Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
Artificial neural networks exhibit learning abilities and can perform tasks which are tricky for conventional computing systems, such as pattern recognition. Here, Serb et al. show experimentally that memristor arrays can learn reversibly from noisy data thanks to sophisticated learning rules.
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
29 Sep 2016
|
| In: |
Nature Communications
Year: 2016, Jahrgang: 7 |
| ISSN: | 2041-1723 |
| DOI: | 10.1038/ncomms12611 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/ncomms12611 Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/ncomms12611 
|
| Verfasserangaben: | Alexander Serb, Johannes Bill, Ali Khiat, Radu Berdan, Robert Legenstein & Themis Prodromakis |
| Zusammenfassung: | Artificial neural networks exhibit learning abilities and can perform tasks which are tricky for conventional computing systems, such as pattern recognition. Here, Serb et al. show experimentally that memristor arrays can learn reversibly from noisy data thanks to sophisticated learning rules. |
|---|---|
| Beschreibung: | Gesehen am 05.05.2020 |
| Beschreibung: | Online Resource |
| ISSN: | 2041-1723 |
| DOI: | 10.1038/ncomms12611 |