隨著科技的進步，深度學習改變了許多工業的生產方式，例如用於檢測缺陷、辨識物件等。其中位於最核心的網路模型，是演算法的核心，也是經過大數據訓練之後的精華。但是，對於大多數業者來說，如何從零開始訓練出一個可用的模型，是在生產線上導入人工智慧的一大難關。如何快速且簡單的完成一個可用的深度學習模型，就成了一個大多數非資工領域的作業人員想要了解的議題。
通常要訓練一個準確度高的深度學習模型，除了需要大量的資料外，也需要複雜的網路架構，並經過無數次的微調後，才能完成。資料的取得對於產線作業人員而言相對容易，網路架構則需要花時間了解細節，並不是一時半刻可以完成的，也使得入門的門檻相對提高許多，不利於各類工廠進行產業升級。
本研究結合了深度模型套件Keras及客戶端與伺服器端的網頁語言，提供一個可以快速訓練的深度學習模型的網頁端人工智慧系統。本系統可以讓使用者透過圖形介面設定參數並上傳訓練資料，讓非資工領域的使用者不需要花太多時間了解深度學習的細節也能快速訓練出所需的模型。

As technology advances, deep learning has changed the way many industries produce, such as detecting defects, identifying objects, and so on. The core network model is the core of the algorithm and the essence of the training after big data. However, for most operators, how to train a usable model from scratch is a major difficulty in introducing artificial intelligence on the production line. How to quickly and easily complete a usable deep learning model becomes an issue that most non-employed workers want to know.
Usually, training a highly accurate deep learning model requires a complex network architecture in addition to a large amount of data, and can be completed after numerous fine-tuning. The acquisition of data is relatively easy for the production line operators, and the network architecture needs to take time to understand the details. It is not completed in a moment and a half, and the threshold for entry is relatively improved, which is not conducive to industrial upgrading of various factories.
This study combines the deep learning model suite Keras with the web language of the client and server side to provide a web-based artificial intelligence system that can quickly train deep learning models. The system allows users to set parameters and upload training data through the graphical interface, so that users in non-employed fields can quickly train the required models without spending too much time on the details of deep learning.

[1] A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.
[2] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le. Learning transferable architectures for scalable image recognition. arXiv: 1707.07012, 2017.
[3] B. Zoph and Q. V. Le. Neural architecture search with reinforcement learning. In International Conference on Learning Representations, 2017.
[4] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1–9, 2015.
[5] G. Huang, Z. Liu, K. Q. Weinberger, and L. Maaten. Densely connected convolutional networks. In CVPR, 2017.
[6] F. Chollet. Xception: Deep learning with depthwise separable convolutions. arXiv preprint arXiv:1610.02357v2, 2016
[7] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567, 2015.
[8] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of CVPR, pages 770–778, 2016.
[9] Yi-Hsuan Huang. A Web Application Generator for Embedded Devices with HTML5 and JavaScript. Master Thesis, National Taiwan University, 2015.
[10] Wolber, David. "App inventor and real-world motivation." Proceedings of the 42nd ACM technical symposium on Computer science education. ACM, 2011.
[11] Blockly. Retrieved June 16, 2019, from https://developers.google.com/blockly/
[12] Chared, Zeev, and Shmuel S. Tyszberowicz. "Projective Template-Based Code Generation." CAiSE Forum. 2013.
[13] Morrison, J. Paul. Flow-Based Programming: A new approach to application development. CreateSpace, 2010.
[14] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradientbased learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
[15] the Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition. Retrieved June 16, 2019, from http://cs231n.github.io/convolutional-networks/
[16] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, pages 1929–1958, 2014
[17] JSON. Retrieved June 16, 2019, from https://www.json.org/
[18] Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zheng, X. Tensorflow: A system for large-scale machine learning. arXiv:1605.08695, 2016.
[19] Francois Chollet et al. Keras. Retrieved June 16, 2019, from https://keras.io/
[20] A. Krizhevsky. Learning multiple layers of features from tiny images. Tech Report, 2009.
[21] The CIFAR-10 dataset. Retrieved June 16, 2019, from https://www.cs.toronto.edu/~kriz/cifar.html
[22] Spyder Website. Retrieved June 16, 2019, from https://www.spyder-ide.org/
[23] Node.js. Retrieved June 16, 2019, from https://nodejs.org/
 
[24] Mohorovicic, S. "Implementing responsive web design for enhanced web presence." Information & Communication Technology Electronics & Microelectronics (MIPRO), 2013 36th International Convention on. IEEE, 2013.
[25] Myers, Brad A. "Taxonomies of visual programming and program visualization." Journal of Visual Languages & Computing 1.1 (1990): 97-123.
[26] Weigert, Thomas, et al. "Automated code generation for industrial-strength systems." Computer Software and Applications, 2008. COMPSAC''08. 32nd Annual IEEE International. IEEE, 2008.