RT Journal Article
T1 nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
A1 Susi, Gianluca
A1 Antón Toro, Luis Fernando
A1 Maestu Unturbe, Fernando
A1 Pereda, Ernesto
A1 Mirasso, Claudio
AB The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological learning. Unfortunately, the range of problems to which this topology can be applied is limited because of the low cardinality of the parallel spike trains that it can process, and the lack of a visualization mechanism to understand its internal operation. We present here the nMNSD structure, which is a generalization of the MNSD to any number of inputs. The mathematical framework of the structure is introduced, together with the “trapezoid method,” that is a reduced method to analyze the recognition mechanism operated by the nMNSD in response to a specific input parallel spike train. We apply the nMNSD to a classification problem previously faced with the classical MNSD from the same authors, showing the new possibilities the nMNSD opens, with associated improvement in classification performances. Finally, we benchmark the nMNSD on the classification of static inputs (MNIST database) obtaining state-of-the-art accuracies together with advantageous aspects in terms of time- and energy-efficiency if compared to similar classification methods.
PB Frontiers Media
SN 1662-4548
YR 2021
FD 2021-02-19
LK https://hdl.handle.net/20.500.14352/116676
UL https://hdl.handle.net/20.500.14352/116676
LA eng
NO Susi, G., Antón-Toro, L. F., Maestú, F., Pereda, E., and Mirasso, C. (2021). nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift. Front. Neurosci. 15, 582608. doi: 10.3389/fnins.2021.582608
NO "UCM-SANTANDER scholarship to PhD students (Ref. C2017)""María de Maeztu Program for Units of Excellence in R&D (MDM-2017-0711)"
NO Universidad Complutense de Madrid
NO Banco Santander
NO Comunidad de Madrid
NO Ministerio de Economía, Comercio y Empresa (España)
NO Ministerio de Ciencia e Innovación (España)
NO European Commission
NO Agencia Estatal de Investigación (España)
DS Docta Complutense
RD 17 abr 2025