在本論文中，我們透過光通訊軟體來設計出使用Echo State Network(ESN)模型的光學電腦，隱藏層中的類神經元都是由兩個耦合器、光纖和摻鉺光纖放大器所組成。在我們的研究中，我們使用EDFA來提供非線性函數。最後我們透過幾項信號辨識任務 : 無雜訊三角波方波之信號辨識、含雜訊三角波方波之信號辨識、不同頻率之弦波信號辨識，來證明我們設計之光學電腦的可行性。

In this thesis, we use optical communication simulation software to build an optical neural network system based on Echo State Network(ESN) model. The optical neurons in the system consist of directional couplers, optical fibers, and the erbium-doped optical fiber amplifiers (EDFA). The nonlinear activation function of optical neuron can be obtained by EDFA.
To evaluate the performance of our optical neural network system, we illustratting its performance on tasks of Signal classification. Such as signal classification of triangular and retangular waveforms with and without noise and signal classification of sine waveforms with different frequencies.

[1] Xiao-Qian Sun, Hua-Wei Shen and Xue-Qi Cheng, “Trading Network Predicts Stock Price, ” Scientific Reports 4, 3711(2014).
[2] N. Baba and M. Kozakai, ” An intelligent forecasting system of stock price using neural networks, ” IJCNN 92, 371 (1992).
[3]林逸塵, “類神經網路應用於空氣品質預測之研究,” 碩士論文, 國立中山大學環境工程研究所, (2002).
[4] I. A. Maaly and M. El-Obaid, “Speech Recognition using Artificial Neural Network, ” International Conference on Information & Communication Technologies 2, 1246(2006)
[5] D. Psaltis, A. Yamamura, K. Hsu, S. Lin, X.G Gu and D. Brady, “Optoelectronic Implementations of Neural Networks, ” IEEE Communications Magazine 27, 37(1989)
[6] I. Shariv and A. A. Friesem, “All-optical neural network with inhibitory neurons, ” OPTICS LETTERS 14, 485(1989)
[7] H. Jaeger, “The ‘Echo State’ approach to analysing andtraining
recurrent neural networks, ” GMD Report 148, German National Research
Center for Information Technology, (2001).
[8] H. Jaeger and H.Haas, “Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication, ” Science 304, 78(2004).
[9] L.Appeltant, M.C.Soriano, G.Van der Sande, J.Danckaert, S.Massar, J. Dambr, B.Schrauwen, C.R.Mirasso and I. Fischer, “Information Processing using a Single Dynamical Node as Complex System, ” Nature Communications 2, 468(2011).
[10] Y. Paquot, F. Duport, A. Smerieri, J. Dambre, B. Schrauwen, M.Haelterman and S. Massar, “Optoelectronic Reservoir Computing, ” Scientific Reports 2, 287(2012).
[11] F. Duport, A. Smerieri, M.Haelterman, S. Massar and B. Schrauwen, “All-optical Reservoir Computing, ” Optics Express 20, 22783(2012).
[12] S. Ortín1, M. C. Soriano, L. Pesquera1, D. Brunner, D. San-Martín, I. Fischer, C. R. Mirasso and J. M. Gutiérrez, “A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron, ” Scientific Reports 5, 14945(2015).
[13] G. B. Huang, Q. Y. Zhu, and C. K. Siew, “Extreme Learning Machine:a New Learning Scheme of Feedforward Neural Networks, ” IEEE 49 International Joint Conference on Neural Networks 2, 985 (2004).
[14] A. Dejonckheere, F. Ois Duport, A. Smerieri, Li Fang, J.L. Oudar, M. Haelterman and S. Massar, “All-optical Reservoir Computer based on Saturation of Absorption, ” Optics Express 22, 10868(2014).
[15] R.M. Nguimdo, E. Lacot, O. Jacquin, O Hugon, G. Van Der Sande and H. Guillet De Chatellus, “Prediction Performance of Reservoir Computing Systems based on a Diode-Pumped Erbium-Doped Microchip Laser Subject to Optical Feedback, ” Optics Letters 42, 375(2016).
[16] F. DuportDejonckheere, A. Smerieri, A. Akrout, M. Haelterman and S. Massar, “Fully Analogue Photonic Reservoir Computer, ” Scientific Reports 6, 22381(2016).
[17]羅華強, “類神經網路-MATLAB 的應用, ” 高立圖書有限公司,
(2005).
[18]蔡瑞煌, “類神經網路概論, ” 三民書局, (1995).
[19]葉怡成, “類神經網路模式應用與實作, ” 儒林圖書有限公司,
(1995).
[20]伊相志, “SQL Server 2008 Data Mining資料採礦, ” 悅知文化, (2009)
[21] J. J. Hopfield, “Neural networks and physical systems with emergent
collective computational abilities, ” Proceedings of the National Academy
of Sciences of the USA 79, 2554(1982).
[22] Y. Chauvin and D. Rumelhart“, Backpropagation: theory,
architectures, and applications, ” Hillsdale: HJ: Lawrence Erlbaum,
(1995).
[23] T. Panayiotou, S. P. Chatzis, and G. Ellinas, “Performance Analysis of a Data-Driven Quality-of-Transmission Decision Approach on a Dynamic Multicast-Capable Metro Optical Network, ” Journal of Optical Communications and Networking 9, 98(2017).
[24] R. J. Williams and D. Zipser, “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks, ” Neural Computation 1, 270(1989).
[25] F. Duport, A. Smerieri, A. Akrout, M. Haelterman, and S. Massar,
“Virtualization of a Photonic Reservoir Computer, ” JOURNAL OF LIGHTWAVE TECHNOLOGY 34, 2085(2016)
[26] J. Steil, “Memory in backpropagation–decorrelation: O(N) efficient
online recurrent learning, ” In Proceedings of the International Conference
on Artificial Neural Networks 3697 ,649 (2005).
[27] W. Maass, T. Natschlaeger, and H. Markram, “Real-time computing
without stable states: a new framework for neural computation based on 50 perturbations, ” Neural Computation 14(11), 2531 (2002).
[28] S. Roy, A. Banerjee and A. Basu, “Liquid State Machine With Dendritically Enhanced Readout for Low-Power, Neuromorphic VLSI Implementations, ” IEEE Transactions on Biomedical Circuits and Systems 8, 681(2014).
[29]Y. Zhang, P. Li and Y. Jin, ” A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition, ” IEEE Transactions on Biomedical Circuits and Systems 26, 2635(2015).
[30] M. Lukoševičius, “A practical guide to applying echo state network, ” Neural Networks: Tricks of the Trade 7700, 659 (2012).
[31] M. Lukoševičius, H. Jaeger, ”Reservoir computing approaches to
recurrent neural network training, ” Computer Science Review 3, 127
(2009).
[32]鄒志偉,“光纖通訊,”五南圖書, (2011).
[33]陳瑞鑫,陳鴻仁和林依恩, “光通訊原理與技術, ” 金華科技圖書股份有限公司, (2004).
[34]曾文宏, “增益平坦化長波段摻鉺光纖放大器之研究, ” 碩士論文, 國立中山大學光電工程研究所, (2000).
[35] Synopsys, Inc. “OptSim Models Reference Volume II Block Mode.”
[36]周達業, “神經網路光學電腦, ” 碩士論文, 國立中央大學光電工程研究所, (2017).