Benchmarking Spike-Based Visual Recognition: a Dataset and EvaluationCitation formats

  • Authors:
  • Qian Liu
  • Garibaldi Pineda garcia
  • Evangelos Stromatias
  • Teresa Serrano-Gotarredona
  • Steve Furber

Standard

Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation. / Liu, Qian; Pineda garcia, Garibaldi; Stromatias, Evangelos; Serrano-Gotarredona, Teresa; Furber, Steve.

In: Frontiers in Neuroscience, Vol. 10, 496, 02.11.2016.

Research output: Contribution to journalArticlepeer-review

Harvard

Liu, Q, Pineda garcia, G, Stromatias, E, Serrano-Gotarredona, T & Furber, S 2016, 'Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation', Frontiers in Neuroscience, vol. 10, 496. https://doi.org/10.3389/fnins.2016.00496

APA

Liu, Q., Pineda garcia, G., Stromatias, E., Serrano-Gotarredona, T., & Furber, S. (2016). Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation. Frontiers in Neuroscience, 10, [496]. https://doi.org/10.3389/fnins.2016.00496

Vancouver

Liu Q, Pineda garcia G, Stromatias E, Serrano-Gotarredona T, Furber S. Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation. Frontiers in Neuroscience. 2016 Nov 2;10. 496. https://doi.org/10.3389/fnins.2016.00496

Author

Liu, Qian ; Pineda garcia, Garibaldi ; Stromatias, Evangelos ; Serrano-Gotarredona, Teresa ; Furber, Steve. / Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation. In: Frontiers in Neuroscience. 2016 ; Vol. 10.

Bibtex

@article{56af59c0610c4646ab7e8b3ffa19a6e5,
title = "Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation",
abstract = "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 benchmarksand 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.",
author = "Qian Liu and {Pineda garcia}, Garibaldi and Evangelos Stromatias and Teresa Serrano-Gotarredona and Steve Furber",
year = "2016",
month = nov,
day = "2",
doi = "10.3389/fnins.2016.00496",
language = "English",
volume = "10",
journal = "Frontiers in Neuroscience",
issn = "1662-4548",
publisher = "Frontiers Media S. A.",

}

RIS

TY - JOUR

T1 - Benchmarking Spike-Based Visual Recognition: a Dataset and Evaluation

AU - Liu, Qian

AU - Pineda garcia, Garibaldi

AU - Stromatias, Evangelos

AU - Serrano-Gotarredona, Teresa

AU - Furber, Steve

PY - 2016/11/2

Y1 - 2016/11/2

N2 - 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 benchmarksand 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.

AB - 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 benchmarksand 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.

U2 - 10.3389/fnins.2016.00496

DO - 10.3389/fnins.2016.00496

M3 - Article

VL - 10

JO - Frontiers in Neuroscience

JF - Frontiers in Neuroscience

SN - 1662-4548

M1 - 496

ER -