{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T16:45:43Z","timestamp":1758818743904,"version":"3.37.3"},"reference-count":21,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Scienc","doi-asserted-by":"crossref","award":["20K11957"],"award-info":[{"award-number":["20K11957"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In recent years, neural networks have attracted much attention in the machine learning and the deep learning technologies. Bio-inspired functions and intelligence are also expected to process efficiently and improve existing technologies. In the visual pathway, the prominent features consist of nonlinear characteristics of squaring and rectification functions observed in the retinal and visual cortex networks, respectively. Further, adaptation is an important feature to activate the biological systems, efficiently. Recently, to overcome short-comings of the deep learning techniques, orthogonality for the weights in the networks has been developed for the signal propagation and the efficient optimization of the learning. In this paper, bio-inspired asymmetric networks with nonlinear characteristics are proposed, which are derived from the retinal networks in the biological visual pathway. The asymmetric network proposed here was verified to detect the movement of the object, efficiently in our previous studies. This paper shows a new characteristic of the adaptive orthogonality in the asymmetric networks. First, it is shown that the asymmetric network with nonlinear characteristics is effective for generating orthogonality. Second, the proposed asymmetric network with Gabor filters is compared with the conventional energy model from the point of the orthogonality characteristics. Finally, the asymmetric networks with nonlinear characteristics can generate the extended orthogonal bases in independent subspaces, which are useful for classification and efficient learning.<\/jats:p>","DOI":"10.1093\/jigpal\/jzab004","type":"journal-article","created":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T20:08:31Z","timestamp":1612037311000},"page":"578-598","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Orthogonal Characteristics of Bio-Inspired Neural Networks"],"prefix":"10.1093","volume":"30","author":[{"given":"Naohiro","family":"Ishii","sequence":"first","affiliation":[{"name":"Advanced Institute of Industrial Technology , Tokyo 140-0011, Japan"}]},{"given":"Toshinori","family":"Deguchi","sequence":"additional","affiliation":[{"name":"Gifu College National Institute of Technology, , Gifu 501-0495, Japan"}]},{"given":"Masashi","family":"Kawaguchi","sequence":"additional","affiliation":[{"name":"Suzuka College National Institute of Technology, , Mie 510-0294, Japan"}]},{"given":"Hiroshi","family":"Sasaki","sequence":"additional","affiliation":[{"name":"Fukui University of Technology , Fukui 910-8505, Japan"}]},{"given":"Tokuro","family":"Matsuo","sequence":"additional","affiliation":[{"name":"Advanced Institute of Industrial Technology , Tokyo 140-0011, Japan"}]}],"member":"286","published-online":{"date-parts":[[2021,2,4]]},"reference":[{"volume-title":"Autocorrelation, A Principle for the Evaluation of Sensory Information by the Central Nervous System, Sensory Communication.","year":"2012","author":"Reichard","key":"2022072013382409600_ref1"},{"volume-title":"Possible Principles Underlying the Transformations of Sensory Messages, Sensory Communication","year":"2012","author":"Barlow","key":"2022072013382409600_ref2"},{"key":"2022072013382409600_ref3","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1364\/JOSAA.2.000284","article-title":"Spatiotemporal energy models for the perception of motion","volume":"2","author":"Adelson","year":"1985","journal-title":"Journal of the Optical Society of America. A"},{"key":"2022072013382409600_ref4","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"key":"2022072013382409600_ref5","first-page":"1","article-title":"Learning convolutional neural networks using hybrid orthogonal projection and estimation, ACML 2017","volume":"77","author":"Pan","year":"2017","journal-title":"Proceedings of Machine Learning Research"},{"key":"2022072013382409600_ref6","first-page":"1","article-title":"Can we gain more from orthogonality regularizations in training deep CNNs?","volume-title":"Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS2018), Montreal, Canada","author":"Bansal","year":"2018"},{"key":"2022072013382409600_ref7","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.neunet.2012.09.020","article-title":"The No-Prop algorithm: a new learning algorithm for multilayer neural networks","volume":"37","author":"Widrow","year":"2013","journal-title":"Neural Networks"},{"key":"2022072013382409600_ref8","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1109\/5.58323","article-title":"30 years of adaptive neural networks: perceptron, Madaline, and backpropagation","volume":"78","author":"Widrow","year":"1990","journal-title":"Proceedings of the IEEE"},{"key":"2022072013382409600_ref9","first-page":"3271","article-title":"Orthogonal weight normalization: solution to optimization over multiple dependent Stiefel manifolds in deep neural networks","volume-title":"32nd AAAI Conference on AI, AAAI-18","author":"Huang","year":"2018"},{"key":"2022072013382409600_ref10","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.patcog.2018.03.036","article-title":"Entropy orthogonality based deep discriminative feature learning for object recognition","volume":"81","author":"Shi","year":"2018","journal-title":"Pattern Recognition"},{"key":"2022072013382409600_ref11","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1016\/S0042-6989(97)00183-1","article-title":"Model of neuronal responses in visual area MT","volume":"38","author":"Simoncelli","year":"1996","journal-title":"Vision Research"},{"article-title":"Models of motion perception","year":"1987","author":"Heeger","key":"2022072013382409600_ref12"},{"key":"2022072013382409600_ref13","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1073\/pnas.1619788114","article-title":"Theory of cortical function","volume":"114","author":"Heeger","year":"2017","journal-title":"Proceedings of the National Academy of Sciences of the USA"},{"key":"2022072013382409600_ref14","first-page":"129","article-title":"A model for the estimate of local image velocity by cells in the visual cortex","volume":"239","author":"Grzywacz","year":"1990","journal-title":"Proceedings of the Royal Society of London, Series B"},{"key":"2022072013382409600_ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4613-3970-0","volume-title":"Analysis of Physiological Systems\u2014The White Noise Approach","author":"Marmarelis","year":"1978"},{"key":"2022072013382409600_ref16","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1152\/jn.1985.53.2.411","article-title":"Signal transmission in the catfish retina. III. Transmission to type-C cell","volume":"53","author":"Sakuranaga","year":"1985","journal-title":"Journal of Neurophysiology"},{"key":"2022072013382409600_ref17","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1152\/jn.1987.58.6.1329","article-title":"Signal transmission in the catfish retina, V. Sensitivity and circuit","volume":"58","author":"Sakai","year":"1987","journal-title":"Journal of Neurophysiology"},{"key":"2022072013382409600_ref18","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/BF02367380","article-title":"Generation and transformation of second-order nonlinearity in catfish retina","volume":"16","author":"Naka","year":"1988","journal-title":"Annals of Biomedical Engineering"},{"key":"2022072013382409600_ref19","first-page":"409","volume-title":"Advances in Neural Networks","author":"Ishii","year":"2016"},{"key":"2022072013382409600_ref20","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/978-3-319-92639-1_16","volume-title":"Intelligent Hybrid Artificial Systems","author":"Ishii","year":"2018"},{"key":"2022072013382409600_ref21","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1007\/978-3-030-29859-3_50","volume-title":"Intelligent Hybrid Artificial Systems","author":"Ishii","year":"2019"}],"container-title":["Logic Journal of the IGPL"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jigpal\/article-pdf\/30\/4\/578\/45027500\/jzab004.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jigpal\/article-pdf\/30\/4\/578\/45027500\/jzab004.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T13:40:24Z","timestamp":1658324424000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jigpal\/article\/30\/4\/578\/6126299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,4]]},"references-count":21,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2,4]]},"published-print":{"date-parts":[[2022,7,25]]}},"URL":"https:\/\/doi.org\/10.1093\/jigpal\/jzab004","relation":{},"ISSN":["1367-0751","1368-9894"],"issn-type":[{"type":"print","value":"1367-0751"},{"type":"electronic","value":"1368-9894"}],"subject":[],"published-other":{"date-parts":[[2022,7,19]]},"published":{"date-parts":[[2021,2,4]]}}}