本論文主要目的是透過光通訊模擬軟體來設計出Echo State Network(ESN)之結構，在結構中的類神經元都是由光纖、兩個耦合器和摻鉺光纖放大器所組成，並用於處理與時間有關的數據，使其能夠分辨訊號。本論文將改變類神經元接法、數目，或者輸入的光源，並以NRMSE來當作辨別訊號能力的好壞，來找尋一個最好的結構。

The main purpose of this paper is to design the structure of Echo State Network (ESN) through optical communication simulation software. Our structure uses several neurons. The neuron is composed of optical fibers, two couplers and erbium-doped fiber amplifiers (EDFA). We use structure to deal with time-related data, so that it can recognize the signal. This paper will change the connection of neurons, the number of neurons, or the input light source. We use NRMSE to identify the ability of the signal is good or bad, to find a best structure.

[1] D. Silver, A. Huang, et al, “Mastering the game of go with deep neural networks and tree search,” Nature 529(7857), 484 (2016).
[2] N. Baba, and M. Kozakai, “An intelligent forecasting system of stock price using neural networks,” IJCNN 92, 371 (1992).
[3] D. J. Burr, “Experiments on neural net recognition of spoken and written text,” IEEE Trans. On ASSP. 36, 1162 (1988).
[4] H. Jaeger, “The ‘echo state’ approach to analysing andtraining recurrent neural networks,” GMD Report 148, German National Research Center for Information Technology, (2001).
[5] L. Larger, et al, “Photonic information processing beyond turing: an optoelectronic implementation of reservoir computing,” Opt. Exp. 20, 3241 (2012).
[6] Y. Paquot, et al, “Optoelectronic reservoir computing,” Sci. Rep. 2, 287 (2012).
[7] D. Woods and T. J. Naughton, “Photonic neural networks”, Nature Physics 8, 257 (2012).
[8] S. Ortín, et al, “A unified framework for reservoir computing and extreme learning machines based on a single time-delayed neuron,” Sci. Rep. 5, 14945 (2015).
[9] G. B. Huang, Q. Y. Zhu, and C. K. Siew, “Extreme learning machine: a new learning scheme of feedforward neural networks,” IEEE International Joint Conference on Neural Networks 2, 985 (2004).
[10]羅華強, “類神經網路-MATLAB的應用,” 高立圖書有限公司, (2005).
[11]蔡瑞煌, “類神經網路概論,” 三民書局, (1995).
[12]葉怡成, “類神經網路模式應用與實作,” 儒林圖書有限公司, (1995).
[13] J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proceedings of the National Academy of Sciences of the USA 79(8), 2554 (1982).
[14] Y. Chauvin and D. Rumelhart, “Backpropagation: theory, architectures, and applications,” Hillsdale: HJ: Lawrence Erlbaum, (1995).
[15] D. S. Broomhead, D. Lowe, “Multivariable functional interpolation and adaptive networks,” Complex Systems 2(3), 321 (1988).
[16] R. J. Williams and D. Zipser, “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks,” Neural Computation 1, 270 (1989).
[17] 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).
[18] W. Maass, T. Natschlaeger, and H. Markram, “Real-time computing without stable states: a new framework for neural computation based on perturbations,” Neural Computation 14(11), 2531 (2002).
[19] M. Lukoševičius, “A practical guide to applying echo state network,” Neural Networks: Tricks of the Trade 7700, 659 (2012).
[20] M. Lukoševičius, H. Jaeger, ”Reservoir computing approaches to recurrent neural network training,” Computer Science Review 3, 127 (2009).
[21]張育誠, “Prediction of sensory input using echo state network,” 碩士論文, 國立中正大學電機工程研究所, (2011).
[22]鄒志偉, “光纖通訊,” 五南圖書, (2011).
[23]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).
[24]Synopsys, Inc. “OptSim Models Reference Volume II Block Mode.”