Classifying Images with CoLaNET Spiking Neural Network -- the MNIST Example
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929498607321088 |
|---|---|
| author | Kiselev, Mikhail |
| author_facet | Kiselev, Mikhail |
| contents | In the present paper, it is shown how the columnar/layered CoLaNET spiking neural network (SNN) architecture can be used in supervised learning image classification tasks. Image pixel brightness is coded by the spike count during image presentation period. Image class label is indicated by activity of special SNN input nodes (one node per class). The CoLaNET classification accuracy is evaluated on the MNIST benchmark. It is demonstrated that CoLaNET is almost as accurate as the most advanced machine learning algorithms (not using convolutional approach). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07833 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Classifying Images with CoLaNET Spiking Neural Network -- the MNIST Example Kiselev, Mikhail Neural and Evolutionary Computing In the present paper, it is shown how the columnar/layered CoLaNET spiking neural network (SNN) architecture can be used in supervised learning image classification tasks. Image pixel brightness is coded by the spike count during image presentation period. Image class label is indicated by activity of special SNN input nodes (one node per class). The CoLaNET classification accuracy is evaluated on the MNIST benchmark. It is demonstrated that CoLaNET is almost as accurate as the most advanced machine learning algorithms (not using convolutional approach). |
| title | Classifying Images with CoLaNET Spiking Neural Network -- the MNIST Example |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2409.07833 |