University of Sussex
Browse
fnins-10-00496.pdf (3.99 MB)

Benchmarking spike-based visual recognition: a dataset and evaluation

Download (3.99 MB)
journal contribution
posted on 2023-06-09, 16:20 authored by Qian Liu, Garibaldi Pineda Garcia, Evangelos Stromatias, Teresa Serrano-Gotarredona, Steve B Furber
Today, increasing attention is being paid to research into spike-based neural computation both to gain a better understanding of the brain and to explore biologically-inspired computation. Within this field, the primate visual pathway and its hierarchical organisation have been extensively studied. Spiking Neural Networks (SNNs), inspired by the understanding of observed biological structure and function, have been successfully applied to visual recognition and classification tasks. In addition, implementations on neuromorphic hardware have enabled large-scale networks to run in (or even faster than) real time, making spike-based neural vision processing accessible on mobile robots. Neuromorphic sensors such as silicon retinas are able to feed such mobile systems with real-time visual stimuli. A new set of vision benchmarks for spike-based neural processing are now needed to measure progress quantitatively within this rapidly advancing field. We propose that a large dataset of spike-based visual stimuli is needed to provide meaningful comparisons between different systems, and a corresponding evaluation methodology is also required to measure the performance of SNN models and their hardware implementations. In this paper we first propose an initial NE (Neuromorphic Engineering) dataset based on standard computer vision benchmarks and that uses digits from the MNIST database. This dataset is compatible with the state of current research on spike-based image recognition. The corresponding spike trains are produced using a range of techniques: rate-based Poisson spike generation, rank order encoding, and recorded output from a silicon retina with both flashing and oscillating input stimuli. In addition, a complementary evaluation methodology is presented to assess both model-level and hardware-level performance. Finally, we demonstrate the use of the dataset and the evaluation methodology using two SNN models to validate the performance of the models and their hardware implementations. With this dataset we hope to (1) promote meaningful comparison between algorithms in the field of neural computation, (2) allow comparison with conventional image recognition methods, (3) provide an assessment of the state of the art in spike-based visual recognition, and (4) help researchers identify future directions and advance the field.

History

Publication status

  • Published

File Version

  • Published version

Journal

Frontiers in Neuroscience

ISSN

1662-453X

Publisher

Frontiers Research Foundation

Volume

10

Page range

496 1-18

Department affiliated with

  • Informatics Publications

Research groups affiliated with

  • Centre for Computational Neuroscience and Robotics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2018-12-21

First Open Access (FOA) Date

2023-05-25

First Compliant Deposit (FCD) Date

2023-05-25

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC