Unravelling an optical extreme learning machine

• Tipo: Artigo em Revista Científica Internacional
• Data: 2022

Autores

Silva, D (Autor) Outra; Silva, NA (Autor) Outra; Ferreira, TD (Autor) Outra; Rosa, CC (Autor) FCUP; Guerreiro, A (Autor) FCUP

Revista

Título: EPJ Web of Conferences

Vol. 266

ISSN: 2101-6275

Editora: EDP Sciences

Outras Informações

ID Authenticus: P-00X-J78

DOI: 10.1051/epjconf/202226613034

Abstract (EN): <jats:p>Extreme learning machines (ELMs) are a versatile machine learning technique that can be seamlessly implemented with optical systems. In short, they can be described as a network of hidden neurons with random fixed weights and biases, that generate a complex behaviour in response to an input. Yet, despite the success of the physical implementations of ELMs, there is still a lack of fundamental understanding about their optical implementations. This work makes use of an optical complex media to implement an ELM and introduce an ab-initio theoretical framework to support the experimental implementation. We validate the proposed framework, in particular, by exploring the correlation between the rank of the outputs, <jats:italic><jats:bold>H</jats:bold></jats:italic>, and its generalization capability, thus shedding new light into the inner workings of optical ELMs and opening paths towards future technological implementations of similar principles.</jats:p>

Idioma: Inglês

Tipo (Avaliação Docente): Científica