Classifying Neuromorphic Data Using a Deep Learning Framework for Image Classification

Classifying Neuromorphic Data Using a Deep Learning Framework for Image Classification
Title:
Classifying Neuromorphic Data Using a Deep Learning Framework for Image Classification
Other Titles:
2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)
Keywords:
Publication Date:
18 November 2018
Citation:
R. Gopalakrishnan, Y. Chua and L. R. Iyer, "Classifying Neuromorphic Data Using a Deep Learning Framework for Image Classification," 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, 2018, pp. 1520-1524. doi: 10.1109/ICARCV.2018.8581256
Abstract:
In the field of artificial intelligence, neuromorphic computing has been around for several decades. Deep learning has however made much recent progress such that it consistently outperforms neuromorphic learning algorithms in classification tasks in terms of accuracy. Specifically in the field of image classification, neuromorphic computing has been traditionally using either the temporal or rate code for encoding static images in datasets into spike trains. It is only till recently, that neuromorphic vision sensors are widely used by the neuromorphic research community, and provides an alternative to such encoding methods. Since then, several neuromorphic datasets as obtained by applying such sensors on image datasets (e.g. the neuromorphic CALTECH 101) have been introduced. These data are encoded in spike trains and hence seem ideal for benchmarking of neuromorphic learning algorithms. Specifically, we train a deep learning framework used for image classification on the CALTECH 101 and a collapsed version of the neuromorphic CALTECH 101 datasets. We obtained an accuracy of 91.66% and 78.01% for the CALTECH 101 and neuromorphic CALTECH 101 datasets respectively. For CALTECH 101, our accuracy is close to the best reported accuracy, while for neuromorphic CALTECH 101, it outperforms the last best reported accuracy by over 10%. This raises the question of the suitability of such datasets as benchmarks for neuromorphic learning algorithms.
License type:
PublisherCopyrights
Funding Info:
Description:
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
978-1-5386-9582-1
978-1-5386-9581-4
978-1-5386-9583-8
Files uploaded:
File Size Format Action
There are no attached files.