Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Frontiers in computational neuroscience, 2018-06, Vol.12, p.46-46
2018

Details

Autor(en) / Beteiligte
Titel
Event-Based, Timescale Invariant Unsupervised Online Deep Learning With STDP
Ist Teil von
  • Frontiers in computational neuroscience, 2018-06, Vol.12, p.46-46
Ort / Verlag
Switzerland: Frontiers Research Foundation
Erscheinungsjahr
2018
Link zum Volltext
Quelle
EZB Electronic Journals Library
Beschreibungen/Notizen
  • Learning of hierarchical features with spiking neurons has mostly been investigated in the database framework of standard deep learning systems. However, the properties of neuromorphic systems could be particularly interesting for learning from continuous sensor data in real-world settings. In this work, we introduce a deep spiking convolutional neural network of integrate-and-fire (IF) neurons which performs unsupervised online deep learning with spike-timing dependent plasticity (STDP) from a stream of asynchronous and continuous event-based data. In contrast to previous approaches to unsupervised deep learning with spikes, where layers were trained successively, we introduce a mechanism to train all layers of the network simultaneously. This allows approximate online inference already during the learning process and makes our architecture suitable for online learning and inference. We show that it is possible to train the network without providing implicit information about the database, such as the number of classes and the duration of stimuli presentation. By designing an STDP learning rule which depends only on relative spike timings, we make our network fully event-driven and able to operate without defining an absolute timescale of its dynamics. Our architecture requires only a small number of generic mechanisms and therefore enforces few constraints on a possible neuromorphic hardware implementation. These characteristics make our network one of the few neuromorphic architecture which could directly learn features and perform inference from an event-based vision sensor.
Sprache
Englisch
Identifikatoren
ISSN: 1662-5188
eISSN: 1662-5188
DOI: 10.3389/fncom.2018.00046
Titel-ID: cdi_doaj_primary_oai_doaj_org_article_4a143a01e2e8426b8716975ae07199a5

Weiterführende Literatur

Empfehlungen zum selben Thema automatisch vorgeschlagen von bX