Exploring the hidden dimensions of an optical extreme learning machine

• Type: Article in International Scientific Journal
• Date: 2023

Authors

Silva, D (Author) Other; Ferreira, T (Author) Other; Moreira, FC (Author) Other; Rosa, CC (Author) FCUP; Guerreiro, A (Author) FCUP; Silva, NA (Author) Other

Journal

The Journal is awaiting validation by the Administrative Services.

Title: JOURNAL OF THE EUROPEAN OPTICAL SOCIETY-RAPID PUBLICATIONS

Vol. 19

Pages: 436-444

ISSN: 1990-2573

Indexing

ISI Web of Knowledge - 0 Citations

Scopus

Other information

Authenticus ID: P-00Y-088

DOI: 10.1051/jeos/2023001

Abstract (EN): Extreme Learning Machines (ELMs) are a versatile Machine Learning (ML) algorithm that features as the main advantage the possibility of a seamless implementation with physical systems. Yet, despite the success of the physical implementations of ELMs, there is still a lack of fundamental understanding in regard to their optical implementations. In this context, this work makes use of an optical complex media and wavefront shaping techniques to implement a versatile optical ELM playground to gain a deeper insight into these machines. In particular, we present experimental evidences on the correlation between the effective dimensionality of the hidden space and its generalization capability, thus bringing the inner workings of optical ELMs under a new light and opening paths toward future technological implementations of similar principles.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 4