Proposal of Carrier-Wave Reservoir Computing
作者： Akira Hirose , Gouhei Tanaka , Seiji Takeda , Toshiyuki Yamane , Hidetoshi Numata
DOI: 10.1007/978-3-030-04167-0_56
关键词:
摘要: Reservoir computing is highly compatible with physical waves such as optical wave and spin wave. In wave-realized reservoir computing, signals are not limited to the raw signals, or baseband but also expressed frequency-shifted having a carrier. This paper proposes architecture, namely, carrier-wave computing. We present its construction suitable learning dynamics which we deal phase information explicitly. The merits of proposed frequency-dependent processing functions, frequency-domain multiplexing ability explicit phase-information utilization. It useful for material evaluation from viewpoint computational in
springer.com
sci-hub.se 参考文章(28)
Chrisantha Fernando, Sampsa Sojakka, Pattern Recognition in a Bucket european conference on artificial life. pp. 588- 597 ,(2003) , 10.1007/978-3-540-39432-7_63
A. Hirose, Continuous complex-valued back-propagation learning Electronics Letters. ,vol. 28, pp. 1854- 1855 ,(1992) , 10.1049/EL:19921186
D. Verstraeten, B. Schrauwen, M. D’Haene, D. Stroobandt, 2007 Special Issue: An experimental unification of reservoir computing methods Neural Networks. ,vol. 20, pp. 391- 403 ,(2007) , 10.1016/J.NEUNET.2007.04.003
Sotaro Kawata, Akira Hirose, None, Frequency-multiplexing ability of complex-valued Hebbian learning in logic gates. International Journal of Neural Systems. ,vol. 18, pp. 173- 184 ,(2008) , 10.1142/S0129065708001488
H. Leung, S. Haykin, The complex backpropagation algorithm IEEE Transactions on Signal Processing. ,vol. 39, pp. 2101- 2104 ,(1991) , 10.1109/78.134446
A. Hirose, R. Eckmiller, Behavior control of coherent-type neural networks by carrier-frequency modulation IEEE Transactions on Neural Networks. ,vol. 7, pp. 1032- 1034 ,(1996) , 10.1109/72.508945
Akira Hirose, Rolf Eckmiller, Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain Applied Optics. ,vol. 35, pp. 836- 843 ,(1996) , 10.1364/AO.35.000836
Herbert Jaeger, Harald Haas, Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication Science. ,vol. 304, pp. 78- 80 ,(2004) , 10.1126/SCIENCE.1091277
Sotaro Kawata, Akira Hirose, None, Coherent optical neural network that learns desirable phase values in the frequency domain by use of multiple optical-path differences Optics Letters. ,vol. 28, pp. 2524- 2526 ,(2003) , 10.1364/OL.28.002524
G.M. Georgiou, C. Koutsougeras, Complex domain backpropagation IEEE Transactions on Circuits and Systems Ii: Analog and Digital Signal Processing. ,vol. 39, pp. 330- 334 ,(1992) , 10.1109/82.142037