{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,2]],"date-time":"2025-03-02T05:40:41Z","timestamp":1740894041407,"version":"3.38.0"},"reference-count":12,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2000,2,1]],"date-time":"2000-02-01T00:00:00Z","timestamp":949363200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2000,2]]},"abstract":"<jats:p> This paper addresses the problem of developing efficient parallel algorithms for the training procedure of a neural network-based Fingerprint Image Comparison (FIC) system. The target architecture is assumed to be a coarse-grain distributed-memory parallel architecture. Two types of parallelism\u2014node parallelism and training set parallelism (TSP)\u2014are investigated. Theoretical analysis and experimental results show that node parallelism has low speedup and poor scalability, while TSP proves to have the best speedup performance. TSP, however, is amenable to a slow convergence rate. To reduce this effect, a modified training set parallel algorithm using weighted contributions of synaptic connections is proposed. Experimental results show that this algorithm provides a fast convergence rate while keeping the best speedup performance obtained. The combination of TSP with node parallelism is also investigated. A good performance is achieved by this approach. This provides better scalability with the trade-off of a slight decrease in speedup. The above algorithms are implemented on a 32-node CM-5. <\/jats:p>","DOI":"10.1177\/109434200001400101","type":"journal-article","created":{"date-parts":[[2005,3,8]],"date-time":"2005-03-08T19:23:21Z","timestamp":1110309801000},"page":"3-25","source":"Crossref","is-referenced-by-count":1,"title":["Parallel Algorithms for the Training Process of a Neural Network-Based System"],"prefix":"10.1177","volume":"14","author":[{"given":"Hany H.","family":"Ammar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Electrical Engineering, West Virginia\r                        University, Morgantown, West Virginia, U.S.A."}]},{"given":"Zhouhui","family":"Miao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Electrical Engineering, West Virginia\r                        University, Morgantown, West Virginia, U.S.A."}]}],"member":"179","published-online":{"date-parts":[[2000,2,1]]},"reference":[{"key":"atypb1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.3.402"},{"volume-title":"Computer Vision","year":"1982","author":"Ballard","key":"atypb2"},{"volume-title":"Neural Networks: A Comprehensive Foundation","year":"1994","author":"Haykin, S.","key":"atypb3"},{"first-page":"143","volume-title":"Proceedings of the IEEE International Conference on Neural Networks","author":"Pomerleau, D. A.","key":"atypb4"},{"first-page":"329","volume-title":"Proceedings of 10th International Conference on Artificial Intelligence","author":"Rosenberg, C. R.","key":"atypb5"},{"key":"atypb6","doi-asserted-by":"publisher","DOI":"10.1109\/2.485893"},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(90)90083-L"},{"volume-title":"Fourth International Conference on Artificial Neural Networks","author":"T\u00f8rresen, J.","key":"atypb8"},{"key":"atypb9","doi-asserted-by":"publisher","DOI":"10.6028\/NBS.TN.466"},{"key":"atypb10","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.4880"},{"key":"atypb11","unstructured":"Zeng, S. 1994. The application of parallel processing techniques to neural\n                network based fingerprint recognition systems. Ph.D. thesis, Department of\n                Electrical and Computer Engineering, West Virginia University."},{"key":"atypb12","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/0167-8191(90)90084-M","volume":"14","author":"Zhang, X.","year":"1990","journal-title":"Parallel Computing"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/109434200001400101","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/109434200001400101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T11:51:34Z","timestamp":1740829894000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/109434200001400101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000,2]]},"references-count":12,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2000,2]]}},"alternative-id":["10.1177\/109434200001400101"],"URL":"https:\/\/doi.org\/10.1177\/109434200001400101","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"type":"print","value":"1094-3420"},{"type":"electronic","value":"1741-2846"}],"subject":[],"published":{"date-parts":[[2000,2]]}}}