{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T03:50:29Z","timestamp":1761969029244,"version":"build-2065373602"},"reference-count":19,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Adv. Adapt. Data Anal."],"published-print":{"date-parts":[[2011,7]]},"abstract":"<jats:p>We propose an initialization method for feedforward artificial neural networks (FFANNs) trained to model physical systems. A polynomial solution of the physical system is obtained using a mathematical model and then mapped into the neural network to initialize its weights. The network can next be trained with a dataset to refine its accuracy. We focus attention on an elliptical partial differential equation modeled using a feedforward backpropagation network. We present a numerical example and compare our method with other initialization methods. Our method converges nearly 90% faster compared to random weights, with higher probability of convergence to an acceptable local minimum.<\/jats:p>","DOI":"10.1142\/s1793536911000684","type":"journal-article","created":{"date-parts":[[2011,10,24]],"date-time":"2011-10-24T09:37:59Z","timestamp":1319449079000},"page":"385-400","source":"Crossref","is-referenced-by-count":6,"title":["AN INITIALIZATION METHOD FOR FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING POLYNOMIAL BASES"],"prefix":"10.1142","volume":"03","author":[{"given":"THANASIS M.","family":"VARNAVA","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering and Materials Science, William Marsh Rice University, 6100 Main Street, Houston, Texas, 77005-1892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"JR.","given":"ANDREW J.","family":"MEADE","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering and Materials Science, William Marsh Rice University, 6100 Main Street, Houston, Texas, 77005-1892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2012,4,5]]},"reference":[{"volume-title":"Spectral Methods in Fluid Dynamics","year":"1987","author":"Canto C.","key":"rf2"},{"key":"rf3","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753713007"},{"key":"rf4","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"volume-title":"The Method of Weighted Residuals and Variational Principles","year":"1972","author":"Finlayson B. A.","key":"rf5"},{"key":"rf6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00195855"},{"key":"rf7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.2.219"},{"volume-title":"Neurocomputing","year":"1990","author":"Hecht-Nielsen R.","key":"rf8"},{"key":"rf9","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"rf10","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90005-6"},{"key":"rf12","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90075-G"},{"key":"rf13","doi-asserted-by":"publisher","DOI":"10.1002\/0470855487"},{"key":"rf15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.5.982"},{"key":"rf16","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80131-5"},{"key":"rf17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.1.164"},{"key":"rf18","doi-asserted-by":"publisher","DOI":"10.1109\/5.58326"},{"key":"rf19","doi-asserted-by":"publisher","DOI":"10.1126\/science.247.4945.978"},{"key":"rf21","doi-asserted-by":"crossref","unstructured":"D.\u00a0Rumelhart, G. E.\u00a0Hinton and R. J.\u00a0Williams, Parallel Distributed Processing: Exploration in the Microstructure of Cognition, eds. D.\u00a0Rumelhart and J. L.\u00a0McClelland (MIT Press, Cambridge, MA, 1986)\u00a0pp. 318\u2013362.","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"rf22","doi-asserted-by":"publisher","DOI":"10.1137\/0914044"},{"key":"rf24","first-page":"378","volume":"7","author":"Xiao R.","journal-title":"J. Zhejiang Univ. Sci. A"}],"container-title":["Advances in Adaptive Data Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1793536911000684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,26]],"date-time":"2020-06-26T12:14:03Z","timestamp":1593173643000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S1793536911000684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,7]]},"references-count":19,"journal-issue":{"issue":"03","published-online":{"date-parts":[[2012,4,5]]},"published-print":{"date-parts":[[2011,7]]}},"alternative-id":["10.1142\/S1793536911000684"],"URL":"https:\/\/doi.org\/10.1142\/s1793536911000684","relation":{},"ISSN":["1793-5369","1793-7175"],"issn-type":[{"type":"print","value":"1793-5369"},{"type":"electronic","value":"1793-7175"}],"subject":[],"published":{"date-parts":[[2011,7]]}}}