A survey of quaternion neural networks

citation_journal_title=IEEE J Sel Top Signal Process; citation_title=Sound event localization and detection of overlapping sources using convolutional recurrent neural networks; citation_author=S Adavanne, A Politis, J Nikunen, T Virtanen; citation_volume=13; citation_publication_date=2018; citation_pages=34-48; citation_id=CR1 Aizenberg IN, Gonzalez A (2018) Image recognition using MLMVN and frequency domain features. In: 2018 International joint conference on neural networks (IJCNN), pp 1–8 Aizenberg I, Alexander S, Jackson J (2011) Recognition of blurred images using multilayer neural network based on multi-valued neurons. In: 2011 41st IEEE International symposium on multiple-valued logic. IEEE, pp 282–287 Arena P, Fortuna L, Re R, Xibilia MG (1993) On the capability of neural networks with complex neurons in complex valued functions approximation. In: 1993 IEEE International symposium on circuits and systems, ISCAS’93. IEEE, pp 2168–2171 Arena P, Fortuna L, Occhipinti L, Xibilia MG (1994) Neural networks for quaternion-valued function approximation. In: 1994 IEEE International symposium on circuits and systems, ISCAS’94, vol 6. IEEE, pp 307–310 citation_journal_title=Neural Netw; citation_title=Multilayer perceptrons to approximate quaternion valued functions; citation_author=P Arena, L Fortuna, G Muscato, MG Xibilia; citation_volume=10; citation_issue=2; citation_publication_date=1997; citation_pages=335-342; citation_id=CR6 citation_journal_title=Robot Auton Syst; citation_title=Geometric techniques for robotics and hmi: Interpolation and haptics in conformal geometric algebra and control using quaternion spike neural networks; citation_author=E Bayro-Corrochano, L Lechuga-Gutiérrez, M Garza-Burgos; citation_volume=104; citation_publication_date=2018; citation_pages=72-84; citation_id=CR7 Bechet F, Maza B, Bigouroux N, Bazillon T, El-Beze M, De Mori R, Arbillot E (2012) Decoda: a call-centre human–human spoken conversation corpus. In: LREC, pp 1343–1347 citation_journal_title=J Mach Learn Res; citation_title=Latent dirichlet allocation; citation_author=DM Blei, AY Ng, MI Jordan; citation_volume=3; citation_issue=Jan; citation_publication_date=2003; citation_pages=993-1022; citation_id=CR9 citation_title=Quaternionic spinor MLP; citation_publication_date=2000; citation_id=CR10; citation_author=S Buchholz; citation_author=G Sommer; citation_publisher=CiteSeer Buchholz S, Le Bihan N (2006) Optimal separation of polarized signals by quaternionic neural networks. In: 2006 14th European signal processing conference. IEEE, pp 1–5 citation_journal_title=IEEE Trans Robot Autom; citation_title=Quaternion kinematic and dynamic differential equations; citation_author=JC Chou; citation_volume=8; citation_issue=1; citation_publication_date=1992; citation_pages=53-64; citation_id=CR12 Comminiello D, Lella M, Scardapane S, Uncini A (2018) Quaternion convolutional neural networks for detection and localization of 3D sound events. arXiv:181206811 Cui Y, Takahashi K, Hashimoto M (2013) Design of control systems using quaternion neural network and its application to inverse kinematics of robot manipulator. In: 2013 IEEE/SICE International symposium on system integration (SII). IEEE, pp 527–532 Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE Computer society conference on computer vision and pattern recognition, CVPR 2005, vol 1. IEEE, pp 886–893 citation_journal_title=Ann Oper Res; citation_title=A tutorial on the cross-entropy method; citation_author=PT Boer, DP Kroese, S Mannor, RY Rubinstein; citation_volume=134; citation_issue=1; citation_publication_date=2005; citation_pages=19-67; citation_id=CR16 De Leo S, Rotelli P (1997) Local hypercomplex analyticity. arXiv preprint arXiv:9703002 [funct-an] citation_journal_title=Matrix; citation_title=Representing attitude: Euler angles, unit quaternions, and rotation vectors; citation_author=J Diebel; citation_volume=58; citation_issue=15–16; citation_publication_date=2006; citation_pages=1-35; citation_id=CR18 citation_journal_title=IEEE Trans Robot Autom; citation_title=Simultaneous robot-world and hand-eye calibration; citation_author=F Dornaika, R Horaud; citation_volume=14; citation_issue=4; citation_publication_date=1998; citation_pages=617-622; citation_id=CR19 Fortuna L, Muscato G, Xibilia M (1996) An hypercomplex neural network platform for robot positioning. In: 1996 IEEE International symposium on circuits and systems, ISCAS’96. Connecting the World, vol 3. IEEE, pp 609–612 citation_journal_title=IEEE Trans Neural Netw; citation_title=A comparison between hmlp and hrbf for attitude control; citation_author=L Fortuna, G Muscato, MG Xibilia; citation_volume=12; citation_issue=2; citation_publication_date=2001; citation_pages=318-328; citation_id=CR21 Garofolo JS, Lamel LF, Fisher WM, Fiscus JG, Pallett DS (1993) Darpa timit acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1. NASA STI/Recon technical report no. 93 Gaudet CJ, Maida AS (2018) Deep quaternion networks. In: 2018 International joint conference on neural networks (IJCNN). IEEE, pp 1–8 citation_journal_title=Int J Robot Res (IJRR); citation_title=Vision meets robotics: the KITTI dataset; citation_author=A Geiger, P Lenz, C Stiller, R Urtasun; citation_volume=32; citation_publication_date=2013; citation_pages=1231-1237; citation_id=CR24 Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 249–256 Graves A, Mohamed Ar, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: 2013 IEEE International conference on acoustics, speech and signal processing. IEEE, pp 6645–6649 Greenblatt A, Mosquera-Lopez C, Agaian S (2013) Quaternion neural networks applied to prostate cancer gleason grading. In: 2013 IEEE International conference on systems, man, and cybernetics (SMC). IEEE, pp 1144–1149 citation_journal_title=Lond Edinb Dublin Philos Mag J Sci; citation_title=Ii. on quaternions; or on a new system of imaginaries in algebra; citation_author=WR Hamilton; citation_volume=25; citation_issue=163; citation_publication_date=1844; citation_pages=10-13; citation_id=CR28 citation_journal_title=IEEE Intell Syst Appl; citation_title=Support vector machines; citation_author=MA Hearst, ST Dumais, E Osuna, J Platt, B Scholkopf; citation_volume=13; citation_issue=4; citation_publication_date=1998; citation_pages=18-28; citation_id=CR29 He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034 He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778 citation_title=Analysis of the Cholesky decomposition of a semi-definite matrix; citation_publication_date=1990; citation_id=CR32; citation_author=NJ Higham; citation_publisher=Oxford University Press citation_journal_title=Science; citation_title=Reducing the dimensionality of data with neural networks; citation_author=GE Hinton, RR Salakhutdinov; citation_volume=313; citation_issue=5786; citation_publication_date=2006; citation_pages=504-507; citation_id=CR33 citation_journal_title=Neural Comput; citation_title=A fast learning algorithm for deep belief nets; citation_author=GE Hinton, S Osindero, YW Teh; citation_volume=18; citation_issue=7; citation_publication_date=2006; citation_pages=1527-1554; citation_id=CR34 citation_journal_title=IEEE Signal Process Mag; citation_title=Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups; citation_author=G Hinton, L Deng, D Yu, GE Dahl, A Mohamed, N Jaitly, A Senior, V Vanhoucke, P Nguyen, TN Sainath; citation_volume=29; citation_issue=6; citation_publication_date=2012; citation_pages=82-97; citation_id=CR35 citation_title=Complex-valued neural networks; citation_publication_date=2012; citation_id=CR36; citation_author=A Hirose; citation_publisher=Springer citation_journal_title=Adv Appl Clifford Algebras; citation_title=Quaternion fourier transform on quaternion fields and generalizations; citation_author=EM Hitzer; citation_volume=17; citation_issue=3; citation_publication_date=2007; citation_pages=497-517; citation_id=CR37 citation_journal_title=Neural Comput; citation_title=Long short-term memory; citation_author=S Hochreiter, J Schmidhuber; citation_volume=9; citation_issue=8; citation_publication_date=1997; citation_pages=1735-1780; citation_id=CR38 citation_journal_title=Biol Cybern; citation_title=“Neural” computation of decisions in optimization problems; citation_author=JJ Hopfield, DW Tank; citation_volume=52; citation_issue=3; citation_publication_date=1985; citation_pages=141-152; citation_id=CR39 Huang FJ, LeCun Y (2006) Large-scale learning with SVM and convolutional for generic object categorization. In: null. IEEE, pp 284–291 Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:150203167 Isokawa T, Kusakabe T, Matsui N, Peper F (2003) Quaternion neural network and its application. In: International conference on knowledge-based and intelligent information and engineering systems. Springer, pp 318–324 Isokawa T, Nishimura H, Kamiura N, Matsui N (2006) Fundamental properties of quaternionic hopfield neural network. In: 2006 International joint conference on neural networks, IJCNN’06. IEEE, pp 218–223 citation_journal_title=Int J Neural Syst; citation_title=Associative memory in quaternionic hopfield neural network; citation_author=T Isokawa, H Nishimura, N Kamiura, N Matsui; citation_volume=18; citation_issue=02; citation_publication_date=2008; citation_pages=135-145; citation_id=CR44 Isokawa T, Matsui N, Nishimura H (2009) Quaternionic neural networks: fundamental properties and applications. In: Complex-valued neural networks: utilizing high-dimensional parameters. IGI global. pp 411–439 citation_journal_title=Information; citation_title=Quaternionic multilayer perceptron with local analyticity; citation_author=T Isokawa, H Nishimura, N Matsui; citation_volume=3; citation_issue=4; citation_publication_date=2012; citation_pages=756-770; citation_id=CR46 Jolliffe I (2011) Principal component analysis. In: Lovric M (ed) International encyclopedia of statistical science. Springer, Berlin, pp 1094–1096 citation_journal_title=J Mol Graph Model; citation_title=Quaternions in molecular modeling; citation_author=CF Karney; citation_volume=25; citation_issue=5; citation_publication_date=2007; citation_pages=595-604; citation_id=CR48 citation_journal_title=IEEE Geosci Remote Sens Lett; citation_title=Isotropization of quaternion-neural-network-based PolSAR adaptive land classification in Poincare-sphere parameter space; citation_author=K Kinugawa, F Shang, N Usami, A Hirose; citation_volume=15; citation_publication_date=2018; citation_pages=1234-1238; citation_id=CR49 citation_journal_title=IEICE Trans Fundam Electron Commun Comput Sci; citation_title=Hybrid quaternionic hopfield neural network; citation_author=M Kobayashi; citation_volume=98; citation_issue=7; citation_publication_date=2015; citation_pages=1512-1518; citation_id=CR50 citation_journal_title=IEEJ Trans Electr Electron Eng; citation_title=Twisted quaternary neural networks; citation_author=M Kobayashi, A Nakajima; citation_volume=7; citation_issue=4; citation_publication_date=2012; citation_pages=397-401; citation_id=CR51 Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105 Krizhevsky A, Nair V, Hinton G (2014) The cifar-10 dataset. http://www.cs.toronto.edu/kriz/cifar html Kusamichi H, Isokawa T, Matsui N, Ogawa Y, Maeda K (2004) A new scheme for color night vision by quaternion neural network. In: Proceedings of the 2nd international conference on autonomous robots and agents, vol 1315. Citeseer citation_journal_title=IEEE Trans Nucl Sci; citation_title=A fuzzy hopfield neural network for medical image segmentation; citation_author=JS Lin, KS Cheng, CW Mao; citation_volume=43; citation_issue=4; citation_publication_date=1996; citation_pages=2389-2398; citation_id=CR55 citation_title=Complex valued nonlinear adaptive filters: noncircularity, widely linear and neural models; citation_publication_date=2009; citation_id=CR56; citation_author=DP Mandic; citation_author=VSL Goh; citation_publisher=Wiley citation_journal_title=IEEE Signal Process Lett; citation_title=A quaternion gradient operator and its applications; citation_author=DP Mandic, C Jahanchahi, CC Took; citation_volume=18; citation_issue=1; citation_publication_date=2011; citation_pages=47-50; citation_id=CR57 citation_journal_title=J Intell Fuzzy Syst; citation_title=Quaternion neural network with geometrical operators; citation_author=N Matsui, T Isokawa, H Kusamichi, F Peper, H Nishimura; citation_volume=15; citation_issue=3, 4; citation_publication_date=2004; citation_pages=149-164; citation_id=CR58 Mikolov T, Karafiát M, Burget L, Černockỳ J, Khudanpur S (2010) Recurrent neural network based language model. In: Eleventh annual conference of the international speech communication association Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807–814 Nitta T (1995) A quaternary version of the back-propagation algorithm. In: IEEE International conference on neural networks, 1995. Proceedings, vol 5. IEEE, pp 2753–2756 citation_journal_title=Neural Inf Process Lett Rev; citation_title=A solution to the 4-bit parity problem with a single quaternary neuron; citation_author=T Nitta; citation_volume=5; citation_issue=2; citation_publication_date=2004; citation_pages=33-39; citation_id=CR62 Nitta T, de Garis H (1992) A 3D vector version of the back-propagation algorithm. In: Proceedings of international joint conference on neural networks, pp 511–516 citation_journal_title=Comput Technol Appl; citation_title=Neural network inversion for multilayer quaternion neural networks; citation_author=T Ogawa; citation_volume=7; citation_publication_date=2016; citation_pages=73-82; citation_id=CR64 Parcollet T, Morchid M, Bousquet PM, Dufour R, Linarès G, De Mori R (2016) Quaternion neural networks for spoken language understanding. In: 2016 IEEE Spoken language technology workshop (SLT). IEEE, pp 362–368 Parcollet T, Morchid M, Linares G (2017a) Deep quaternion neural networks for spoken language understanding. In: 2017 IEEE Automatic speech recognition and understanding workshop (ASRU). IEEE, pp 504–511 Parcollet T, Morchid M, Linares G (2017b) Quaternion denoising encoder–decoder for theme identification of telephone conversations. Proceedings of Interspeech 2017, pp 3325–3328 Parcollet T, Morchid M, Linarès G (2018a) Quaternion convolutional neural networks for heterogeneous image processing. arXiv preprint arXiv:181102656 Parcollet T, Ravanelli M, Morchid M, Linarès G, Trabelsi C, Mori RD, Bengio Y (2018b) Quaternion recurrent neural networks. arXiv preprint arXiv:1806.04418 Parcollet T, Zhang Y, Morchid M, Trabelsi C, Linarès G, de Mori R, Bengio Y (2018c) Quaternion convolutional neural networks for end-to-end automatic speech recognition. In: Interspeech 2018, 19th Annual conference of the international speech communication association, Hyderabad, India, 2–6 September 2018, pp 22–26. https://doi.org/10.21437/Interspeech.2018-1898 Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp 1310–1318 Platt J, et al. (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in large margin classifiers. MIT Press, pp 61–74 citation_journal_title=Vis Comput; citation_title=Quaternion calculus as a basic tool in computer graphics; citation_author=D Pletinckx; citation_volume=5; citation_issue=1–2; citation_publication_date=1989; citation_pages=2-13; citation_id=CR73 citation_journal_title=Neural Process Lett; citation_title=Learning algorithms for quaternion-valued neural networks; citation_author=CA Popa; citation_volume=47; citation_issue=3; citation_publication_date=2018; citation_pages=949-973; citation_id=CR74 citation_journal_title=Electron Lett; citation_title=Fourier transforms of colour images using quaternion or hypercomplex, numbers; citation_author=SJ Sangwine; citation_volume=32; citation_issue=21; citation_publication_date=1996; citation_pages=1979-1980; citation_id=CR75 citation_journal_title=IEEE Trans Signal Process; citation_title=Bidirectional recurrent neural networks; citation_author=M Schuster, KK Paliwal; citation_volume=45; citation_issue=11; citation_publication_date=1997; citation_pages=2673-2681; citation_id=CR76 citation_journal_title=IEEE Trans Geosci Remote Sensing; citation_title=Quaternion neural-network-based PolSAR land classification in poincare-sphere-parameter space; citation_author=F Shang, A Hirose; citation_volume=52; citation_issue=9; citation_publication_date=2014; citation_pages=5693-5703; citation_id=CR77 Shoemake K (1985) Animating rotation with quaternion curves. In: ACM SIGGRAPH computer graphics, vol 19. ACM, pp 245–254 Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556 citation_journal_title=Pattern Recognit Lett; citation_title=Quaternionic wavelets for texture classification; citation_author=R Soulard, P Carré; citation_volume=32; citation_issue=13; citation_publication_date=2011; citation_pages=1669-1678; citation_id=CR80 citation_journal_title=J Mach Learn Res; citation_title=Dropout: a simple way to prevent neural networks from overfitting; citation_author=N Srivastava, G Hinton, A Krizhevsky, I Sutskever, R Salakhutdinov; citation_volume=15; citation_issue=1; citation_publication_date=2014; citation_pages=1929-1958; citation_id=CR81 Takahashi K, Takahashi S, Cui Y, Hashimoto M (2014) Remarks on computational facial expression recognition from HOG features using quaternion multi-layer neural network. In: International conference on engineering applications of neural networks. Springer, pp 15–24 Takahashi K, Isaka A, Fudaba T, Hashimoto M (2017) Remarks on quaternion neural network-based controller trained by feedback error learning. In: 2017 IEEE/SICE International symposium on system integration (SII), pp 875–880 Tokuda, K., Zen, H., Kitamura, T. (2003) Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features. In Eighth European conference on speech communication and technology Trabelsi C, Bilaniuk O, Zhang Y, Serdyuk D, Subramanian S, Santos JF, Mehri S, Rostamzadeh N, Bengio Y, Pal CJ (2017) Deep complex networks. arXiv preprint arXiv:170509792 Ujang BC, Jahanchahi C, Took CC, Mandic D (2010) Quaternion valued neural networks and nonlinear adaptive filters. citation_journal_title=IEEE Trans Neural Netw; citation_title=Quaternion-valued nonlinear adaptive filtering; citation_author=BC Ujang, CC Took, DP Mandic; citation_volume=22; citation_issue=8; citation_publication_date=2011; citation_pages=1193-1206; citation_id=CR87 citation_journal_title=IEEE Trans Neural Netw Learn Syst; citation_title=On the dynamics of hopfield neural networks on unit quaternions; citation_author=ME Valle, FZ Castro; citation_volume=29; citation_issue=6; citation_publication_date=2018; citation_pages=2464-2471; citation_id=CR88 Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning. ACM, pp 1096–1103 citation_journal_title=Clim Res; citation_title=Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance; citation_author=CJ Willmott, K Matsuura; citation_volume=30; citation_issue=1; citation_publication_date=2005; citation_pages=79-82; citation_id=CR90 citation_journal_title=R Soc Open Sci; citation_title=Enabling quaternion derivatives: the generalized HR calculus; citation_author=D Xu, C Jahanchahi, CC Took, DP Mandic; citation_volume=2; citation_issue=8; citation_publication_date=2015; citation_pages=150255; citation_id=CR91 citation_journal_title=Neural Netw World; citation_title=Learning algorithms in quaternion neural networks using GHR calculus; citation_author=D Xu, L Zhang, H Zhang; citation_volume=27; citation_issue=3; citation_publication_date=2017; citation_pages=271; citation_id=CR92 citation_journal_title=Int J Neural Syst; citation_title=Models of hopfield-type quaternion neural networks and their energy functions; citation_author=M Yoshida, Y Kuroe, T Mori; citation_volume=15; citation_publication_date=2005; citation_pages=129-135; citation_id=CR93 citation_journal_title=IEEE Trans Robot; citation_title=Design, implementation, and experimental results of a quaternion-based kalman filter for human body motion tracking; citation_author=X Yun, ER Bachmann; citation_volume=22; citation_issue=6; citation_publication_date=2006; citation_pages=1216-1227; citation_id=CR94