Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918108310011904 |
|---|---|
| author | Daniels, Rishona Wattad, Duna Ronen, Ronny Saad, David Kvatinsky, Shahar |
| author_facet | Daniels, Rishona Wattad, Duna Ronen, Ronny Saad, David Kvatinsky, Shahar |
| contents | Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite growing interest, a comprehensive evaluation that quantifies the impact of these factors is still lacking. This paper systematically compares various preprocessing methods for memristive RC systems, assessing their effects on accuracy and energy consumption. We also propose a parity-based preprocessing method that improves accuracy by 2-6% while requiring only a modest increase in device count compared to other methods. Our findings highlight the importance of informed preprocessing strategies to improve the efficiency and scalability of memristive RC systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05588 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Preprocessing Methods for Memristive Reservoir Computing for Image Recognition Daniels, Rishona Wattad, Duna Ronen, Ronny Saad, David Kvatinsky, Shahar Neural and Evolutionary Computing Hardware Architecture Emerging Technologies Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite growing interest, a comprehensive evaluation that quantifies the impact of these factors is still lacking. This paper systematically compares various preprocessing methods for memristive RC systems, assessing their effects on accuracy and energy consumption. We also propose a parity-based preprocessing method that improves accuracy by 2-6% while requiring only a modest increase in device count compared to other methods. Our findings highlight the importance of informed preprocessing strategies to improve the efficiency and scalability of memristive RC systems. |
| title | Preprocessing Methods for Memristive Reservoir Computing for Image Recognition |
| topic | Neural and Evolutionary Computing Hardware Architecture Emerging Technologies |
| url | https://arxiv.org/abs/2506.05588 |