Supporting Data and Software for Event-based computation: Unsupervised elementary motion decomposition



We show that the presented architecture allows for unsupervised learning; that synaptic rewiring enhanced to initialise synapses by drawing from a distribution of delays produces more specialised neurons for the task of motion decomposition; and that a pair of readout neurons is sufficient to correctly classify the input based on the target layer's activity using rank-order encoding, rather than spike-rate encoding.
Date made available11 Mar 2019
PublisherMendeley Data
Date of data production1 Jan 2019 - 10 Mar 2019

Cite this