Scalable platform enabling reservoir computing with nanoporous oxide memristors for image recognition and time series prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912877402652672 |
|---|---|
| author | Donald, Joshua Johnson, Ben A. Mehrnejat, Amir Gabbitas, Alex Coveney, Arthur G. T. Balanov, Alexander G. Savel'ev, Sergey Borisov, Pavel |
| author_facet | Donald, Joshua Johnson, Ben A. Mehrnejat, Amir Gabbitas, Alex Coveney, Arthur G. T. Balanov, Alexander G. Savel'ev, Sergey Borisov, Pavel |
| contents | Typical mammal brains have some form of random connectivity between neurons. Reservoir computing, a neural network approach, uses random weights within its processing layer along with built-in recurrent connections and short-term, fading memory, and is shown to be time and training efficient in processing spatiotemporal signals. Here we prepared a niobium oxide-based thin film memristor device with intrinsic structural in-homogeneity in the form of random nanopores and performed computational tasks of XOR operations, image recognition, and time series prediction and reconstruction. For the latter task we chose a complex three-dimensional chaotic Lorenz-63 time series. By applying three temporal voltage waveforms individually across the device and training the readout layer with electrical current signals from a three-output physical reservoir, we achieved satisfactory prediction and reconstruction accuracy in comparison to the case of no reservoir. This work highlights the potential for scalable, on-chip devices using all-oxide reservoir systems, paving the way for energy-efficient neuromorphic electronics dealing with time signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04619 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scalable platform enabling reservoir computing with nanoporous oxide memristors for image recognition and time series prediction Donald, Joshua Johnson, Ben A. Mehrnejat, Amir Gabbitas, Alex Coveney, Arthur G. T. Balanov, Alexander G. Savel'ev, Sergey Borisov, Pavel Disordered Systems and Neural Networks Materials Science Typical mammal brains have some form of random connectivity between neurons. Reservoir computing, a neural network approach, uses random weights within its processing layer along with built-in recurrent connections and short-term, fading memory, and is shown to be time and training efficient in processing spatiotemporal signals. Here we prepared a niobium oxide-based thin film memristor device with intrinsic structural in-homogeneity in the form of random nanopores and performed computational tasks of XOR operations, image recognition, and time series prediction and reconstruction. For the latter task we chose a complex three-dimensional chaotic Lorenz-63 time series. By applying three temporal voltage waveforms individually across the device and training the readout layer with electrical current signals from a three-output physical reservoir, we achieved satisfactory prediction and reconstruction accuracy in comparison to the case of no reservoir. This work highlights the potential for scalable, on-chip devices using all-oxide reservoir systems, paving the way for energy-efficient neuromorphic electronics dealing with time signals. |
| title | Scalable platform enabling reservoir computing with nanoporous oxide memristors for image recognition and time series prediction |
| topic | Disordered Systems and Neural Networks Materials Science |
| url | https://arxiv.org/abs/2602.04619 |