{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:46Z","timestamp":1740108046203,"version":"3.37.3"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"30","license":[{"start":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T00:00:00Z","timestamp":1691625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T00:00:00Z","timestamp":1691625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41706198"],"award-info":[{"award-number":["41706198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00521-023-08881-7","type":"journal-article","created":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T12:09:54Z","timestamp":1691669394000},"page":"22431-22447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Power-law initialization algorithm for convolutional neural networks"],"prefix":"10.1007","volume":"35","author":[{"given":"Kaiwen","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongtong","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunyao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengjing","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rencheng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,10]]},"reference":[{"issue":"7553","key":"8881_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"8881_CR2","doi-asserted-by":"publisher","first-page":"25-195","DOI":"10.1109\/ACCESS.2019.2899901","volume":"7","author":"NU Islam","year":"2019","unstructured":"Islam NU, Lee S (2019) Interpretation of deep cnn based on learning feature reconstruction with feedback weights. IEEE Access 7:25-195\u201325-208","journal-title":"IEEE Access"},{"key":"8881_CR3","doi-asserted-by":"crossref","unstructured":"Go J, Baek B, Lee C (2004) Analyzing weight distribution of feedforward neural networks and efficient weight initialization. In: Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR). Springer, pp 840\u2013849","DOI":"10.1007\/978-3-540-27868-9_92"},{"key":"8881_CR4","unstructured":"Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv:1609.04747"},{"key":"8881_CR5","first-page":"21","volume":"1990","author":"D. Nguyen and B. Widrow, Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights, in","year":"1990","unstructured":"D. Nguyen and B. Widrow, Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights, in (1990) IJCNN international joint conference on neural networks. IEEE 1990:21\u201326","journal-title":"IEEE"},{"issue":"2","key":"8881_CR6","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1109\/72.914538","volume":"12","author":"JY Yam","year":"2001","unstructured":"Yam JY, Chow TW (2001) Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficients. IEEE Trans. Neural Netw 12(2):430\u2013434","journal-title":"IEEE Trans. Neural Netw"},{"key":"8881_CR7","doi-asserted-by":"crossref","unstructured":"Sodhi SS, Chandra P, Tanwar S (2014), A new weight initialization method for sigmoidal feedforward artificial neural networks. In: 2014 international joint conference on neural networks (IJCNN). IEEE, pp 291\u2013298","DOI":"10.1109\/IJCNN.2014.6889373"},{"key":"8881_CR8","first-page":"5","volume":"1524","author":"Y Cun","year":"1998","unstructured":"Cun Y, Bottou L, Orr G, Muller K (1998) Efficient backprop, neural networks: tricks of the trade. Lect Notes Comput Sci 1524:5\u201350","journal-title":"Lect Notes Comput Sci"},{"key":"8881_CR9","unstructured":"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. JMLR Workshop and Conference Proceedings, pp 249\u2013256"},{"key":"8881_CR10","unstructured":"Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv:1609.04747"},{"key":"8881_CR11","doi-asserted-by":"crossref","unstructured":"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\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"8881_CR12","doi-asserted-by":"crossref","unstructured":"Hirasawa K, Ohbayashi M, Koga M, Harada M (1996) Forward propagation universal learning network. In: Proceedings of international conference on neural networks (ICNN\u201996), vol\u00a01. minus IEEE, pp 353\u2013358","DOI":"10.1109\/ICNN.1996.548917"},{"issue":"6088","key":"8881_CR13","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"D.\u00a0E Rumelhart","year":"1986","unstructured":"Rumelhart D.\u00a0E, Hinton G.\u00a0E, Williams R.\u00a0J (1986) Learning representations by back-propagating errors. Nature 323(6088):533\u2013536","journal-title":"Nature"},{"issue":"1","key":"8881_CR14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.94.018102","volume":"94","author":"VM Eguiluz","year":"2005","unstructured":"Eguiluz VM, Chialvo DR, Cecchi GA, Baliki M, Apkarian AV (2005) Scale-free brain functional networks. Phys Rev Lett 94(1):018102","journal-title":"Phys Rev Lett"},{"key":"8881_CR15","first-page":"048","volume":"007","author":"X Tongtong","year":"2022","unstructured":"Tongtong X, Rencheng S, Fengjing S, Yi S (2022) Research on weight initialization method in deep learning. Comput Eng 007:048","journal-title":"Comput Eng"},{"issue":"6","key":"8881_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"8881_CR17","doi-asserted-by":"crossref","unstructured":"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\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8881_CR18","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"8881_CR19","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems 28 (NIPS 2015)"},{"key":"8881_CR20","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et\u00a0al (2019) Pytorch: an imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems 32 (NeurIPS 2019). arXiv:1912.01703"},{"key":"8881_CR21","unstructured":"Ioffe S, Szegedy C (2015), Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. pmlr, pp 448\u2013456"},{"key":"8881_CR22","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-642-04898-2_319","volume-title":"Jarque-Bera test","author":"CM Jarque","year":"2011","unstructured":"Jarque CM (2011) Jarque-Bera test. Springer, Berlin, pp 701\u2013702. https:\/\/doi.org\/10.1007\/978-3-642-04898-2_319"},{"issue":"1","key":"8881_CR23","doi-asserted-by":"publisher","first-page":"52","DOI":"10.5395\/rde.2013.38.1.52","volume":"38","author":"H-Y Kim","year":"2013","unstructured":"Kim H-Y (2013) Statistical notes for clinical researchers: assessing normal distribution (2) using skewness and kurtosis. Restor Dent Endod 38(1):52\u201354","journal-title":"Restor Dent Endod"},{"key":"8881_CR24","unstructured":"Hou L, Kwok JT (2018) Power law in sparsified deep neural networks. arXiv:1805.01891"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08881-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08881-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08881-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T15:06:43Z","timestamp":1694876803000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08881-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,10]]},"references-count":24,"journal-issue":{"issue":"30","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8881"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08881-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,8,10]]},"assertion":[{"value":"7 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The weight data for the pretrained models supporting the findings of this study are publicly available for download at .","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data availability"}},{"value":"The authors declare no potential conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}