Learning in Memristive Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908457883402240 |
|---|---|
| author | Heidema, H. M. van Waarde, H. J. Besselink, B. |
| author_facet | Heidema, H. M. van Waarde, H. J. Besselink, B. |
| contents | Memristors are nonlinear two-terminal circuit elements whose resistance at a given time depends on past electrical stimuli. Recently, networks of memristors have received attention in neuromorphic computing since they can be used to implement Artificial Neural Networks (ANNs) in hardware. For this, one can use a class of memristive circuits called crossbar arrays. In this paper, we describe a circuit implementation of an ANN and resolve three questions concerning such an implementation. In particular, we show (1) how to evaluate the implementation at an input, (2) how the resistance values of the memristors at a given time can be determined from external (current) measurements, and (3) how the resistances can be steered to desired values by applying suitable external voltages to the network. The results will be applied to two examples: an academic example to show proof of concept and an ANN that was trained using the MNIST dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15324 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning in Memristive Neural Networks Heidema, H. M. van Waarde, H. J. Besselink, B. Optimization and Control Memristors are nonlinear two-terminal circuit elements whose resistance at a given time depends on past electrical stimuli. Recently, networks of memristors have received attention in neuromorphic computing since they can be used to implement Artificial Neural Networks (ANNs) in hardware. For this, one can use a class of memristive circuits called crossbar arrays. In this paper, we describe a circuit implementation of an ANN and resolve three questions concerning such an implementation. In particular, we show (1) how to evaluate the implementation at an input, (2) how the resistance values of the memristors at a given time can be determined from external (current) measurements, and (3) how the resistances can be steered to desired values by applying suitable external voltages to the network. The results will be applied to two examples: an academic example to show proof of concept and an ANN that was trained using the MNIST dataset. |
| title | Learning in Memristive Neural Networks |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2507.15324 |