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.
