| Autor: |
Skalli Anas, Goldmann Mirko, Porte Xavier, Haghighi Nasibeh, Reitzenstein Stephan, Lott James A., Brunner Daniel |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
EPJ Web of Conferences, Vol 287, p 13008 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2100-014X |
| DOI: |
10.1051/epjconf/202328713008 |
| Popis: |
We experimentally demonstrate an autonomous, fully tuneable and scalable neural network of 350+ parallel nodes based on a large area, multimode semiconductor laser. We implement online learning strategies based on reinforcement learning. Our system achieves high performance and a high classification bandwidth of 15KHz for the MNIST dataset. Our approach is highly scalable both in terms of classification bandwidth and neural network size. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
