Online spike-based recognition of digits with ultrafast microlaser neurons
Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficie...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2023.1164472/full |
| _version_ | 1797789224589590528 |
|---|---|
| author | Amir Masominia Laurie E. Calvet Simon Thorpe Sylvain Barbay |
| author_facet | Amir Masominia Laurie E. Calvet Simon Thorpe Sylvain Barbay |
| author_sort | Amir Masominia |
| collection | DOAJ |
| description | Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step. In particular, we discuss the merits of event, spike-time and rank-order based algorithms adapted to this system. These techniques have the potential to significantly improve the efficiency and effectiveness of optical classification systems, minimizing the number of spiking nodes required for a given task and leveraging the parallelism offered by photonic hardware. |
| first_indexed | 2024-03-13T01:47:41Z |
| format | Article |
| id | doaj.art-8603911d08934ac196bb1f0fef2646c8 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-03-13T01:47:41Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-8603911d08934ac196bb1f0fef2646c82023-07-03T05:42:58ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882023-07-011710.3389/fncom.2023.11644721164472Online spike-based recognition of digits with ultrafast microlaser neuronsAmir Masominia0Laurie E. Calvet1Simon Thorpe2Sylvain Barbay3Université Paris-Saclay, CNRS, Centre de Nanosciences et de Nanotechnologies, Palaiseau, FranceLPICM, CNRS-Ecole Polytechnique, Palaiseau, FranceCERCO UMR5549, CNRS—Université Toulouse III, Toulouse, FranceUniversité Paris-Saclay, CNRS, Centre de Nanosciences et de Nanotechnologies, Palaiseau, FranceClassification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step. In particular, we discuss the merits of event, spike-time and rank-order based algorithms adapted to this system. These techniques have the potential to significantly improve the efficiency and effectiveness of optical classification systems, minimizing the number of spiking nodes required for a given task and leveraging the parallelism offered by photonic hardware.https://www.frontiersin.org/articles/10.3389/fncom.2023.1164472/fullphotonic hardwaretemporal codingrank-order codespiking neuronsmicrolasersreceptive fields |
| spellingShingle | Amir Masominia Laurie E. Calvet Simon Thorpe Sylvain Barbay Online spike-based recognition of digits with ultrafast microlaser neurons Frontiers in Computational Neuroscience photonic hardware temporal coding rank-order code spiking neurons microlasers receptive fields |
| title | Online spike-based recognition of digits with ultrafast microlaser neurons |
| title_full | Online spike-based recognition of digits with ultrafast microlaser neurons |
| title_fullStr | Online spike-based recognition of digits with ultrafast microlaser neurons |
| title_full_unstemmed | Online spike-based recognition of digits with ultrafast microlaser neurons |
| title_short | Online spike-based recognition of digits with ultrafast microlaser neurons |
| title_sort | online spike based recognition of digits with ultrafast microlaser neurons |
| topic | photonic hardware temporal coding rank-order code spiking neurons microlasers receptive fields |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2023.1164472/full |
| work_keys_str_mv | AT amirmasominia onlinespikebasedrecognitionofdigitswithultrafastmicrolaserneurons AT laurieecalvet onlinespikebasedrecognitionofdigitswithultrafastmicrolaserneurons AT simonthorpe onlinespikebasedrecognitionofdigitswithultrafastmicrolaserneurons AT sylvainbarbay onlinespikebasedrecognitionofdigitswithultrafastmicrolaserneurons |