Please use this identifier to cite or link to this item: https://doi.org/10.3389/fnins.2016.00184
Title: Skimming digits: Neuromorphic classification of spike-encoded images
Authors: Cohen, G.K
Orchard, G 
Leng, S.-H
Tapson, J
Benosman, R.B
van Schaik, A
Keywords: Article
artificial neural network
biosensor
computer
computer program
computer simulation
dendrite
equipment design
image analysis
image processing
imaging system
kernel method
learning algorithm
mathematical computing
measurement accuracy
silicon retina
spike
Spiking Neural Network
statistical distribution
Synaptic Kernel Inverse Method
validation process
visual information
visual system
Issue Date: 2016
Citation: Cohen, G.K, Orchard, G, Leng, S.-H, Tapson, J, Benosman, R.B, van Schaik, A (2016). Skimming digits: Neuromorphic classification of spike-encoded images. Frontiers in Neuroscience 10 (APR) : 184. ScholarBank@NUS Repository. https://doi.org/10.3389/fnins.2016.00184
Rights: Attribution 4.0 International
Abstract: The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value. @ 2016 Cohen, Orchard, Leng, Tapson, Benosman and van Schaik.
Source Title: Frontiers in Neuroscience
URI: https://scholarbank.nus.edu.sg/handle/10635/183340
ISSN: 16624548
DOI: 10.3389/fnins.2016.00184
Rights: Attribution 4.0 International
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_3389_fnins_2016_00184.pdf2.54 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

34
checked on Jul 25, 2021

Page view(s)

56
checked on Jul 22, 2021

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons