Forward-only learning in memristor arrays with month-scale stability
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915832724979712 |
|---|---|
| author | Renaudineau, Adrien Diallo, Mamadou Hawa Dupuis, Théo Imbert, Bastien Iftakher, Mohammed Akib Harabi, Kamel-Eddine Turck, Clément Hirtzlin, Tifenn Bonnet, Djohan Melul, Franck Aguirre-Morales, Jorge-Daniel Vianello, Elisa Bocquet, Marc Portal, Jean-Michel Querlioz, Damien |
| author_facet | Renaudineau, Adrien Diallo, Mamadou Hawa Dupuis, Théo Imbert, Bastien Iftakher, Mohammed Akib Harabi, Kamel-Eddine Turck, Clément Hirtzlin, Tifenn Bonnet, Djohan Melul, Franck Aguirre-Morales, Jorge-Daniel Vianello, Elisa Bocquet, Marc Portal, Jean-Michel Querlioz, Damien |
| contents | Turning memristor arrays from efficient inference engines into systems capable of on-chip learning has proved difficult. Weight updates have a high energy cost and cause device wear, analog states drift, and backpropagation requires a backward pass with reversed signal flow. Here we experimentally demonstrate learning on standard filamentary HfOx/Ti arrays that addresses these challenges with two design choices. First, we rely on forward-only training algorithms in the Forward-Forward family that use only inference-style operations. Second, we use sub-1 V reset-only, single-pulse updates that cut energy and yield stable analog states. We train two-layer classifiers on an ImageNet-resolution four-class task using arrays up to 8,064 devices. Two forward-only variants, two-pass supervised Forward-Forward and a single-pass competitive rule, achieve test accuracies of 89.5% and 89.6%, respectively; a reference experiment using backpropagation reaches 90.0%. Across five independent runs per method, these accuracies are indistinguishable within statistical uncertainty. Trained models retain accuracy for at least one month under ambient conditions, consistent with the stability of reset-only states. Sub-1 V reset updates use 460 times less energy than conventional program-and-verify programming and require just 46% more energy than inference-only operation. Together, these results establish forward-only, sub-1 V learning on standard filamentary stacks at array scale, outlining a practical, pulse-aware route to adaptive edge intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Forward-only learning in memristor arrays with month-scale stability Renaudineau, Adrien Diallo, Mamadou Hawa Dupuis, Théo Imbert, Bastien Iftakher, Mohammed Akib Harabi, Kamel-Eddine Turck, Clément Hirtzlin, Tifenn Bonnet, Djohan Melul, Franck Aguirre-Morales, Jorge-Daniel Vianello, Elisa Bocquet, Marc Portal, Jean-Michel Querlioz, Damien Emerging Technologies Turning memristor arrays from efficient inference engines into systems capable of on-chip learning has proved difficult. Weight updates have a high energy cost and cause device wear, analog states drift, and backpropagation requires a backward pass with reversed signal flow. Here we experimentally demonstrate learning on standard filamentary HfOx/Ti arrays that addresses these challenges with two design choices. First, we rely on forward-only training algorithms in the Forward-Forward family that use only inference-style operations. Second, we use sub-1 V reset-only, single-pulse updates that cut energy and yield stable analog states. We train two-layer classifiers on an ImageNet-resolution four-class task using arrays up to 8,064 devices. Two forward-only variants, two-pass supervised Forward-Forward and a single-pass competitive rule, achieve test accuracies of 89.5% and 89.6%, respectively; a reference experiment using backpropagation reaches 90.0%. Across five independent runs per method, these accuracies are indistinguishable within statistical uncertainty. Trained models retain accuracy for at least one month under ambient conditions, consistent with the stability of reset-only states. Sub-1 V reset updates use 460 times less energy than conventional program-and-verify programming and require just 46% more energy than inference-only operation. Together, these results establish forward-only, sub-1 V learning on standard filamentary stacks at array scale, outlining a practical, pulse-aware route to adaptive edge intelligence. |
| title | Forward-only learning in memristor arrays with month-scale stability |
| topic | Emerging Technologies |
| url | https://arxiv.org/abs/2601.09903 |