High-Order Associative Learning Based on Memristive Circuits for Efficient Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912081571217408 |
|---|---|
| author | Wang, Shengbo Li, Xuemeng Ding, Jialin Ma, Weihao Wang, Ying Occhipinti, Luigi Nathan, Arokia Gao, Shuo |
| author_facet | Wang, Shengbo Li, Xuemeng Ding, Jialin Ma, Weihao Wang, Ying Occhipinti, Luigi Nathan, Arokia Gao, Shuo |
| contents | Memristive associative learning has gained significant attention for its ability to mimic fundamental biological learning mechanisms while maintaining system simplicity. In this work, we introduce a high-order memristive associative learning framework with a biologically realistic structure. By utilizing memristors as synaptic modules and their state information to bridge different orders of associative learning, our design effectively establishes associations between multiple stimuli and replicates the transient nature of high-order associative learning. In Pavlov's classical conditioning experiments, our design achieves a 230% improvement in learning efficiency compared to previous works, with memristor power consumption in the synaptic modules remaining below 11 μW. In large-scale image recognition tasks, we utilize a 20*20 memristor array to represent images, enabling the system to recognize and label test images with semantic information at 100% accuracy. This scalability across different tasks highlights the framework's potential for a wide range of applications, offering enhanced learning efficiency for current memristor-based neuromorphic systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_16734 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | High-Order Associative Learning Based on Memristive Circuits for Efficient Learning Wang, Shengbo Li, Xuemeng Ding, Jialin Ma, Weihao Wang, Ying Occhipinti, Luigi Nathan, Arokia Gao, Shuo Neural and Evolutionary Computing Signal Processing Applied Physics Memristive associative learning has gained significant attention for its ability to mimic fundamental biological learning mechanisms while maintaining system simplicity. In this work, we introduce a high-order memristive associative learning framework with a biologically realistic structure. By utilizing memristors as synaptic modules and their state information to bridge different orders of associative learning, our design effectively establishes associations between multiple stimuli and replicates the transient nature of high-order associative learning. In Pavlov's classical conditioning experiments, our design achieves a 230% improvement in learning efficiency compared to previous works, with memristor power consumption in the synaptic modules remaining below 11 μW. In large-scale image recognition tasks, we utilize a 20*20 memristor array to represent images, enabling the system to recognize and label test images with semantic information at 100% accuracy. This scalability across different tasks highlights the framework's potential for a wide range of applications, offering enhanced learning efficiency for current memristor-based neuromorphic systems. |
| title | High-Order Associative Learning Based on Memristive Circuits for Efficient Learning |
| topic | Neural and Evolutionary Computing Signal Processing Applied Physics |
| url | https://arxiv.org/abs/2410.16734 |