SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module
Abstract Spiking Neural Network is known as the third‐generation artificial neural network whose development has great potential. With the help of Spike Layer Error Reassignment in Time for error back‐propagation, this work presents a new network called SpikeGoogle, which is implemented with GoogLeN...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12082 |
| _version_ | 1811340328274231296 |
|---|---|
| author | Xuan Wang Minghong Zhong Hoiyuen Cheng Junjie Xie Yingchu Zhou Jun Ren Mengyuan Liu |
| author_facet | Xuan Wang Minghong Zhong Hoiyuen Cheng Junjie Xie Yingchu Zhou Jun Ren Mengyuan Liu |
| author_sort | Xuan Wang |
| collection | DOAJ |
| description | Abstract Spiking Neural Network is known as the third‐generation artificial neural network whose development has great potential. With the help of Spike Layer Error Reassignment in Time for error back‐propagation, this work presents a new network called SpikeGoogle, which is implemented with GoogLeNet‐like inception module. In this inception module, different convolution kernels and max‐pooling layer are included to capture deep features across diverse scales. Experiment results on small NMNIST dataset verify the results of the authors’ proposed SpikeGoogle, which outperforms the previous Spiking Convolutional Neural Network method by a large margin. |
| first_indexed | 2024-04-13T18:40:17Z |
| format | Article |
| id | doaj.art-f2dce0d8a22e413fbcf2adcf5fffdc41 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-04-13T18:40:17Z |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-f2dce0d8a22e413fbcf2adcf5fffdc412022-12-22T02:34:45ZengWileyCAAI Transactions on Intelligence Technology2468-23222022-09-017349250210.1049/cit2.12082SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception moduleXuan Wang0Minghong Zhong1Hoiyuen Cheng2Junjie Xie3Yingchu Zhou4Jun Ren5Mengyuan Liu6School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou ChinaSchool of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou ChinaSchool of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou ChinaSchool of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou ChinaShenzhen Academy of Metrology and Quality Inspection Shenzhen ChinaInfocare Systems Limited New ZealandSchool of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou ChinaAbstract Spiking Neural Network is known as the third‐generation artificial neural network whose development has great potential. With the help of Spike Layer Error Reassignment in Time for error back‐propagation, this work presents a new network called SpikeGoogle, which is implemented with GoogLeNet‐like inception module. In this inception module, different convolution kernels and max‐pooling layer are included to capture deep features across diverse scales. Experiment results on small NMNIST dataset verify the results of the authors’ proposed SpikeGoogle, which outperforms the previous Spiking Convolutional Neural Network method by a large margin.https://doi.org/10.1049/cit2.12082GoogLeNetinceptionSpiking Neural Networks |
| spellingShingle | Xuan Wang Minghong Zhong Hoiyuen Cheng Junjie Xie Yingchu Zhou Jun Ren Mengyuan Liu SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module CAAI Transactions on Intelligence Technology GoogLeNet inception Spiking Neural Networks |
| title | SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module |
| title_full | SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module |
| title_fullStr | SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module |
| title_full_unstemmed | SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module |
| title_short | SpikeGoogle: Spiking Neural Networks with GoogLeNet‐like inception module |
| title_sort | spikegoogle spiking neural networks with googlenet like inception module |
| topic | GoogLeNet inception Spiking Neural Networks |
| url | https://doi.org/10.1049/cit2.12082 |
| work_keys_str_mv | AT xuanwang spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule AT minghongzhong spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule AT hoiyuencheng spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule AT junjiexie spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule AT yingchuzhou spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule AT junren spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule AT mengyuanliu spikegooglespikingneuralnetworkswithgooglenetlikeinceptionmodule |