課程介紹

首頁 修業資訊 課程介紹課程大綱

課程目標

1、提昇學生對人工智慧增強技術之瞭解。 2、部份課程邀請業界人士做實務介紹，擴展學生的視野。 3、應用於光學設計專題，增進學生對實務的瞭解。  

修習條件

主要教本

[1] G. Barbastathis, A. Ozcan, and G. Situ. “On the use of deep learning for computational imaging,” Optica 6.8 (July 2019), p. 921. doi:10.1364/optica.6.000921. [2] D.J. Brady, L. Fang, and Z. Ma. “Deep learning for camera data acquisition, control, and image estimation,” Advances in Optics and Photonics 12.4 (Nov. 2020), p. 787. doi: 10.1364/aop.398263. [3] G. Côté, Jean-François Lalonde, and S. Thibault. “Extrapolating from lens design databases using deep learning,” Optics Express 27.20 (Sept. 2019), p. 28279. doi: 10.1364/oe.27.028279. [4] Y. Guo et al. “Deep learning for visual understanding: A review,” Neurocomputing 187 (Apr. 2016), pp. 27–48. doi: 10.1016/j.neucom.2015.09.116. [5] R. S. Hegde. “Deep learning: a new tool for photonic nanostructure design,”. Nanoscale Advances 2.3 (2020), pp. 1007–1023. doi: 10.1039/c9na00656g. [6] L. Huang et al. “Spectral imaging with deep learning,” Light: Science ＆ Applications 11.1 (Mar. 2022). doi: 10.1038/s41377-022-00743-6. [7] Y. LeCun, Y. Bengio, and G. Hinton. “Deep learning,” Nature 521.7553 (May 2015), pp. 436–444. doi: 10.1038/nature14539. [8] W. Ma et al. “Deep learning for the design of photonic structures,” Nature Photonics 15.2 (Oct. 2020), pp. 77–90. doi: 10.1038/s41566-020-0685-y. [9] J. Park et al. “Free-form optimization of nanophotonic devices: from classical methods to deep learning,” Nanophotonics 11.9 (Jan. 2022), pp. 1809–1845. doi: 10.1515/nanoph-2021-0713. [10] P. R. Wiecha et al. “Deep learning in nano-photonics: inverse design and beyond,” Photonics Research 9.5 (Apr. 2021), B182. doi: 10.1364/prj.415960. [11] A.P. Yow et al. “Artificial intelligence in optical lens design, ” Artificial Intelligence Review 57.8 (July 2024). doi: 10.1007/s10462-024-10842-y. [12] T. Zeng, Y. Zhu, and E. Y. Lam. “Deep learning for digital holography: a review,” Optics Express 29.24 (Nov. 2021), p. 40572. doi: 10.1364/oe.443367. [13] C. Zuo et al. “Deep learning in optical metrology: a review,” Light: Science ＆ Applications 11.1 (Feb. 2022). doi: 10.1038/s41377-022-00714-x.

內容大綱

1 CNN 卷積神經網路架構: 以MNIST為簡例，介紹神經網路架構，卷積核，激活函數及基於神經網路非線性回歸的基本概念
2 人工智慧基本認識: 介紹Backpropogation method，並使用matlab與政府公開資料進行人工智慧模型的訓練
3 人工智慧app與科學上的應用，介紹人工智慧應用軟體，以及在科學上的應用
4 Paper Reviews: Deep Learning for Optical Lens Design, Deep Learning for Nanophotonics Devices
6 光學軟體與AI-Zemax: 軟體簡介與應用、軟體實例演示、AI應用
7 光學軟體與AI-Lumerical: 軟體簡介與應用、軟體實例演示、AI應用
8 光學軟體與AI-SPEOS: 軟體簡介與應用、軟體實例演示、AI應用
9 結構軟體與AI-Mechanical : 軟體簡介與應用、軟體實例演示、AI應用
10 熱流軟體與AI-CFD: 軟體簡介與應用、軟體實例演示、AI應用
11 電磁軟體與AI-HFSS: 軟體簡介與應用、軟體實例演示、AI應用
12 17-18週：自主學習、準備並繳交專題報告