performance by 2% suggesting that our classifier can be used as the output layer in works where features are extracted using unsupervised spike-based learning methods. Lastly, this work also presents a comparison between different data sets in terms of total activity and network latency.

Keywords: spiking neural networks, supervised learning, Event driven Processing, DVS sensors, Convolutional Neural Networks, Neuromorphic, Fully connected neural networks

Received: 24 Mar 2017; Accepted: 06 Jun 2017.

Edited by:

Emre O. Neftci, University of California, Irvine, United States

Reviewed by:

Thomas Nowotny, University of Sussex, United Kingdom
Hesham Mostafa, University of California, San Diego, United States of America  

Copyright: © 2017 Stromatias, Soto, Serrano-Gotarredona and Linares-Barranco. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Prof. Bernabe Linares-Barranco, Instituto de Microelectrónica de Sevilla (CSIC and Univ. of Seville), Sevilla, Spain,