{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:31:24Z","timestamp":1759332684927},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The learning algorithm for a three-layered neural structure with novel non-linear quaternionic-valued multiplicative (QVM) neurons is proposed in this paper. The computing capability of non-linear aggregation in the cell body of biological neurons inspired the development of a non-linear neuron model. However, unlike linear neuron models, most non-linear neuron models are built on higher order aggregation, which is more mathematically complex and difficult to train. As a result, building non-linear neuron models with a simple structure is a difficult and time-consuming endeavor in the neurocomputing field. The concept of a QVM neuron model was influenced by the non-linear neuron model, which has a simple structure and the great computational ability. The suggested neuron\u2019s linearity is determined by the weight and bias associated with each quaternionic-valued input. Non-commutative multiplication of all linearly connected quaternionic input-weight terms accommodates the non-linearity. To train three-layered networks with QVM neurons, the standard quaternionic-gradient-based backpropagation (QBP) algorithm is utilized. The computational and generalization capabilities of the QVM neuron are assessed through training and testing in the quaternionic domain utilizing benchmark problems, such as 3D and 4D chaotic time-series predictions, 3D geometrical transformations, and 3D face recognition. The training and testing outcomes are compared to conventional and root-power mean (RPM) neurons in quaternionic domain using training\u2013testing MSEs, network topology (parameters), variance, and AIC as statistical measures. According to these findings, networks with QVM neurons have greater computational and generalization capabilities than networks with conventional and RPM neurons in quaternionic domain.<\/jats:p>","DOI":"10.1007\/s40747-022-00911-6","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T05:10:48Z","timestamp":1669612248000},"page":"3161-3183","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A novel non-linear neuron model based on multiplicative aggregation in quaternionic domain"],"prefix":"10.1007","volume":"9","author":[{"given":"Sushil","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Rishitosh Kumar","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Aryan","family":"Chaudhary","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,28]]},"reference":[{"key":"911_CR1","first-page":"41","volume":"11","author":"S Kumar","year":"2018","unstructured":"Kumar S, Tripathi BK (2018) High-dimensional information processing through resilient propagation in quaternionic domain. J Ind Inf Integr 11:41\u201349","journal-title":"J Ind Inf Integr"},{"issue":"4","key":"911_CR2","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1080\/03772063.2018.1436473","volume":"65","author":"S Kumar","year":"2019","unstructured":"Kumar S, Tripathi BK (2019) Root-power mean aggregation-based neuron in quaternionic domain. IETE J Res 65(4):557\u2013575","journal-title":"IETE J Res"},{"issue":"1","key":"911_CR3","first-page":"33","volume":"6","author":"S Kumar","year":"2019","unstructured":"Kumar S, Tripathi BK (2019) On the learning machine with compensatory aggregation based neurons in quaternionic domain. J Comput Des Eng 6(1):33\u201348","journal-title":"J Comput Des Eng"},{"key":"911_CR4","doi-asserted-by":"crossref","first-page":"20293","DOI":"10.1109\/ACCESS.2019.2897000","volume":"7","author":"Q Yin","year":"2019","unstructured":"Yin Q, Wang J, Luo X, Zhai J, Jha SK, Shi Y-Q (2019) Quaternion convolutional neural network for color image classification and forensics. IEEE Access 7:20293\u201320301","journal-title":"IEEE Access"},{"issue":"1\u20132","key":"911_CR5","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.cviu.2006.11.019","volume":"107","author":"P Denis","year":"2007","unstructured":"Denis P, Carre P, Fernandez-Maloigne C (2007) Spatial and spectral quaternionic approaches for colour images. Comput Vis Image Underst 107(1\u20132):74\u201387","journal-title":"Comput Vis Image Underst"},{"key":"911_CR6","volume-title":"Elements of quaternions","author":"WR Hamilton","year":"1866","unstructured":"Hamilton WR (1866) Elements of quaternions. Green, & Company, Longmans"},{"key":"911_CR7","doi-asserted-by":"crossref","unstructured":"Kajiwara J, Li XD, Shon KH (2004) Regeneration in complex, quaternion and Clifford analysis. In: Finite or infinite dimensional complex analysis and applications. Springer, pp 287\u2013298","DOI":"10.1007\/978-1-4613-0221-6_19"},{"issue":"4","key":"911_CR8","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1007\/BF01077870","volume":"16","author":"AG \u00c9lashvili","year":"1982","unstructured":"\u00c9lashvili AG (1982) Frobenius Lie algebras. Funct Anal Appl 16(4):326\u2013328","journal-title":"Funct Anal Appl"},{"issue":"1\u20132","key":"911_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF01448439","volume":"88","author":"A Hurwitz","year":"1922","unstructured":"Hurwitz A (1922) \u00dcber die Komposition der quadratischen Formen. Math Ann 88(1\u20132):1\u201325","journal-title":"Math Ann"},{"key":"911_CR10","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.jnt.2016.11.008","volume":"175","author":"Z-W Sun","year":"2017","unstructured":"Sun Z-W (2017) Refining Lagrange\u2019s four-square theorem. J Number Theory 175:167\u2013190","journal-title":"J Number Theory"},{"issue":"1","key":"911_CR11","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.jfranklin.2013.08.028","volume":"351","author":"Y Ma","year":"2014","unstructured":"Ma Y, Jiang B, Tao G, Cheng Y (2014) Actuator failure compensation and attitude control for rigid satellite by adaptive control using quaternion feedback. J Frankl Inst 351(1):296\u2013314","journal-title":"J Frankl Inst"},{"key":"911_CR12","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2020.105995","volume":"105","author":"SO Ariyibi","year":"2020","unstructured":"Ariyibi SO, Tekinalp O (2020) Quaternion-based nonlinear attitude control of quadrotor formations carrying a slung load. Aerosp Sci Technol 105:105995","journal-title":"Aerosp Sci Technol"},{"issue":"6","key":"911_CR13","doi-asserted-by":"crossref","first-page":"1762","DOI":"10.2514\/1.58558","volume":"36","author":"MS Andrle","year":"2013","unstructured":"Andrle MS, Crassidis JL (2013) Geometric integration of quaternions. J Guid Control Dyn 36(6):1762\u20131767","journal-title":"J Guid Control Dyn"},{"issue":"4","key":"911_CR14","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.2514\/1.47782","volume":"33","author":"D Condurache","year":"2010","unstructured":"Condurache D, Martinusi V (2010) Quaternionic exact solution to the relative orbital motion problem. J Guid Control Dyn 33(4):1035\u20131047","journal-title":"J Guid Control Dyn"},{"issue":"8","key":"911_CR15","doi-asserted-by":"crossref","first-page":"1812","DOI":"10.1021\/acs.jpcb.6b11703","volume":"121","author":"P-C Chen","year":"2017","unstructured":"Chen P-C, Hologne M, Walker O (2017) Computing the rotational diffusion of biomolecules via molecular dynamics simulation and quaternion orientations. J Phys Chem B 121(8):1812\u20131823","journal-title":"J Phys Chem B"},{"issue":"5","key":"911_CR16","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/j.jmgm.2006.04.002","volume":"25","author":"CF Karney","year":"2007","unstructured":"Karney CF (2007) Quaternions in molecular modeling. J Mol Graph Model 25(5):595\u2013604","journal-title":"J Mol Graph Model"},{"key":"911_CR17","volume":"176","author":"L Wu","year":"2020","unstructured":"Wu L, Zhang X, Chen H, Zhou Y (2020) Unsupervised quaternion model for blind colour image quality assessment. Signal Process 176:107708","journal-title":"Signal Process"},{"key":"911_CR18","doi-asserted-by":"crossref","DOI":"10.1002\/9781118930908","volume-title":"Quaternion Fourier transforms for signal and image processing","author":"TA Ell","year":"2014","unstructured":"Ell TA, Le Bihan N, Sangwine SJ (2014) Quaternion Fourier transforms for signal and image processing. Wiley, New York"},{"key":"911_CR19","doi-asserted-by":"crossref","unstructured":"Pervin E, Webb JA (1982) Quaternions in computer vision and robotics. Technical report, Department of Computer Science, Carnegie-Mellon University, Pittsburgh, PA","DOI":"10.21236\/ADA125076"},{"issue":"1","key":"911_CR20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-015-0667-0","volume":"16","author":"C Caudai","year":"2015","unstructured":"Caudai C, Salerno E, Zopp\u00e8 M, Tonazzini A (2015) Inferring 3D chromatin structure using a multiscale approach based on quaternions. BMC Bioinform 16(1):1\u201311","journal-title":"BMC Bioinform"},{"issue":"7","key":"911_CR21","doi-asserted-by":"crossref","first-page":"2172","DOI":"10.1002\/prot.23037","volume":"79","author":"RM Hanson","year":"2011","unstructured":"Hanson RM, Kohler D, Braun SG (2011) Quaternion-based definition of protein secondary structure straightness and its relationship to Ramachandran angles. Proteins Struct Funct Bioinform 79(7):2172\u20132180","journal-title":"Proteins Struct Funct Bioinform"},{"issue":"20","key":"911_CR22","doi-asserted-by":"crossref","first-page":"6141","DOI":"10.1016\/j.actamat.2008.08.031","volume":"56","author":"J Mason","year":"2008","unstructured":"Mason J, Schuh C (2008) Hyperspherical harmonics for the representation of crystallographic texture. Acta Mater 56(20):6141\u20136155","journal-title":"Acta Mater"},{"key":"911_CR23","unstructured":"Barrallo J et\u00a0al (2010) Expanding the Mandelbrot set into higher dimensions. In: Proceedings of Bridges 2010: mathematics, music, art, architecture, culture, pp 247\u2013254"},{"issue":"6","key":"911_CR24","doi-asserted-by":"crossref","first-page":"5189","DOI":"10.3233\/JIFS-17461","volume":"36","author":"S Kumar","year":"2019","unstructured":"Kumar S, Tripathi BK (2019) On the learning machine with quaternionic domain neural network and its high-dimensional applications. J Intell Fuzzy Syst 36(6):5189\u20135202","journal-title":"J Intell Fuzzy Syst"},{"issue":"4","key":"911_CR25","doi-asserted-by":"crossref","first-page":"2957","DOI":"10.1007\/s10462-019-09752-1","volume":"53","author":"T Parcollet","year":"2020","unstructured":"Parcollet T, Morchid M, Linares G (2020) A survey of quaternion neural networks. Artif Intell Rev 53(4):2957\u20132982","journal-title":"Artif Intell Rev"},{"key":"911_CR26","unstructured":"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"},{"key":"911_CR27","unstructured":"Parcollet T, Ravanelli M, Morchid M, Linar\u00e8s G, De\u00a0Mori R (2018) Speech recognition with quaternion neural networks. arXiv preprint arXiv:1811.09678"},{"key":"911_CR28","doi-asserted-by":"crossref","unstructured":"Qiu X, Parcollet T, Ravanelli M, Lane N, Morchid M (2020) Quaternion neural networks for multi-channel distant speech recognition. arXiv preprint arXiv:2005.08566","DOI":"10.21437\/Interspeech.2020-1682"},{"key":"911_CR29","doi-asserted-by":"crossref","unstructured":"Rao SP, Panetta K, Agaian S (2020) Quaternion based neural network for hyperspectral image classification. In: Mobile multimedia\/image processing, security, and applications 2020, vol 11399. International Society for Optics and Photonics, p 113990S","DOI":"10.1117\/12.2558808"},{"issue":"9","key":"911_CR30","doi-asserted-by":"crossref","first-page":"5693","DOI":"10.1109\/TGRS.2013.2291940","volume":"52","author":"F Shang","year":"2013","unstructured":"Shang F, Hirose A (2013) Quaternion neural-network-based PolSAR land classification in Poincare-sphere-parameter space. IEEE Trans Geosci Remote Sens 52(9):5693\u20135703","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"911_CR31","doi-asserted-by":"crossref","unstructured":"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, IEEE, pp 1144\u20131149","DOI":"10.1109\/SMC.2013.199"},{"key":"911_CR32","doi-asserted-by":"crossref","unstructured":"Luo L, Feng H, Ding L (2010) Color image compression based on quaternion neural network principal component analysis. In: 2010 international conference on multimedia technology. IEEE, pp 1\u20134","DOI":"10.1109\/ICMULT.2010.5631456"},{"key":"911_CR33","doi-asserted-by":"crossref","unstructured":"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\u201324","DOI":"10.1007\/978-3-319-11071-4_2"},{"key":"911_CR34","doi-asserted-by":"crossref","unstructured":"Takahashi K (2018) Remarks on control of robot manipulator using quaternion neural network. In: 2018 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC). IEEE, pp 560\u2013565","DOI":"10.23919\/APSIPA.2018.8659775"},{"key":"911_CR35","doi-asserted-by":"crossref","unstructured":"Parcollet T, Morchid M, Bousquet P-M, Dufour R, Linar\u00e8s G, De\u00a0Mori R (2016) Quaternion neural networks for spoken language understanding. In: 2016 IEEE spoken language technology workshop (SLT). IEEE, pp 362\u2013368","DOI":"10.1109\/SLT.2016.7846290"},{"issue":"2","key":"911_CR36","doi-asserted-by":"crossref","first-page":"548","DOI":"10.2514\/1.56352","volume":"36","author":"A-M Zou","year":"2013","unstructured":"Zou A-M, Kumar KD (2013) Quaternion-based distributed output feedback attitude coordination control for spacecraft formation flying. J Guid Control Dyn 36(2):548\u2013556","journal-title":"J Guid Control Dyn"},{"key":"911_CR37","doi-asserted-by":"crossref","first-page":"162141","DOI":"10.1109\/ACCESS.2020.3021181","volume":"8","author":"X Huang","year":"2020","unstructured":"Huang X, Gai S (2020) Banknote classification based on convolutional neural network in quaternion wavelet domain. IEEE Access 8:162141\u2013162148","journal-title":"IEEE Access"},{"issue":"2","key":"911_CR38","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/S0893-6080(96)00048-2","volume":"10","author":"P Arena","year":"1997","unstructured":"Arena P, Fortuna L, Muscato G, Xibilia MG (1997) Multilayer perceptrons to approximate quaternion valued functions. Neural Netw 10(2):335\u2013342","journal-title":"Neural Netw"},{"key":"911_CR39","doi-asserted-by":"crossref","unstructured":"Muramoto N, Isokawa T, Nishimura H, Matsui N (2013) On processing three dimensional data by quaternionic neural networks. In: The 2013 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20135","DOI":"10.1109\/IJCNN.2013.6707127"},{"issue":"6","key":"911_CR40","doi-asserted-by":"crossref","first-page":"2949","DOI":"10.1007\/s40747-021-00480-0","volume":"7","author":"M Amiri","year":"2021","unstructured":"Amiri M, Soleimani S (2021) ML-based group method of data handling: an improvement on the conventional GMDH. Complex Intell Syst 7(6):2949\u20132960","journal-title":"Complex Intell Syst"},{"key":"911_CR41","doi-asserted-by":"crossref","unstructured":"Hayman S (1999) The Mcculloch\u2013Pitts model. In: IJCNN\u201999. International joint conference on neural networks. Proceedings (Cat. No. 99CH36339), vol 6. IEEE, pp 4438\u20134439","DOI":"10.1109\/IJCNN.1999.830886"},{"issue":"8","key":"911_CR42","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1016\/S0893-6080(97)00036-1","volume":"10","author":"T Nitta","year":"1997","unstructured":"Nitta T (1997) An extension of the back-propagation algorithm to complex numbers. Neural Netw 10(8):1391\u20131415","journal-title":"Neural Netw"},{"key":"911_CR43","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-20353-4","volume-title":"Complex-valued neural networks with multi-valued neurons","author":"I Aizenberg","year":"2011","unstructured":"Aizenberg I (2011) Complex-valued neural networks with multi-valued neurons, vol 353. Springer, Berlin"},{"key":"911_CR44","doi-asserted-by":"crossref","unstructured":"Nitta T (1995) A quaternary version of the back-propagation algorithm. In: Proceedings of ICNN\u201995-international conference on neural networks, vol 5. IEEE, pp 2753\u20132756","DOI":"10.1109\/ICNN.1995.488166"},{"issue":"6","key":"911_CR45","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1162\/neco.1994.6.6.1031","volume":"6","author":"BW Mel","year":"1994","unstructured":"Mel BW (1994) Information processing in dendritic trees. Neural Comput 6(6):1031\u20131085","journal-title":"Neural Comput"},{"key":"911_CR46","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.conb.2019.07.006","volume":"58","author":"A Payeur","year":"2019","unstructured":"Payeur A, B\u00e9\u00efque J-C, Naud R (2019) Classes of dendritic information processing. Curr Opin Neurobiol 58:78\u201385","journal-title":"Curr Opin Neurobiol"},{"key":"911_CR47","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1146\/annurev.neuro.28.061604.135703","volume":"28","author":"M London","year":"2005","unstructured":"London M, H\u00e4usser M (2005) Dendritic computation. Annu Rev Neurosci 28:503\u2013532","journal-title":"Annu Rev Neurosci"},{"key":"911_CR48","doi-asserted-by":"crossref","unstructured":"Jiang T, Wang D, Ji J, Todo Y, Gao S (2015) Single dendritic neuron with nonlinear computation capacity: a case study on xor problem. In: 2015 IEEE international conference on progress in informatics and computing (PIC). IEEE, pp 20\u201324","DOI":"10.1109\/PIC.2015.7489802"},{"key":"911_CR49","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.neunet.2014.07.011","volume":"60","author":"Y Todo","year":"2014","unstructured":"Todo Y, Tamura H, Yamashita K, Tang Z (2014) Unsupervised learnable neuron model with nonlinear interaction on dendrites. Neural Netw 60:96\u2013103","journal-title":"Neural Netw"},{"issue":"1","key":"911_CR50","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1162\/neco_a_01338","volume":"33","author":"A St\u00f6ckel","year":"2021","unstructured":"St\u00f6ckel A, Eliasmith C (2021) Passive nonlinear dendritic interactions as a computational resource in spiking neural networks. Neural Comput 33(1):96\u2013128","journal-title":"Neural Comput"},{"issue":"2","key":"911_CR51","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1152\/jn.1999.82.2.909","volume":"82","author":"A Anzai","year":"1999","unstructured":"Anzai A, Ohzawa I, Freeman RD (1999) Neural mechanisms for processing binocular information ii. Complex cells. J Neurophysiol 82(2):909\u2013924","journal-title":"J Neurophysiol"},{"key":"911_CR52","doi-asserted-by":"crossref","unstructured":"Koch C, Poggio T (1992) Multiplying with synapses and neurons. In: Single neuron computation. Elsevier, pp 315\u2013345","DOI":"10.1016\/B978-0-12-484815-3.50019-0"},{"key":"911_CR53","doi-asserted-by":"crossref","unstructured":"Todo Y, Tang Z, Todo H, Ji J, Yamashita K (2019) Neurons with multiplicative interactions of nonlinear synapses. Int J Neural Syst 29(08):1950012","DOI":"10.1142\/S0129065719500126"},{"issue":"16","key":"911_CR54","doi-asserted-by":"crossref","first-page":"R640","DOI":"10.1016\/S0960-9822(01)00381-5","volume":"11","author":"JW Schnupp","year":"2001","unstructured":"Schnupp JW, King AJ (2001) Neural processing: the logic of multiplication in single neurons. Curr Biol 11(16):R640\u2013R642","journal-title":"Curr Biol"},{"issue":"4","key":"911_CR55","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1109\/72.80265","volume":"1","author":"NE Cotter","year":"1990","unstructured":"Cotter NE (1990) The Stone\u2013Weierstrass theorem and its application to neural networks. IEEE Trans Neural Netw 1(4):290\u2013295","journal-title":"IEEE Trans Neural Netw"},{"issue":"4","key":"911_CR56","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1049\/ip-cds:20050252","volume":"153","author":"P Gao","year":"2006","unstructured":"Gao P, Woo W, Dlay S (2006) Weierstrass approach to blind source separation of multiple nonlinearly mixed signals. IEE Proc Circuits Devices Syst 153(4):332\u2013345","journal-title":"IEE Proc Circuits Devices Syst"},{"issue":"2","key":"911_CR57","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1049\/ip-vis:20045174","volume":"153","author":"P Gao","year":"2006","unstructured":"Gao P, Woo W, Dlay S (2006) Non-linear independent component analysis using series reversion and Weierstrass network. IEE Proc Vis Image Signal Process 153(2):115\u2013131","journal-title":"IEE Proc Vis Image Signal Process"},{"issue":"4","key":"911_CR58","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.1016\/j.asoc.2006.01.003","volume":"7","author":"RN Yadav","year":"2007","unstructured":"Yadav RN, Kalra PK, John J (2007) Time series prediction with single multiplicative neuron model. Appl Soft Comput 7(4):1157\u20131163","journal-title":"Appl Soft Comput"},{"issue":"12","key":"911_CR59","doi-asserted-by":"crossref","first-page":"10287","DOI":"10.1007\/s13369-020-04692-3","volume":"45","author":"S Kumar","year":"2020","unstructured":"Kumar S, Singh RK, Chaudhary A (2020) On the learning machine with amplificatory neuron in complex domain. Arab J Sci Eng 45(12):10287\u201310309","journal-title":"Arab J Sci Eng"},{"issue":"2","key":"911_CR60","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1152\/jn.1999.82.2.891","volume":"82","author":"A Anzai","year":"1999","unstructured":"Anzai A, Ohzawa I, Freeman RD (1999) Neural mechanisms for processing binocular information i. Simple cells. J Neurophysiol 82(2):891\u2013908","journal-title":"J Neurophysiol"},{"issue":"2","key":"911_CR61","doi-asserted-by":"crossref","first-page":"135","DOI":"10.3758\/BF03204959","volume":"15","author":"S Roberts","year":"1987","unstructured":"Roberts S (1987) Evidence for distinct serial processes in animals: the multiplicative-factors method. Anim Learn Behav 15(2):135\u2013173","journal-title":"Anim Learn Behav"},{"issue":"1","key":"911_CR62","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.eswa.2010.06.077","volume":"38","author":"M Fallahnezhad","year":"2011","unstructured":"Fallahnezhad M, Moradi MH, Zaferanlouei S (2011) A hybrid higher order neural classifier for handling classification problems. Expert Syst Appl 38(1):386\u2013393","journal-title":"Expert Syst Appl"},{"key":"911_CR63","doi-asserted-by":"crossref","unstructured":"Zhang M (2009) Artificial higher order neural network nonlinear models: Sas nlin or honns?. In: Artificial higher order neural networks for economics and business. IGI Global, pp 1\u201347","DOI":"10.4018\/978-1-59904-897-0.ch001"},{"issue":"1","key":"911_CR64","doi-asserted-by":"crossref","first-page":"192","DOI":"10.3758\/BF03206482","volume":"11","author":"E-J Wagenmakers","year":"2004","unstructured":"Wagenmakers E-J, Farrell S (2004) AIC model selection using Akaike weights. Psychonom Bull Rev 11(1):192\u2013196","journal-title":"Psychonom Bull Rev"},{"key":"911_CR65","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.ins.2017.09.057","volume":"423","author":"AB Greenblatt","year":"2018","unstructured":"Greenblatt AB, Agaian SS (2018) Introducing quaternion multi-valued neural networks with numerical examples. Inf Sci 423:326\u2013342","journal-title":"Inf Sci"},{"issue":"10","key":"911_CR66","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1007\/s00500-009-0502-5","volume":"14","author":"BK Tripathi","year":"2010","unstructured":"Tripathi BK, Kalra PK (2010) The novel aggregation function-based neuron models in complex domain. Soft Comput 14(10):1069\u20131081","journal-title":"Soft Comput"},{"issue":"3","key":"911_CR67","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1007\/s11063-017-9716-1","volume":"47","author":"C-A Popa","year":"2018","unstructured":"Popa C-A (2018) Learning algorithms for quaternion-valued neural networks. Neural Process Lett 47(3):949\u2013973","journal-title":"Neural Process Lett"},{"key":"911_CR68","doi-asserted-by":"crossref","unstructured":"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\u2013324","DOI":"10.1007\/978-3-540-45226-3_44"},{"key":"911_CR69","unstructured":"Parcollet T, Ravanelli M, Morchid M, Linar\u00e8s G, Trabelsi C, De\u00a0Mori R, Bengio Y (2018) Quaternion recurrent neural networks. arXiv preprint arXiv:1806.04418"},{"key":"911_CR70","unstructured":"Ramachandran P, Zoph B, Le QV (2017) Searching for activation functions. arXiv preprint arXiv:1710.05941"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00911-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-022-00911-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00911-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T23:05:37Z","timestamp":1701471937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-022-00911-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,28]]},"references-count":70,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["911"],"URL":"https:\/\/doi.org\/10.1007\/s40747-022-00911-6","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,28]]},"assertion":[{"value":"14 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}