Cargando…

N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning

Few-shot learning (learning with a few samples) is one of the most important cognitive abilities of the human brain. However, the current artificial intelligence systems meet difficulties in achieving this ability. Similar challenges also exist for biologically plausible spiking neural networks (SNN...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yang, Dong, Yiting, Zhao, Dongcheng, Zeng, Yi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9718842/
https://www.ncbi.nlm.nih.gov/pubmed/36460664
http://dx.doi.org/10.1038/s41597-022-01851-z
_version_ 1784843182602715136
author Li, Yang
Dong, Yiting
Zhao, Dongcheng
Zeng, Yi
author_facet Li, Yang
Dong, Yiting
Zhao, Dongcheng
Zeng, Yi
author_sort Li, Yang
collection PubMed
description Few-shot learning (learning with a few samples) is one of the most important cognitive abilities of the human brain. However, the current artificial intelligence systems meet difficulties in achieving this ability. Similar challenges also exist for biologically plausible spiking neural networks (SNNs). Datasets for traditional few-shot learning domains provide few amounts of temporal information. And the absence of neuromorphic datasets has hindered the development of few-shot learning for SNNs. Here, to the best of our knowledge, we provide the first neuromorphic dataset for few-shot learning using SNNs: N-Omniglot, based on the Dynamic Vision Sensor. It contains 1,623 categories of handwritten characters, with only 20 samples per class. N-Omniglot eliminates the need for a neuromorphic dataset for SNNs with high spareness and tremendous temporal coherence. Additionally, the dataset provides a powerful challenge and a suitable benchmark for developing SNNs algorithms in the few-shot learning domain due to the chronological information of strokes. We also provide the improved nearest neighbor, convolutional network, SiameseNet, and meta-learning algorithm in the spiking version for verification.
format Online
Article
Text
id pubmed-9718842
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-97188422022-12-04 N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning Li, Yang Dong, Yiting Zhao, Dongcheng Zeng, Yi Sci Data Data Descriptor Few-shot learning (learning with a few samples) is one of the most important cognitive abilities of the human brain. However, the current artificial intelligence systems meet difficulties in achieving this ability. Similar challenges also exist for biologically plausible spiking neural networks (SNNs). Datasets for traditional few-shot learning domains provide few amounts of temporal information. And the absence of neuromorphic datasets has hindered the development of few-shot learning for SNNs. Here, to the best of our knowledge, we provide the first neuromorphic dataset for few-shot learning using SNNs: N-Omniglot, based on the Dynamic Vision Sensor. It contains 1,623 categories of handwritten characters, with only 20 samples per class. N-Omniglot eliminates the need for a neuromorphic dataset for SNNs with high spareness and tremendous temporal coherence. Additionally, the dataset provides a powerful challenge and a suitable benchmark for developing SNNs algorithms in the few-shot learning domain due to the chronological information of strokes. We also provide the improved nearest neighbor, convolutional network, SiameseNet, and meta-learning algorithm in the spiking version for verification. Nature Publishing Group UK 2022-12-02 /pmc/articles/PMC9718842/ /pubmed/36460664 http://dx.doi.org/10.1038/s41597-022-01851-z Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Data Descriptor
Li, Yang
Dong, Yiting
Zhao, Dongcheng
Zeng, Yi
N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
title N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
title_full N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
title_fullStr N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
title_full_unstemmed N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
title_short N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
title_sort n-omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
topic Data Descriptor
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9718842/
https://www.ncbi.nlm.nih.gov/pubmed/36460664
http://dx.doi.org/10.1038/s41597-022-01851-z
work_keys_str_mv AT liyang nomniglotalargescaleneuromorphicdatasetforspatiotemporalsparsefewshotlearning
AT dongyiting nomniglotalargescaleneuromorphicdatasetforspatiotemporalsparsefewshotlearning
AT zhaodongcheng nomniglotalargescaleneuromorphicdatasetforspatiotemporalsparsefewshotlearning
AT zengyi nomniglotalargescaleneuromorphicdatasetforspatiotemporalsparsefewshotlearning