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.
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
29 Sep 2016
|
| In: |
Nature Communications
Year: 2016, Volume: 7 |
| ISSN: | 2041-1723 |
| DOI: | 10.1038/ncomms12611 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/ncomms12611 Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/ncomms12611 
|
| Author Notes: | Alexander Serb, Johannes Bill, Ali Khiat, Radu Berdan, Robert Legenstein & Themis Prodromakis |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 05.05.2020 |
| Physical Description: | Online Resource |
| ISSN: | 2041-1723 |
| DOI: | 10.1038/ncomms12611 |