Print Email Facebook Twitter Improve the optical neural network structure by using neural architecture search for visual classification tasks Title Improve the optical neural network structure by using neural architecture search for visual classification tasks Author Hu, T. (TU Delft Mechanical, Maritime and Materials Engineering) Contributor Norte, R.A. (mentor) Bessa, M.A. (mentor) Aragon, A.M. (graduation committee) Degree granting institution Delft University of Technology Programme Mechanical Engineering Date 2023-07-07 Abstract This research explores the integration of Neural Architecture Search with Optical Neural Networks to optimize the efficiency and performance in traditional visual image classification tasks. The study introduces a new approach that applies Neural Architecture Search, a technique traditionally used to optimize the performance of Artificial Neural Networks, to the field of Optical Neural Networks. Subject Neural architecture searchOptical Neural NetworksMach-Zehnder interfereometer To reference this document use: http://resolver.tudelft.nl/uuid:b701fe3b-ccbb-4621-a8db-99ddfbc63ea7 Part of collection Student theses Document type master thesis Rights © 2023 T. Hu Files PDF tud_with_cover_ms.pdf 22.74 MB Close viewer /islandora/object/uuid:b701fe3b-ccbb-4621-a8db-99ddfbc63ea7/datastream/OBJ/view