IEEE/CAA Journal of Automatica Sinica
Citation:  C. Y. Lee, H. Hasegawa, and S. C. Gao, “Complexvalued neural networks: A comprehensive survey,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 8, pp. 1406–1426, Aug. 2022. doi: 10.1109/JAS.2022.105743 
Complexvalued neural networks (CVNNs) have shown their excellent efficiency compared to their real counterparts in speech enhancement, image and signal processing. Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs. Since CVNNs have proven to have better performance in handling the naturally complexvalued data and signals, this area of study will grow and expect the arrival of some effective improvements in the future. Therefore, there exists an obvious reason to provide a comprehensive survey paper that systematically collects and categorizes the advancement of CVNNs. In this paper, we discuss and summarize the recent advances based on their learning algorithms, activation functions, which is the most challenging part of building a CVNN, and applications. Besides, we outline the structure and applications of complexvalued convolutional, residual and recurrent neural networks. Finally, we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.
[1] 
N. Benvenuto and F. Piazza, “On the complex backpropagation algorithm,” IEEE Trans. Signal Processing, vol. 40, no. 4, pp. 967–969, 1992. doi: 10.1109/78.127967

[2] 
G. Georgiou and C. Koutsougeras, “Complex domain backpropagation,” IEEE Trans. Circuits and Systems II: Analog and Digital Signal Processing, vol. 39, no. 5, pp. 330–334, 1992.

[3] 
H. Leung and S. Haykin, “The complex backpropagation algorithm,” IEEE Trans. Signal Processing, vol. 39, no. 9, pp. 2101–2104, 1991. doi: 10.1109/78.134446

[4] 
P. Virtue, S. X. Yu, and M. Lustig, “Better than real: Complexvalued neural nets for mri fingerprinting,” in Proc. IEEE Int. Conf. Image Processing, 2017, pp. 3953–3957.

[5] 
H. Tsuzuki, M. Kugler, S. Kuroyanagi, and A. Iwata, “An approach for sound source localization by complexvalued neural network,” IEICE Trans. Information and Systems, vol. 96, no. 10, pp. 2257–2265, 2013.

[6] 
S. Sepasi, E. Reihani, A. M. Howlader, L. R. Roose, and M. M. Matsuura, “Very short term load forecasting of a distribution system with high PV penetration,” Renewable Energy, vol. 106, pp. 142–148, 2017. doi: 10.1016/j.renene.2017.01.019

[7] 
H. Akramifard, M. Firouzmand, and R. A. Moghadam, “Extracting, recognizing, and counting white blood cells from microscopic images by using complexvalued neural networks,” Journal of Medical Signals and Sensors, vol. 2, no. 3, p. 169, 2012.

[8] 
A. R. Hafiz, A. Y. AlNuaimi, M. F. Amin, and K. Murase, “Classification of skeletal wireframe representation of hand gesture using complexvalued neural network,” Neural Processing Letters, vol. 42, no. 3, pp. 649–664, 2015. doi: 10.1007/s1106301493790

[9] 
A. Hirose, “Complexvalued neural networks: The merits and their origins,” in Proc. Int. Joint Conf. Neural Networks, 2009, pp. 1237–1244.

[10] 
A. Hirose, ComplexValued Neural Networks, 2nd ed. Springer, 2012.

[11] 
T. Nitta, “Solving the XOR problem and the detection of symmetry using a single complexvalued neuron,” Neural Networks, vol. 16, no. 8, pp. 1101–1105, 2003. doi: 10.1016/S08936080(03)001680

[12] 
A. Hirose, “Nature of complex number and complexvalued neural networks,” Frontiers of Electrical and Electronic Engineering in China, vol. 6, no. 1, pp. 171–180, 2011. doi: 10.1007/s1146001101253

[13] 
A. Hirose, “Recent progress in applications of complexvalued neural networks,” in Proc. Int. Conf. Artificial Intelligence and Soft Computing. Springer, 2010, pp. 42−46.

[14] 
J. Bassey, L. Qian, and X. Li, “A survey of complexvalued neural networks,” ArXiv, vol. abs/2101.12249, 2021.

[15] 
Y. Sunaga, R. Natsuaki, and A. Hirose, “Land form classification and similar landshape discovery by using complexvalued convolutional neural networks,” IEEE Trans. Geoscience and Remote Sensing, vol. 57, no. 10, pp. 7907–7917, 2019. doi: 10.1109/TGRS.2019.2917214

[16] 
P. Arena, L. Fortuna, R. Re, and M. G. Xibilia, “Multilayer perceptrons to approximate complex valued functions,” Int. Journal of Neural Systems, vol. 6, no. 04, pp. 435–446, 1995. doi: 10.1142/S0129065795000299

[17] 
M. F. Amin, R. Savitha, M. I. Amin, and K. Murase, “Complexvalued functional link network design by orthogonal least squares method for function approximation problems,” in Proc. Int. Joint Conf. Neural Networks, 2011, pp. 1489–1496.

[18] 
T. Nitta, “Orthogonality of decision boundaries in complexvalued neural networks,” Neural Computation, vol. 16, no. 1, pp. 73–97, 2004. doi: 10.1162/08997660460734001

[19] 
D. P. Reichert and T. Serre, “Neuronal synchrony in complexvalued deep networks,” in Proc. 2nd Int. Conf. Learning Representations, 2014.

[20] 
R. Savitha, S. Suresh, N. Sundararajan, and P. Saratchandran, “A new learning algorithm with logarithmic performance index for complexvalued neural networks,” Neurocomputing, vol. 72, no. 16–18, pp. 3771–3781, 2009. doi: 10.1016/j.neucom.2009.06.004

[21] 
S.S. Yang, C.L. Ho, and S. Siu, “Sensitivity analysis of the splitcomplex valued multilayer perceptron due to the errors of the i.i.d. inputs and weights,” IEEE Trans. Neural Networks, vol. 18, no. 5, pp. 1280–1293, 2007. doi: 10.1109/TNN.2007.894038

[22] 
H. Zhang, C. Zhang, and W. Wu, “Convergence of batch splitcomplex backpropagation algorithm for complexvalued neural networks,” Discrete Dynamics in Nature and Society, vol. 2009, 2009.

[23] 
D. Jianping, N. Sundararajan, and P. Saratchandran, “Complexvalued minimal resource allocation network for nonlinear signal processing,” Int. Journal of Neural Systems, vol. 10, no. 02, pp. 95–106, 2000. doi: 10.1142/S0129065700000090

[24] 
D. Jianping, N. Sundararajan, and P. Saratchandran, “Communication channel equalization using complexvalued minimal radial basis function neural networks,” IEEE Trans. Neural Networks, vol. 13, no. 3, pp. 687–696, 2002. doi: 10.1109/TNN.2002.1000133

[25] 
M. F. Amin and K. Murase, “Singlelayered complexvalued neural network for realvalued classification problems,” Neurocomputing, vol. 72, no. 4–6, pp. 945–955, 2009. doi: 10.1016/j.neucom.2008.04.006

[26] 
M. Peker, B. Sen, and D. Delen, “Computeraided diagnosis of Parkinsons disease using complexvalued neural networks and mRMR feature selection algorithm,” Journal of Healthcare Engineering, vol. 6, no. 3, pp. 281–302, 2015. doi: 10.1260/20402295.6.3.281

[27] 
A. Hirose, “Proposal of fully complexvalued neural networks,” in Proc. Int. Joint Conf. Neural Networks, vol. 4, 1992, pp. 152–157.

[28] 
M. A. Dedmari, S. Conjeti, S. Estrada, P. Ehses, T. Stöcker, and M. Reuter, “Complex fully convolutional neural networks for MR image reconstruction,” in Machine Learning for Medical Image Reconstruction. Springer Int. Publishing, 2018, pp. 30–38.

[29] 
Z. Zhang, H. Wang, F. Xu, and Y.Q. Jin, “Complexvalued convolutional neural network and its application in polarimetric SAR image classification,” IEEE Trans. Geoscience and Remote Sensing, vol. 55, no. 12, pp. 7177–7188, 2017. doi: 10.1109/TGRS.2017.2743222

[30] 
M.B. Li, G.B. Huang, P. Saratchandran, and N. Sundararajan, “Fully complex extreme learning machine,” Neurocomputing, vol. 68, pp. 306–314, 2005. doi: 10.1016/j.neucom.2005.03.002

[31] 
S. Scardapane, S. Van Vaerenbergh, A. Hussain, and A. Uncini, “Complexvalued neural networks with nonparametric activation functions,” IEEE Trans. Emerging Topics in Computational Intelligence, vol. 4, no. 2, pp. 140–150, 2020. doi: 10.1109/TETCI.2018.2872600

[32] 
T. Kim and T. Adali, “Fully complex backpropagation for constant envelope signal processing,” in Proc. Neural Networks for Signal Processing X. IEEE Signal Processing Society Workshop, vol. 1, 2000, pp. 231–240.

[33] 
N. Guberman, “On complex valued convolutional neural networks,” arXiv preprint arXiv: 1602.09046, 2016.

[34] 
K. Tachibana and K. Otsuka, “Wind prediction performance of complex neural network with ReLU activation function,” in Proc. 57th Annu. Conf. Society of Instrument and Control Engineers of Japan, 2018, pp. 1029–1034.

[35] 
B. Widrow, J. McCool, and M. Ball, “The complex LMS algorithm,” Proc. the IEEE, vol. 63, no. 4, pp. 719–720, 1975. doi: 10.1109/PROC.1975.9807

[36] 
M. Arjovsky, A. Shah, and Y. Bengio, “Unitary evolution recurrent neural networks,” in Proc. 33rd Int. Conf. Machine Learning, ser. Proc. Machine Learning Research, vol. 48, 2016, pp. 1120–1128.

[37] 
A. Hirose, “Continuous complexvalued backpropagation learning,” Electronics Letters, vol. 28, no. 20, pp. 1854–1855, 1992. doi: 10.1049/el:19921186

[38] 
C. You and D. Hong, “Nonlinear blind equalization schemes using complexvalued multilayer feedforward neural networks,” IEEE Trans. Neural Networks, vol. 9, no. 6, pp. 1442–1455, 1998. doi: 10.1109/72.728394

[39] 
Y. Özbay, “A new approach to detection of ECG arrhythmias: Complex discrete wavelet transform based complex valued artificial neural network,” Journal of Medical Systems, vol. 33, no. 6, p. 435, 2009.

[40] 
H. A. Jalab and R. W. Ibrahim, “New activation functions for complexvalued neural network,” Int. Journal of Physical Sciences, vol. 6, no. 7, pp. 1766–1772, 2011.

[41] 
N. Benvenuto, M. Marchesi, F. Piazza, and A. Uncini, “Non linear satellite radio links equalized using blind neural networks,” in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, 1991, pp. 1521–1524.

[42] 
T. Nitta, “An extension of the backpropagation algorithm to complex numbers,” Neural Networks, vol. 10, no. 8, pp. 1391–1415, 1997. doi: 10.1016/S08936080(97)000361

[43] 
T. Nitta, ComplexValued Neural Networks: Utilizing HighDimensional Parameters: Utilizing HighDimensional Parameters. IGI Global, 2009.

[44] 
H. G. Zimmermann, A. Minin, and V. Kusherbaeva, “Comparison of the complex valued and real valued neural networks trained with gradient descent and random search algorithms,” in Proc. ESANN, 2011.

[45] 
K. Venkatanareshbabu, S. Nisheel, R. Sakthivel, and K. Muralitharan, “Novel elegant fuzzy genetic algorithms in classification problems,” Soft Computing, vol. 23, no. 14, pp. 5583–5603, 2019. doi: 10.1007/s0050001832168

[46] 
L. Zhang, H. Dong, and B. Zou, “Efficiently utilizing complexvalued PolSAR image data via a multitask deep learning framework,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 157, pp. 59–72, 2019. doi: 10.1016/j.isprsjprs.2019.09.002

[47] 
E. C. Yeats, Y. Chen, and H. Li, “Improving gradient regularization using complexvalued neural networks,” in Proc. Int. Conf. Machine Learning, 2021, pp. 11953–11963.

[48] 
Y.F. Pu, X. Xie, J. Cao, H. Chen, K. Zhang, and J. Wang, “An input weights dependent complexvalued learning algorithm based on wirtinger calculus,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 52, no. 5, pp. 2920–2932, 2022. doi: 10.1109/TSMC.2021.3055501

[49] 
T. Nitta, “Learning dynamics of a single polar variable complexvalued neuron,” Neural Computation, vol. 27, no. 5, pp. 1120–1141, 2015. doi: 10.1162/NECO_a_00729

[50] 
C.A. Popa, “Enhanced gradient descent algorithms for complexvalued neural networks,” in Proc. IEEE 16th Int. Symp. Symbolic and Numeric Algorithms for Scientific Computing, 2014, pp. 272–279.

[51] 
T. Nakama, “Theoretical analysis of batch and online training for gradient descent learning in neural networks,” Neurocomputing, vol. 73, no. 1–3, pp. 151–159, 2009. doi: 10.1016/j.neucom.2009.05.017

[52] 
D. R. Wilson and T. R. Martinez, “The general inefficiency of batch training for gradient descent learning,” Neural Networks, vol. 16, no. 10, pp. 1429–1451, 2003. doi: 10.1016/S08936080(03)001382

[53] 
H. Zhang, Y. Zhang, S. Zhu, and D. Xu, “Deterministic convergence of complex minibatch gradient learning algorithm for fully complexvalued neural networks,” Neurocomputing, vol. 407, pp. 185–193, 2020. doi: 10.1016/j.neucom.2020.04.114

[54] 
C.A. Popa, “Quasinewton learning methods for complexvalued neural networks,” in Proc. Int. Joint Conf. Neural Networks, 2015, pp. 1–8.

[55] 
D. Xu, J. Dong, and C. Zhang, “Convergence of quasinewton method for fully complexvalued neural networks,” Neural Processing Letters, vol. 46, no. 3, pp. 961–968, 2017. doi: 10.1007/s1106301796217

[56] 
M. J. Kidger, “Use of the LevenbergMarquardt (damped leastsquares) optimization method in lens design,” Optical Engineering, vol. 32, no. 8, pp. 1731–1739, 1993. doi: 10.1117/12.145076

[57] 
M. F. Amin, M. I. Amin, A. Y. H. AlNuaimi, and K. Murase, “Wirtinger calculus based gradient descent and LevenbergMarquardt learning algorithms in complexvalued neural networks,” in Proc. Int. Conf. Neural Information Processing. Springer, 2011, pp. 550–559.

[58] 
G.B. Huang, M.B. Li, L. Chen, and C.K. Siew, “Incremental extreme learning machine with fully complex hidden nodes,” Neurocomputing, vol. 71, no. 4–6, pp. 576–583, 2008. doi: 10.1016/j.neucom.2007.07.025

[59] 
R. Savitha, S. Suresh, and N. Sundararajan, “Fast learning circular complexvalued extreme learning machine (CCELM) for realvalued classification problems,” Information Sciences, vol. 187, pp. 277–290, 2012. doi: 10.1016/j.ins.2011.11.003

[60] 
M. Sivachitra, R. Savitha, S. Suresh, and S. Vijayachitra, “A fully complexvalued fast learning classifier (FCFLC) for realvalued classification problems,” Neurocomputing, vol. 149, pp. 198–206, 2015. doi: 10.1016/j.neucom.2014.04.075

[61] 
S. Shukla and R. N. Yadav, “Regularized weighted circular complexvalued extreme learning machine for imbalanced learning,” IEEE Access, vol. 3, pp. 3048–3057, 2015. doi: 10.1109/ACCESS.2015.2506601

[62] 
W. Zong, G.B. Huang, and Y. Chen, “Weighted extreme learning machine for imbalance learning,” Neurocomputing, vol. 101, pp. 229–242, 2013. doi: 10.1016/j.neucom.2012.08.010

[63] 
L. Jiang, H. Y. Huang, and Z. H. Ding, “Path planning for intelligent robots based on deep Qlearning with experience replay and heuristic knowledge,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 4, pp. 1179–1189, 2020. doi: 10.1109/JAS.2019.1911732

[64] 
C. Liu, F. Zhu, Q. Liu, and Y. Fu, “Hierarchical reinforcement learning with automatic subgoal identification,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 10, pp. 1686–1696, 2021. doi: 10.1109/JAS.2021.1004141

[65] 
T. Hamagami, T. Shibuya, and S. Shimada, “Complexvalued reinforcement learning,” in Proc. IEEE Int. Conf. Systems, Man and Cybernetics, vol. 5, 2006, pp. 4175–4179.

[66] 
T. Shibuya and T. Hamagami, ComplexValued Reinforcement Learning: A ContextBased Approach for POMDPs. Intechopen, 2011, pp. 255–274.

[67] 
T. Shibuya, H. Arita, and T. Hamagami, “Reinforcement learning in continuous state space with perceptual aliasing by using complexvalued RBF network,” in Proc. IEEE Int. Conf. Systems, Man and Cybernetics, 2010, pp. 1799–1803.

[68] 
M. Mochida, H. Nakano, and A. Miyauchi, “A complexvalued reinforcement learning method using complexvalued neural networks,” IEICE Technical Report, vol. 117, no. 112, pp. 1–5, 2017.

[69] 
R. Isaacson and F. Fujita, “Metacognitive knowledge monitoring and selfregulated learning,” Journal of the Scholarship of Teaching and Learning, pp. 39–55, 2006.

[70] 
R. Savitha, S. Suresh, and N. Sundararajan, “Metacognitive learning in a fully complexvalued radial basis function neural network,” Neural Computation, vol. 24, no. 5, pp. 1297–1328, 2012. doi: 10.1162/NECO_a_00254

[71] 
S. Suresh, R. Savitha, and N. Sundararajan, “A sequential learning algorithm for complexvalued selfregulating resource allocation networkCSRAN,” IEEE Trans. Neural Networks, vol. 22, no. 7, pp. 1061–1072, 2011. doi: 10.1109/TNN.2011.2144618

[72] 
S. Suresh, R. Savitha, and N. Sundararajan, “A fast learning fully complexvalued relaxation network (FCRN),” in Proc. IEEE Int. Joint Conf. Neural Networks, 2011, pp. 1372–1377.

[73] 
S.S. Yu and W.H. Tsai, “Relaxation by the hopfield neural network,” Pattern Recognition, vol. 25, no. 2, pp. 197–209, 1992. doi: 10.1016/00313203(92)90101N

[74] 
Y. Zhang and H. Huang, “Adaptive complexvalued stepsize based fast learning of complexvalued neural networks,” Neural Networks, vol. 124, pp. 233–242, 2020. doi: 10.1016/j.neunet.2020.01.011

[75] 
Z. Dong and H. Huang, “A training algorithm with selectable search direction for complexvalued feedforward neural networks,” Neural Networks, vol. 137, pp. 75–84, 2021. doi: 10.1016/j.neunet.2021.01.014

[76] 
T. Takase, S. Oyama, and M. Kurihara, “Effective neural network training with adaptive learning rate based on training loss,” Neural Networks, vol. 101, pp. 68–78, 2018. doi: 10.1016/j.neunet.2018.01.016

[77] 
L. Vecci, F. Piazza, and A. Uncini, “Learning and approximation capabilities of adaptive spline activation function neural networks,” Neural Networks, vol. 11, no. 2, pp. 259–270, 1998. doi: 10.1016/S08936080(97)001184

[78] 
M. Scarpiniti, D. Vigliano, R. Parisi, and A. Uncini, “Generalized splitting functions for blind separation of complex signals,” Neurocomputing, vol. 71, no. 10–12, pp. 2245–2270, 2008. doi: 10.1016/j.neucom.2007.07.037

[79] 
T. Kim and T. Adalı, “Approximation by fully complex multilayer perceptrons,” Neural Computation, vol. 15, no. 7, pp. 1641–1666, 2003. doi: 10.1162/089976603321891846

[80] 
N. Mönning and S. Manandhar, “Evaluation of complexvalued neural networks on realvalued classification tasks,” arXiv preprint arXiv: 1811.12351, 2018.

[81] 
C. Trabelsi, O. Bilaniuk, Y. Zhang, D. Serdyuk, S. Subramanian, J. F. Santos, S. Mehri, N. Rostamzadeh, Y. Bengio, and C. J. Pal, “Deep complex networks,” in Proc. Int. Conf. Learning Representations, 2018.

[82] 
S. Goh, M. Chen, D. Popović, K. Aihara, D. Obradovic, and D. Mandic, “Complexvalued forecasting of wind profile,” Renewable Energy, vol. 31, no. 11, pp. 1733–1750, 2006. doi: 10.1016/j.renene.2005.07.006

[83] 
E. Kalnay, M. Kanamitsu, R. Kistler, W. Collins, D. Deaven, L. Gandin, M. Iredell, S. Saha, G. White, J. Woollen, Y. Zhu, M. Chelliah, W. Ebisuzaki, W. Higgins, J. Janowiak, K. C. Mo, C. Ropelewski, J. Wang, A. Leetmaa, R. Reynolds, R. Jenne, and D. Joseph, “The NCEP/NCAR 40year reanalysis project,” Bulletin of the American Meteorological Society, vol. 77, no. 3, pp. 437–472, 1996. doi: 10.1175/15200477(1996)077<0437:TNYRP>2.0.CO;2

[84] 
Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, “Handwritten digit recognition with a backpropagation network,” in Advances in Neural Information Processing Systems, D. Touretzky, Ed., vol. 2. MorganKaufmann, 1990, pp. 396–404.

[85] 
Y. LeCun, K. Kavukcuoglu, and C. Farabet, “Convolutional networks and applications in vision,” in Proc. IEEE Int. Symp. Circuits and Systems, 2010, pp. 253–256.

[86] 
Y. LeCun, “Convolutional networks for images, speech, and time series,” The Handbook of Brain Theory and Neural Networks, pp. 255–258, 1995.

[87] 
P. M. Kebria, A. Khosravi, S. M. Salaken, and S. Nahavandi, “Deep imitation learning for autonomous vehicles based on convolutional neural networks,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 1, pp. 82–95, 2020. doi: 10.1109/JAS.2019.1911825

[88] 
P. Moeskops, M. A. Viergever, A. M. Mendrik, L. S. de Vries, M. J. N. L. Benders, and I. Išgum, “Automatic segmentation of MR brain images with a convolutional neural network,” IEEE Trans. Medical Imaging, vol. 35, no. 5, pp. 1252–1261, 2016. doi: 10.1109/TMI.2016.2548501

[89] 
E. K. Cole, J. Pauly, and J. Cheng, “Complexvalued convolutional neural networks for MRI reconstruction,” in Proc. 27th Annu. Meeting of ISMRM, Montreal, Canada, 2019, p. 4714.

[90] 
I. Danihelka, G. Wayne, B. Uria, N. Kalchbrenner, and A. Graves, “Associative long shortterm memory,” in Proc. 33rd Int. Conf. Machine Learning, vol. 48, 2016, pp. 1986–1994.

[91] 
W. Rawat and Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural Computation, vol. 29, no. 9, pp. 2352–2449, 2017. doi: 10.1162/neco_a_00990

[92] 
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. doi: 10.1038/nature14539

[93] 
S. Wang, H. Cheng, L. Ying, T. Xiao, Z. Ke, H. Zheng, and D. Liang, “DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution,” Magnetic Resonance Imaging, vol. 68, pp. 136–147, 2020. doi: 10.1016/j.mri.2020.02.002

[94] 
P. Virtue, “Complexvalued deep learning with applications to magnetic resonance image synthesis,” Ph.D. dissertation, EECS Department, University of California, Berkeley, Aug. 2019.

[95] 
J. Zhang and Y. Wu, “Complexvalued unsupervised convolutional neural networks for sleep stage classification,” Computer Methods and Programs in Biomedicine, vol. 164, pp. 181–191, 2018. doi: 10.1016/j.cmpb.2018.07.015

[96] 
M. Wilmanski, C. Kreucher, and A. Hero, “Complex input convolutional neural networks for wide angle SAR ATR,” in Proc. IEEE Global Conf. Signal and Information Processing, 2016, pp. 1037–1041.

[97] 
A. Marseet and F. Sahin, “Application of complexvalued convolutional neural network for next generation wireless networks,” in Proc. IEEE Western New York Image and Signal Processing Workshop, 2017, pp. 1–5.

[98] 
J. Gao, B. Deng, Y. Qin, H. Wang, and X. Li, “Enhanced radar imaging using a complexvalued convolutional neural network,” IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 1, pp. 35–39, 2019. doi: 10.1109/LGRS.2018.2866567

[99] 
X. Wang and H. Wang, “Forest height mapping using complexvalued convolutional neural network,” IEEE Access, vol. 7, pp. 126 334–126 343, 2019. doi: 10.1109/ACCESS.2019.2938896

[100] 
Z. Chang, Y. Wang, H. Li, and Z. Wang, “Complex CNNbased equalization for communication signal,” in Proc. IEEE 4th Int. Conf. Signal and Image Processing, 2019, pp. 513–517.

[101] 
H.S. Choi, J. Kim, J. Huh, A. Kim, J.W. Ha, and K. Lee, “Phaseaware speech enhancement with deep complex UNet,” in Proc. Int. Conf. Learning Representations, 2019.

[102] 
L. Yu, Y. Hu, X. Xie, Y. Lin, and W. Hong, “Complexvalued full convolutional neural network for SAR target classification,” IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 10, pp. 1752–1756, 2020. doi: 10.1109/LGRS.2019.2953892

[103] 
X. Wang, P. Chen, H. Xie, and G. Cui, “Throughwall human activity classification using complexvalued convolutional neural network,” in Proc. IEEE Radar Conf., 2021, pp. 1–4.

[104] 
Y. Zhang, Q. Hua, Y. Jiang, H. Li, and D. Xu, “CvMotionNet: Complexvalued convolutional neural network for SAR moving ship targets classification,” in Proc. IEEE Int. Geoscience and Remote Sensing Symp., 2021, pp. 4280–4283.

[105] 
H. Mu, Y. Zhang, Y. Jiang, and C. Ding, “CVGMTINet: GMTI using a deep complexvalued convolutional neural network for multichannel SARGMTI system,” IEEE Trans. Geoscience and Remote Sensing, pp. 1–15, 2021.

[106] 
Y. Sunaga, R. Natsuaki, and A. Hirose, “Similar landform discovery: Complex absolutevalue max pooling in complexvalued convolutional neural networks in interferometric synthetic aperture radar,” in Proc. Int. Joint Conf. Neural Networks, 2020, pp. 1–7.

[107] 
J. Hu and J. Wang, “Global stability of complexvalued recurrent neural networks with timedelays,” IEEE Trans. Neural Networks and Learning Systems, vol. 23, no. 6, pp. 853–865, 2012. doi: 10.1109/TNNLS.2012.2195028

[108] 
Z. Zhang, C. Lin, and B. Chen, “Global stability criterion for delayed complexvalued recurrent neural networks,” IEEE Trans. Neural Networks and Learning Systems, vol. 25, no. 9, pp. 1704–1708, 2013.

[109] 
Y. Huang, H. Zhang, and Z. Wang, “Multistability of complexvalued recurrent neural networks with realimaginarytype activation functions,” Applied Mathematics and Computation, vol. 229, pp. 187–200, 2014. doi: 10.1016/j.amc.2013.12.027

[110] 
T. Fang and J. Sun, “Stability of complexvalued recurrent neural networks with timedelays,” IEEE Trans. Neural Networks and Learning Systems, vol. 25, no. 9, pp. 1709–1713, 2014. doi: 10.1109/TNNLS.2013.2294638

[111] 
A. M. Sarroff, V. Shepardson, and M. A. Casey, “Learning representations using complexvalued nets,” arXiv preprint arXiv: 1511.06351, 2015.

[112] 
Z. Liu, W. Gao, Y.H. Wan, and E. Muljadi, “Wind power plant prediction by using neural networks,” in Proc. IEEE Energy Conversion Congress and Exposition, 2012, pp. 3154–3160.

[113] 
M. Kataoka, M. Kinouchi, and M. Hagiwara, “Music information retrieval system using complexvalued recurrent neural networks,” in Proc. SMC’98 IEEE Int. Conf. Systems, Man, and Cybernetics, vol. 5, 1998, pp. 4290–4295.

[114] 
M. Kinouchi and M. Hagiwara, “Memorization of melodies using complexvalued recurrent neural network,” in ComplexValued Neural Networks: Theories and Applications. World Scientific, 2003, pp. 205–226.

[115] 
I. Shafran, T. Bagby, and R. J. SkerryRyan, “Complex evolution recurrent neural networks (ceRNNs),” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, 2018, pp. 5854–5858.

[116] 
X. Wang, H. Lin, J. Lu, and T. Yahagi, “Channel equalization using complexvalued recurrent neural network,” in Proc. Int. Conf. InfoTech and InfoNet, vol. 3, 2001, pp. 498–503.

[117] 
M. Lv, W. Xu, and T. Chen, “A hybrid deep convolutional and recurrent neural network for complex activity recognition using multimodal sensors,” Neurocomputing, vol. 362, pp. 33–40, 2019. doi: 10.1016/j.neucom.2019.06.051

[118] 
S. Wisdom, T. Powers, J. Hershey, J. Le Roux, and L. Atlas, “Fullcapacity unitary recurrent neural networks,” in Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett, Eds., vol. 29. Curran Associates, Inc., 2016, pp. 4880–4888.

[119] 
S. Wang, H. Cheng, Z. Ke, L. Ying, X. Liu, H. Zheng, and D. Liang, “Complexvalued residual network learning for parallel MR imaging,” in Proc. 26th Annu. Meeting of ISMRM, Paris, France, 2018.

[120] 
Z. Zheng, S. Wang, S. Li, W. Dai, J. Zou, F. Li, and H. Xiong, “DSCRNet: A diffractive sensing and complexvalued reconstruction network for compressive sensing,” in Proc. IEEE Int. Symp. Circuits and Systems, 2020, pp. 1–5.

[121] 
R. Chakraborty, Y. Xing, and S. X. Yu, “SurReal: Complexvalued learning as principled transformations on a scaling and rotation manifold,” IEEE Trans. Neural Networks and Learning Systems, pp. 1–12, 2020.

[122] 
C.A. Popa, “Complexvalued deep belief networks,” in Advances in Neural Networks  ISNN 2018, T. Huang, J. Lv, C. Sun, and A. V. Tuzikov, Eds. Cham: Springer Int. Publishing, pp. 72–78.

[123] 
T. Nakashika, S. Takaki, and J. Yamagishi, “Complexvalued restricted Boltzmann machine for direct learning of frequency spectra,” in Proc. Interspeech, 2017, pp. 4021–4025.

[124] 
Q. Sun, X. Li, L. Li, X. Liu, F. Liu, and L. Jiao, “Semisupervised complexvalued GAN for polarimetric SAR image classification,” in Proc. IEEE Int. Geoscience and Remote Sensing Symp., 2019, pp. 3245–3248.

[125] 
B. Vasudeva, P. Deora, S. Bhattacharya, and P. M. Pradhan, “CoVeGAN: Complexvalued generative adversarial network for compressive sensing MR image reconstruction,” arXiv preprint arXiv: 2002.10523, 2020.

[126] 
X. Li, Q. Sun, L. Li, X. Liu, H. Liu, L. Jiao, and F. Liu, “SSCVGANs: Semisupervised complexvalued GANs for PolSAR image classification,” IEEE Access, vol. 8, pp. 146 560–146 576, 2020. doi: 10.1109/ACCESS.2020.3004591

[127] 
C.A. Popa, “Complexvalued stacked denoising autoencoders,” in Advances in Neural Networks  ISNN 2018, T. Huang, J. Lv, C. Sun, and A. V. Tuzikov, Eds. Cham: Springer Int. Publishing, pp. 64–71.

[128] 
X. Cheng, J. He, J. He, and H. Xu, “CvCapsNet: Complexvalued capsule network,” IEEE Access, vol. 7, pp. 85492–85499, 2019. doi: 10.1109/ACCESS.2019.2924548

[129] 
J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, and T. Chen, “Recent advances in convolutional neural networks,” Pattern Recognition, vol. 77, pp. 354–377, 2018. doi: 10.1016/j.patcog.2017.10.013

[130] 
C.A. Popa, “Complexvalued convolutional neural networks for realvalued image classification,” in Proc. IEEE Int. Joint Conf. Neural Networks, 2017, pp. 816–822.

[131] 
R. Jiao, K. Peng, and J. Dong, “Remaining useful life prediction for a roller in a hot strip mill based on deep recurrent neural networks,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1345–1354, 2021. doi: 10.1109/JAS.2021.1004051

[132] 
A. Kumar and R. Rastogi nee Khemchandani, “Selfattention enhanced recurrent neural networks for sentence classification,” in Proc. IEEE Symp. Series on Computational Intelligence, 2018, pp. 905–911.

[133] 
K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoderdecoder for statistical machine translation,” in Proc. Conf. Empirical Methods in Natural Language Processing, pp. 1724–1734, 2014.

[134] 
L. Jing, Y. Shen, T. Dubček, J. Peurifoi, S. Skirlo, Y. LeCun, M. Tegmark, and M. Soljačić, “Tunable efficient unitary neural networks (EUNN) and their application to RNN,” in Proc. 34th Int. Conf. Machine Learning, vol. 70, 2017, pp. 1733–1741.

[135] 
M. Wolter and A. Yao, “Complex gated recurrent neural networks,” in Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc., 2018, pp. 10536–10546.

[136] 
B. Wang, Y. Lei, T. Yan, N. Li, and L. Guo, “Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery,” Neurocomputing, vol. 379, pp. 117–129, 2020. doi: 10.1016/j.neucom.2019.10.064

[137] 
J. CalvoZaragoza, A. H. Toselli, and E. Vidal, “Handwritten music recognition for mensural notation with convolutional recurrent neural networks,” Pattern Recognition Letters, vol. 128, pp. 115–121, 2019. doi: 10.1016/j.patrec.2019.08.021

[138] 
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2016, pp. 770–778.

[139] 
V. Kumar, “Detection of microcalcifications in digital mammogram using curvelet fractal texture features,” European Journal of Molecular &Clinical Medicine, vol. 7, no. 2, pp. 251–256, 2020.

[140] 
L. Guo, G. Song, and H. Wu, “Complexvalued Pix2pix–deep neural network for nonlinear electromagnetic inverse scattering,” Electronics, vol. 10, no. 6, 2021.

[141] 
W. Xie, G. Ma, F. Zhao, H. Liu, and L. Zhang, “PolSAR image classification via a novel semisupervised recurrent complexvalued convolution neural network,” Neurocomputing, vol. 388, pp. 255–268, 2020. doi: 10.1016/j.neucom.2020.01.020

[142] 
E. C. Kiziltas, A. Uzun, and E. Yılmaz, “Skin segmentation by using complex valued neural network with HSV color spaces,” Int. Journal of Multidisciplinary Studies and Innovative Technologies, vol. 3, no. 1, pp. 1–4, 2019.

[143] 
H. Zhang, M. Gu, X. Jiang, J. Thompson, H. Cai, et al., “An optical neural chip for implementing complexvalued neural network,” Nature Communications, vol. 12, no. 1, pp. 1–11, 2021. doi: 10.1038/s4146702020314w

[144] 
S. Gao, M. Zhou, Z. Wang, D. Sugiyama, J. Cheng, J. Wang, and Y. Todo, “Fully complexvalued dendritic neuron model,” IEEE Trans. Neural Networks and Learning Systems, 2021. DOI: 10.1109/TNNLS.2021.3105901

[145] 
M. Ceylan and H. Yaşar, “A novel approach for automatic blood vessel extraction in retinal images: complex rippletI transform and complex valued artificial neural network,” Turkish Journal of Electrical Engineering &Computer Sciences, vol. 24, no. 4, pp. 3212–3227, 2016.

[146] 
M. Peker, “A new approach for automatic sleep scoring: Combining Taguchi based complexvalued neural network and complex wavelet transform,” Computer Methods and Programs in Biomedicine, vol. 129, pp. 203–216, 2016. doi: 10.1016/j.cmpb.2016.01.001

[147] 
Z. Nafisah, F. Rachmadi, and E. M. Imah, “Face recognition using complex valued backpropagation,” Jurnal Ilmu Komputer dan Informasi, vol. 11, no. 2, pp. 103–109, 2018. doi: 10.21609/jiki.v11i2.617

[148] 
S. Amilia, M. D. Sulistiyo, and R. N. Dayawati, “Face imagebased gender recognition using complexvalued neural network,” in Proc. IEEE 3rd Int. Conf. Information and Communication Technology, 2015, pp. 201–206.

[149] 
A. R. Hafiz, M. F. Amin, and K. Murase, “Realtime hand gesture recognition using complexvalued neural network (CVNN),” in Neural Information Processing, B.L. Lu, L. Zhang, and J. Kwok, Eds. Springer Berlin Heidelberg, 2011, pp. 541–549.

[150] 
M. Çelebi and M. Ceylan, “A new approach for openclose eye states detection: Complex wavelet transform and complexvalued ANN,” in Proc. IEEE 18th Signal Processing and Communications Applications Conf., 2010, pp. 673–676.

[151] 
R. Shang, G. Wang, M. A Okoth, and L. Jiao, “Complexvalued convolutional autoencoder and spatial pixelsquares refinement for polarimetric SAR image classification,” Remote Sensing, vol. 11, no. 5, Article No. 522, 2019. doi: 10.3390/rs11050522

[152] 
M. Meyer, G. Kuschk, and S. Tomforde, “Complexvalued convolutional neural networks for automotive scene classification based on rangebeamdoppler tensors,” in Proc. IEEE 23rd Int. Conf. Intelligent Transportation Systems, 2020, pp. 1–6.

[153] 
M. Yuan, W. Wang, Z. Wang, X. Luo, and J. Kurths, “Exponential synchronization of delayed memristorbased uncertain complexvalued neural networks for image protection,” IEEE Trans. Neural Networks and Learning Systems, vol. 32, no. 1, pp. 151–165, 2021. doi: 10.1109/TNNLS.2020.2977614

[154] 
M. Ceylan, Y. Özbay, O. N. Uçan, and E. Yildirim, “A novel method for lung segmentation on chest CT images: Complexvalued artificial neural network with complex wavelet transform,” Turkish Journal of Electrical Engineering &Computer Sciences, vol. 18, no. 4, pp. 613–624, 2010.

[155] 
M. Ceylan and H. Yaçar, “Blood vessel extraction from retinal images using complex wavelet transform and complexvalued artificial neural network,” in Proc. 36th Int. Conf. Telecommunications and Signal Processing, 2013, pp. 822–825.

[156] 
D. Saraswathi and E. Srinivasan, “An ensemble approach to diagnose breast cancer using fully complexvalued relaxation neural network classifier,” Int. Journal of Biomedical Engineering and Technology, vol. 15, no. 3, pp. 243–260, 2014. doi: 10.1504/IJBET.2014.064651

[157] 
A. Z. Shirazi, S. J. S. M. Chabok, and Z. Mohammadi, “A novel and reliable computational intelligence system for breast cancer detection,” Medical &Biological Engineering &Computing, vol. 56, no. 5, pp. 721–732, 2018.

[158] 
O. Ronneberger, P. Fischer, and T. Brox, “Unet: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and ComputerAssisted InterventionMICCAI 2015. Springer, pp. 234–241.

[159] 
S. Diamond, V. Sitzmann, F. Heide, and G. Wetzstein, “Unrolled optimization with deep priors,” arXiv preprint arXiv: 1705.08041, 2017.

[160] 
A. Hirose, R. Nakane, and G. Tanaka, “Keynote speech: Information processing hardware, physical reservoir computing and complexvalued neural networks,” in Proc. IEEE Int. Meeting for Future of Electron Devices, Kansai, 2019, pp. 19–24.

[161] 
A. K. Alexandridis and A. D. Zapranis, “Wavelet neural networks: A practical guide,” Neural Networks, vol. 42, pp. 1–27, 2013. doi: 10.1016/j.neunet.2013.01.008

[162] 
P. Ö. Bakbak and M. Peker, “Classification of sonar echo signals in their reduced sparse forms using complexvalued wavelet neural network,” Neural Computing and Applications, pp. 1–11, 2018.

[163] 
L. S. Saoud, F. Rahmoune, V. Tourtchine, and K. Baddari, “Fully complex valued wavelet network for forecasting the global solar irradiation,” Neural Processing Letters, vol. 45, no. 2, pp. 475–505, 2017. doi: 10.1007/s1106301695377

[164] 
J. Stankowicz, J. Robinson, J. M. Carmack, and S. Kuzdeba, “Complex neural networks for radio frequency fingerprinting,” in Proc. IEEE Western New York Image and Signal Processing Workshop, 2019, pp. 1–5.

[165] 
M. Peker, B. Sen, and D. Delen, “A novel method for automated diagnosis of epilepsy using complexvalued classifiers,” IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 1, pp. 108–118, 2016. doi: 10.1109/JBHI.2014.2387795

[166] 
I. Aizenberg and Z. Khaliq, “Analysis of EEG using multilayer neural network with multivalued neurons,” in Proc. IEEE 2nd Int. Conf. Data Stream Mining & Processing, 2018, pp. 392–396.

[167] 
I. Aizenberg, ComplexValued Neural Networks With MultiValued Neurons. Springer, 2011, vol. 353.

[168] 
S. Hu, S. Nagae, and A. Hirose, “Millimeterwave adaptive glucose concentration estimation with complexvalued neural networks,” IEEE Trans. Biomedical Engineering, vol. 66, no. 7, pp. 2065–2071, 2018.

[169] 
D. Hayakawa, T. Masuko, and H. Fujimura, “Applying complexvalued neural networks to acoustic modeling for speech recognition,” in Proc. IEEE AsiaPacific Signal and Information Processing Association Annu. Summit and Conf., 2018, pp. 1725–1731.

[170] 
L. Drude, B. Raj, and R. HaebUmbach, “On the appropriateness of complexvalued neural networks for speech enhancement,” in Interspeech, 2016, pp. 1745–1749.

[171] 
S. Gokul, M. Sivachitra, and S. Vijayachitra, “Parkinson’s disease prediction using machine learning approaches,” in Proc. IEEE 5th Int. Conf. Advanced Computing, 2013, pp. 246–252.

[172] 
H. Gürüler, “A novel diagnosis system for parkinson’s disease using complexvalued artificial neural network with kmeans clustering feature weighting method,” Neural Computing and Applications, vol. 28, no. 7, pp. 1657–1666, 2017. doi: 10.1007/s0052101521422

[173] 
T. Kitajima and T. Yasuno, “Output prediction of wind power generation system using complexvalued neural network,” in Proc. IEEE SICE Annu. Conf., 2010, pp. 3610–3613.

[174] 
H. H. Çevik, Y. E. Acar, and M. Çunkaş, “Day ahead wind power forecasting using complex valued neural network,” in Proc. IEEE Int. Conf. Smart Energy Systems and Technologies, 2018, pp. 1–6.

[175] 
E. Sathish, M. Sivachitra, R. Savitha, and S. Vijayachitra, “Wind profile prediction using a metacognitive fully complexvalued neural network,” in Proc. IEEE 4th Int. Conf. Advanced Computing, 2012, pp. 1–6.

[176] 
D. Wang and J. Huang, “Neural networkbased adaptive dynamic surface control for a class of uncertain nonlinear systems in strictfeedback form,” IEEE Trans. Neural Networks, vol. 16, no. 1, pp. 195–202, 2005. doi: 10.1109/TNN.2004.839354

[177] 
L. Kong, W. He, C. Yang, Z. Li, and C. Sun, “Adaptive fuzzy control for coordinated multiple robots with constraint using impedance learning,” IEEE Trans. Cybernetics, vol. 49, no. 8, pp. 3052–3063, 2019. doi: 10.1109/TCYB.2018.2838573

[178] 
L. Kong, W. He, Y. Dong, L. Cheng, C. Yang, and Z. Li, “Asymmetric bounded neural control for an uncertain robot by state feedback and output feedback,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 51, no. 3, pp. 1735–1746, 2021.

[179] 
S. Slama, A. Errachdi, and M. Benrejeb, “Model reference adaptive control for MIMO nonlinear systems using RBF neural networks,” in Proc. IEEE Int. Conf. Advanced Systems and Electric Technologies, 2018, pp. 346–351.

[180] 
X. Li and J. Cao, “An impulsive delay inequality involving unbounded timevarying delay and applications,” IEEE Trans. Automatic Control, vol. 62, no. 7, pp. 3618–3625, 2017. doi: 10.1109/TAC.2017.2669580

[181] 
T. Dong, X. Liao, and A. Wang, “Stability and hopf bifurcation of a complexvalued neural network with two time delays,” Nonlinear Dynamics, vol. 82, no. 1, pp. 173–184, 2015.

[182] 
Y. Kan, J. Lu, J. Qiu, and J. Kurths, “Exponential synchronization of timevarying delayed complexvalued neural networks under hybrid impulsive controllers,” Neural Networks, vol. 114, pp. 157–163, 2019. doi: 10.1016/j.neunet.2019.02.006

[183] 
H. Zhang, X.Y. Wang, and X.H. Lin, “Synchronization of complexvalued neural network with sliding mode control,” Journal of the Franklin Institute, vol. 353, no. 2, pp. 345–358, 2016. doi: 10.1016/j.jfranklin.2015.11.014

[184] 
X. Wang, Z. Wang, Q. Song, H. Shen, and X. Huang, “A waitingtimebased eventtriggered scheme for stabilization of complexvalued neural networks,” Neural Networks, vol. 121, pp. 329–338, 2020. doi: 10.1016/j.neunet.2019.09.032

[185] 
H. Bao and J. H. Park, “Adaptive synchronization of complexvalued neural networks with time delay,” in Proc. IEEE 8th Int. Conf. Advanced Computational Intelligence, 2016, pp. 283–288.

[186] 
J. Hu and C. Zeng, “Adaptive exponential synchronization of complexvalued CohenGrossberg neural networks with known and unknown parameters,” Neural Networks, vol. 86, pp. 90–101, 2017. doi: 10.1016/j.neunet.2016.11.001

[187] 
P. Wan, J. Jian, and J. Mei, “Periodically intermittent control strategies for αexponential stabilization of fractionalorder complexvalued delayed neural networks,” Nonlinear Dynamics, vol. 92, no. 2, pp. 247–265, 2018. doi: 10.1007/s1107101840530

[188] 
R. Ji, S. Zhang, L. Zheng, Q. Liu, and A. S. Iftikhar, “Prediction of soil moisture with complexvalued neural network,” in Proc. IEEE 29th Chinese Control And Decision Conf., 2017, pp. 1231–1236.

[189] 
S. Rashid, S. Saraswathi, A. Kloczkowski, S. Sundaram, and A. Kolinski, “Protein secondary structure prediction using a small training set (compact model) combined with a complexvalued neural network approach,” BMC Bioinformatics, vol. 17, no. 1, p. 362, 2016.

[190] 
B. Yang, W. Zhang, L.N. Gong, and H.Z. Ma, “Finance time series prediction using complexvalued flexible neural tree model,” in Proc. IEEE 13th Int. Conf. Natural Computation, Fuzzy Systems and Knowledge Discovery, 2017, pp. 54–58.

[191] 
A. Y. H. AlNuaimi, M. F. Amin, and K. Murase, “Enhancing MP3 encoding by utilizing a predictive complexvalued neural network,” in Proc. IEEE Int. Joint Conf. Neural Networks, 2012, pp. 1–6.

[192] 
R. Akhmetsin, V. Giniyatullin, and S. Kirlan, “Identification of structures of organic substances by means of complexvalued perceptron,” Optical Memory and Neural Networks, vol. 21, no. 1, pp. 11–16, 2012. doi: 10.3103/S1060992X1201002X

[193] 
R. Olanrewaju, O. O. Khalifa, A.H. Hashim, A. M. Zeki, and A. Aburas, “Forgery detection in medical images using complex valued neural network (CVNN),” Australian Journal of Basic and Applied Sciences, vol. 5, no. 7, pp. 1251–1264, 2011.

[194] 
L. Xiao, W. Meng, R. Lu, X. Yang, B. Liao, and L. Ding, “A fully complexvalued neural network for rapid solution of complexvalued systems of linear equations,” in Proc. Int. Symp. Neural Networks. Springer, 2015, pp. 444–451.

[195] 
F. Agostinelli, M. Hoffman, P. Sadowski, and P. Baldi, “Learning activation functions to improve deep neural networks,” in Proc. Int. Conf. Learning Representations, 2015.

[196] 
J. Inturrisi, S. Y. Khoo, A. Kouzani, and R. Pagliarella, “Piecewise linear units improve deep neural networks,” arXiv preprint arXiv: 2108.00700, 2021.

[197] 
H. Zhang and D. P. Mandic, “Is a complexvalued stepsize advantageous in complexvalued gradient learning algorithms?” IEEE Trans. Neural Networks and Learning Systems, vol. 27, no. 12, pp. 2730–2735, 2016. doi: 10.1109/TNNLS.2015.2494361

[198] 
Y. Hua, Q. Liu, K. Hao, and Y. Jin, “A survey of evolutionary algorithms for multiobjective optimization problems with irregular Pareto fronts,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 2, pp. 303–318, 2021. doi: 10.1109/JAS.2021.1003817

[199] 
P. Wang, Y. Zhou, Q. Luo, C. Han, Y. Niu, and M. Lei, “Complexvalued encoding metaheuristic optimization algorithm: A comprehensive survey,” Neurocomputing, vol. 407, pp. 313–342, 2020. doi: 10.1016/j.neucom.2019.06.112

[200] 
Y. R. Wang, S. C. Gao, M. C. Zhou, and Y. Yu, “A multilayered gravitational search algorithm for function optimization and realworld problems,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 94–109, 2021. doi: 10.1109/JAS.2020.1003462

[201] 
Y. H. Du, L. Wang, L. N. Xing, J. G. Yan, and M. S. Cai, “Datadriven heuristic assisted memetic algorithm for efficient intersatellite link scheduling in the BeiDou Navigation Satellite System,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 11, pp. 1800–1816, 2021. doi: 10.1109/JAS.2021.1004174

[202] 
Q. Q. Fan and O. K. Ersoy, “Zoning search with adaptive resource allocating method for balanced and imbalanced multimodal multiobjective optimization,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1163–1176, 2021. doi: 10.1109/JAS.2021.1004027

[203] 
Z. Y. Zhao, S. X. Liu, M. C. Zhou, and A. Abusorrah, “Dualobjective mixed integer linear program and memetic algorithm for an industrial group scheduling problem,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1199–1209, Jun. 2021. doi: 10.1109/JAS.2020.1003539

[204] 
Y. Wang and X. Q. Zuo, “An effective cloud workflow scheduling approach combining PSO and idle time slotaware rules,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 5, pp. 1079–1094, May 2021. doi: 10.1109/JAS.2021.1003982

[205] 
A. H. Khan, X. W. Cao, S. Li, V. N. Katsikis, and L. F. Liao, “BASADAM: An ADAM based approach to improve the performance of beetle antennae search optimizer,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 2, pp. 461–171, Mar. 2020. doi: 10.1109/JAS.2020.1003048

[206] 
A. Taherkhani, A. Belatreche, Y. Li, G. Cosma, L. P. Maguire, and T. McGinnity, “A review of learning in biologically plausible spiking neural networks,” Neural Networks, vol. 122, pp. 253–272, 2020. doi: 10.1016/j.neunet.2019.09.036

[207] 
A. Baranski and T. Froese, “Efficient spike timing dependent plasticity rule for complexvalued neurons,” in Proc. Conf. Artificial Life. MIT Press, 2021.

[208] 
K. Zhang, Y. K. Su, X. W. Guo, L. Qi, and Z. B. Zhao, “MUGAN: Facial attribute editing based on multiattention mechanism,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 9, pp. 1614–1626, Sept. 2021. doi: 10.1109/JAS.2020.1003390

[209] 
J. Banzi, I. Bulugu, and Z. F. Ye, “Learning a deep predictive coding network for a semisupervised 3Dhand pose estimation,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 5, pp. 1371–1379, Sept. 2020.

[210] 
Z. Zhao, H. Zhou, L. Qi, L. Chang and M. Zhou, “Inductive representation learning via CNN for partiallyunseen attributed networks,” IEEE Trans. Network Science and Engineering, vol. 8, no. 1, pp. 695–706, Jan.−Mar. 2021. doi: 10.1109/TNSE.2020.3048902

[211] 
J. X. Zhang, K. W. Li, and Y. M. Li, “Outputfeedback based simplified optimized backstepping control for strictfeedback systems with input and state constraints,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1119–1132, Jun. 2021. doi: 10.1109/JAS.2021.1004018

[212] 
E. F. Ohata, G. M. Bezerra, J. V. S. Chagas, A. V. Lira Neto, A. B. Albuquerque, V. H. C. Albuquerque, and P. P. Rebouças Filho, “Automatic detection of COVID19 infection using chest Xray images through transfer learning,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 239–248, Jan. 2021. doi: 10.1109/JAS.2020.1003393

[213] 
T. Wang, X. Xu, F. Shen, and Y. Yang, “A cognitive memoryaugmented network for visual anomaly detection,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1296–1307, Jul. 2021. doi: 10.1109/JAS.2021.1004045

[214] 
P. Liu, Y. Zhou, D. Peng and D. Wu, “Globalattentionbased neural networks for vision language intelligence,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1243–1252, Jul. 2021.

[215] 
Z. Huang, X. Xu, H. Zhu and M. Zhou, “An efficient group recommendation model with multiattentionbased neural networks,” IEEE Trans. Neural Networks and Learning Systems, vol. 31, no. 11, pp. 4461–4474, Nov. 2020. doi: 10.1109/TNNLS.2019.2955567

[216] 
W. J. Zhang, J. C. Wang, and F. P. Lan, “Dynamic hand gesture recognition based on shortterm sampling neural networks,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 110–120, Jan. 2021. doi: 10.1109/JAS.2020.1003465

[217] 
S. Liu, Y. Xia, Z. Shi, H. Yu, Z. Li, and J. Lin, “Deep learning in sheet metal bending with a novel theoryguided deep neural network,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 3, pp. 565–581, Mar. 2021. doi: 10.1109/JAS.2021.1003871

[218] 
M. Ghahramani, Y. Qiao, M. C. Zhou, A. O’Hagan, and J. Sweeney, “AIbased modeling and datadriven evaluation for smart manufacturing processes,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 7, pp. 1026–1037, Jul. 2020.

[219] 
H. Zhang, L. Jin and C. Ye, “An RGBD camera based visual positioning system for assistive navigation by a robotic navigation aid,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1389–1400, Aug. 2021. doi: 10.1109/JAS.2021.1004084

[220] 
S. Li, M. Zhou and X. Luo, “Modified primaldual neural networks for motion control of redundant manipulators with dynamic rejection of harmonic noises,” IEEE Trans. Neural Networks and Learning Systems, vol. 29, no. 10, pp. 4791–4801, Oct. 2018. doi: 10.1109/TNNLS.2017.2770172

[221] 
H. Dong, B. Zou, L. Zhang, and S. Zhang, “Automatic design of CNNs via differentiable neural architecture search for PolSAR image classification,” IEEE Trans. Geoscience and Remote Sensing, vol. 58, no. 9, pp. 6362–6375, 2020. doi: 10.1109/TGRS.2020.2976694
