Improve the optical neural network structure by using neural architecture search for visual classification tasks

Improve the optical neural network structure by using neural architecture search for visual classification tasks

Hu, T. (TU Delft Mechanical, Maritime and Materials Engineering)

Norte, R.A. (mentor)
Bessa, M.A. (mentor)
Aragon, A.M. (graduation committee)

Delft University of Technology

Mechanical Engineering

2023-07-07

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.

Neural architecture search
Optical Neural Networks
Mach-Zehnder interfereometer

http://resolver.tudelft.nl/uuid:b701fe3b-ccbb-4621-a8db-99ddfbc63ea7

Student theses

master thesis

© 2023 T. Hu