SPIDERweb: a neural network approach to spectral phase interferometry
Year: 2024
Authors: Gianani I., Walmsley I.A., Barbieri M.
Autors Affiliation: Univ Roma Tre, Dipartimento Sci, Via Vasca Navale 84, I-00146 Rome, Italy; Imperial Coll London, Dept Phys, QOLS, London SW7 2BW, England; Ist Nazl Ottica CNR, Largo Enrico Fermi 6, I-50125 Florence, Italy.
Abstract: Reliably characterized pulses are the starting point of any application of ultrafast techniques. Unfortunately, experimental constraints do not always allow for optimizing the characterization conditions. This dictates the need for refined analysis methods. Here we show that neural networks can provide a viable characterization when applied to data from interferometry for direct electric-field reconstruction (SPIDER). We have adopted a cascade of convolutional networks, addressing the multiparameter structure of the interferogram with a reasonable computing power. In particular, the necessity of precalibration is reduced, thus pointing toward the introduction of neural networks in more generic arrangements. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.
Journal/Review: OPTICS LETTERS
Volume: 49 (19) Pages from: 5415 to: 5418
More Information: Ministero dell’Universita e della Ricerca (Dipartimento di Eccellenza 2023-2027) ; Horizon 2020 Framework Programme (899587) .KeyWords: Ultrashort-pulse Characterization; ReconstructionDOI: 10.1364/OL.534767
