Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain.
Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain.
复制标题
相干光神经网络具有光频控制行为和频域泛化能力。
DOI：
10.1364/ao.35.000836
复制
发表时间：
1996
期刊：
影响因子：
1.9
通讯作者：
Rolf Eckmiller
中科院分区：
文献类型：
--
作者：
Akira Hirose;Rolf Eckmiller
具有光学频率控制行为的相干光学神经网络被认为是复杂的光学神经系统。相干光学神经网络系统由光学复值神经网络、相位参考路径和用于自零差检测的相干检测器组成。以光频率为学习参数，通过调整光神经网络中神经连接的延迟时间和透明度来实现学习过程。还分析了频率空间的泛化能力。讨论了学习过程中的信息几何，以获得在频率空间中实现合理泛化的参数范围。发现延迟时域和输入信号频域均周期性地存在误差函数极小值。因此，为了有意义的概括，初始连接延迟应该在一定范围内。仿真实验表明，在理论获得的参数范围内，成功实现了频域的稳定学习和合理泛化。
Coherent optical neural networks that have optical-frequency-controlled behavior are proposed as sophisticated optical neural systems. The coherent optical neural-network system consists of an optical complex-valued neural network, a phase reference path, and coherent detectors for selfhomodyne detection. The learning process is realized by adjusting the delay time and the transparency of neural connections in the optical neural network with the optical frequency as a learning parameter. Generalization ability in frequency space is also analyzed. Information geometry in the learning process is discussed for obtaining a parameter range in which a reasonable generalization is realized in frequency space. It is found that there are error-function minima periodically both in the delay-time domain and the input-signal-frequency domain. Because of this reason, the initial connection delay should be within a certain range for a meaningful generalization. Simulation experiments demonstrate that a stable learning and a reasonable generalization in the frequency domain are successfully realized in a parameter range obtained in the theory.