{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:38:43Z","timestamp":1764833923722,"version":"3.46.0"},"reference-count":31,"publisher":"World Scientific Pub Co Pte Ltd","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[2025,12,15]]},"abstract":"<jats:p>Machine learning, deep learning and neural networks are extensively developed in many fields, with neural networks playing an important role in a wide variety of applications. However, a sufficient explanation of the structure and functionality of complex and deep neural networks is still needed. In this paper, it is shown that bio-inspired networks are useful for the explanation of network functions. First, the asymmetric network is created based on the biological retinal networks. Second, the classification performance of the asymmetric network is compared to that of the symmetric networks. The directional vectors in the asymmetric networks are generated on the adjacent neurons caused by movement stimulus, which create independent subspaces. Vectors for the movement stimulus are reported experimentally to be generated in the layered cortex in the brain. In this paper, it is shown computationally that many directional movement vectors are generated in the layered asymmetric networks, which create also independent subspaces. Further, when the correlational activities of the adjacent cells are represented in the directed vectors, they create independent subspaces than the direct inputs in the networks. These asymmetric subnetworks will facilitate the transmission of sensory information to higher-level processes such as efficient feature extraction, classification, and learning in the layered networks.<\/jats:p>","DOI":"10.1142\/s0129065725500790","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T12:46:26Z","timestamp":1761914786000},"source":"Crossref","is-referenced-by-count":0,"title":["Directed Vectors for Generation of Independent Subspaces in the Bio-inpired Networks"],"prefix":"10.1142","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3840-1763","authenticated-orcid":false,"given":"Naohiro","family":"Ishii","sequence":"first","affiliation":[{"name":"Computer Architecture, Advanced Institute of Industrial Technology, 1-10-40, Higashiooi, Shinagawa-ku, Tokyo 140-0011, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8291-4735","authenticated-orcid":false,"given":"Kazunori","family":"Iwata","sequence":"additional","affiliation":[{"name":"Faculty of Business Administration, Aichi University, 4-60-6, Hiraikecho, Nakamura-ku, Nagoya, Aichi 453-8777, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7831-0506","authenticated-orcid":false,"given":"Kazuya","family":"Odagiri","sequence":"additional","affiliation":[{"name":"Department of Information Design Studies, Sugiyama Jogakuen University 17-3, Hoshigaoka-motomachi, Chikusa-ku, Nagoya, Aichi 464-8662, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3551-8799","authenticated-orcid":false,"given":"Tokuro","family":"Matsuo","sequence":"additional","affiliation":[{"name":"Computer Architecture, Advanced Institute of Industrial Technology 1-10-40, Higashiooi, Shinagawa-ku, Tokyo, 140-0011, Japan"}]}],"member":"219","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"S0129065725500790BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"S0129065725500790BIB002","first-page":"1","volume":"23","author":"Peng X.","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"S0129065725500790BIB003","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.00007"},{"key":"S0129065725500790BIB004","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.92.7.2433"},{"key":"S0129065725500790BIB005","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(83)90081-4"},{"key":"S0129065725500790BIB006","doi-asserted-by":"publisher","DOI":"10.1007\/s003590050397"},{"key":"S0129065725500790BIB007","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-020-0336-9"},{"key":"S0129065725500790BIB008","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9504.003.0038"},{"key":"S0129065725500790BIB009","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"S0129065725500790BIB010","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0287736"},{"key":"S0129065725500790BIB011","doi-asserted-by":"crossref","unstructured":"T. He, Z. Li, Y. Gong, Y. Yao, X. Nie and Y. Yin, Exploring linear feature disentanglement for neural networks, preprint (2022), arXiv:2203.11700v1, https:\/\/doi.org\/10.1109\/ICME52920.2022.9859978.","DOI":"10.1109\/ICME52920.2022.9859978"},{"key":"S0129065725500790BIB012","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2008.00674.x"},{"key":"S0129065725500790BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3388526"},{"key":"S0129065725500790BIB014","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.2.000284"},{"issue":"4","key":"S0129065725500790BIB015","first-page":"63","volume":"11","author":"Fukushima K.","year":"2007","journal-title":"Neural Inf. Process."},{"key":"S0129065725500790BIB016","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10448-w"},{"key":"S0129065725500790BIB017","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500254"},{"key":"S0129065725500790BIB018","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015312"},{"key":"S0129065725500790BIB019","doi-asserted-by":"publisher","DOI":"10.1088\/0954-898X_14_4_308"},{"key":"S0129065725500790BIB020","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00183-1"},{"key":"S0129065725500790BIB021","doi-asserted-by":"publisher","DOI":"10.1017\/S0952523800009640"},{"key":"S0129065725500790BIB022","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1984.52.6.1106"},{"key":"S0129065725500790BIB023","first-page":"315","volume-title":"Proc. 14th Int. Conf. Artificial Intelligence and Statistics","volume":"15","author":"Glorot X.","year":"2011"},{"key":"S0129065725500790BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/BF02367380"},{"key":"S0129065725500790BIB025","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1985.53.2.411"},{"volume-title":"Analysis of Physiological Systems \u2014 The White Noise Approach","year":"2011","author":"Marmarelis P. Z.","key":"S0129065725500790BIB026"},{"key":"S0129065725500790BIB027","doi-asserted-by":"publisher","DOI":"10.1002\/9780471679370"},{"key":"S0129065725500790BIB028","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-022-00606-4"},{"key":"S0129065725500790BIB029","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00767.2004"},{"key":"S0129065725500790BIB030","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2145-21.2022"},{"key":"S0129065725500790BIB031","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62495-7_34"}],"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065725500790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:06:13Z","timestamp":1764831973000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0129065725500790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":31,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12,15]]}},"alternative-id":["10.1142\/S0129065725500790"],"URL":"https:\/\/doi.org\/10.1142\/s0129065725500790","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"type":"print","value":"0129-0657"},{"type":"electronic","value":"1793-6462"}],"subject":[],"published":{"date-parts":[[2025,11,26]]},"article-number":"2550079"}}