Application of Reconfigurable All-Optical Activation Unit based on Optical Injection into Bistable Fabry-Pérot Laser in Multilayer Perceptron Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916601634226176 |
|---|---|
| author | Crnjanski, Jasna V. Teofilović, Isidora Krstić, Marko M. Gvozdić, Dejan M. |
| author_facet | Crnjanski, Jasna V. Teofilović, Isidora Krstić, Marko M. Gvozdić, Dejan M. |
| contents | In this paper we theoretically investigate application of a bistable Fabry-Pérot semiconductor laser under optical-injection as all-optical activation unit for multilayer perceptron optical neural networks. The proposed device is programmed to provide reconfigurable sigmoid-like activation functions with adjustable thresholds and saturation points and benchmarked on machine learning image recognition problems. Due to the reconfigurability of the activation unit, the accuracy can be increased by up to 2% simply by adjusting the control parameter of the activation unit to suit the specific problem. For a simple two-layer perceptron neural network, we achieve inference accuracies of up to 95% and 85%, for the MNIST and Fashion-MNIST datasets, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_14748 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Application of Reconfigurable All-Optical Activation Unit based on Optical Injection into Bistable Fabry-Pérot Laser in Multilayer Perceptron Neural Networks Crnjanski, Jasna V. Teofilović, Isidora Krstić, Marko M. Gvozdić, Dejan M. Emerging Technologies Optics In this paper we theoretically investigate application of a bistable Fabry-Pérot semiconductor laser under optical-injection as all-optical activation unit for multilayer perceptron optical neural networks. The proposed device is programmed to provide reconfigurable sigmoid-like activation functions with adjustable thresholds and saturation points and benchmarked on machine learning image recognition problems. Due to the reconfigurability of the activation unit, the accuracy can be increased by up to 2% simply by adjusting the control parameter of the activation unit to suit the specific problem. For a simple two-layer perceptron neural network, we achieve inference accuracies of up to 95% and 85%, for the MNIST and Fashion-MNIST datasets, respectively. |
| title | Application of Reconfigurable All-Optical Activation Unit based on Optical Injection into Bistable Fabry-Pérot Laser in Multilayer Perceptron Neural Networks |
| topic | Emerging Technologies Optics |
| url | https://arxiv.org/abs/2311.14748 |