{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:32:16Z","timestamp":1777703536075,"version":"3.51.4"},"reference-count":23,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2019,8,7]],"date-time":"2019-08-07T00:00:00Z","timestamp":1565136000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,9,9]]},"abstract":"<jats:p>\n                    In this paper we present a new algorithm called Neural Network Pruning Based on Input Importance (NNPII) that prunes the neural network based on the input importance. The algorithm depends on the frequency of using a certain value of an attribute in all the given instances in the dataset. Pruning will include only links between input layer and hidden layer. The algorithm has three phases, the first phase is the preprocessing phase, where the data inputs are replaced with their importance. The second phase is a forward pass, which is similar to forward pass in the backpropgation algorithm, but instead of using the real inputs as inputs, we use the input importance obtained in the preprocessing stage. The third pass is the backward phase which is again as backpropgation algorithm, but in this stage we use the input importance instead of real inputs, and\n                    <jats:italic>\u03b2<\/jats:italic>\n                    factor that measures the value changing for every input attribute,\n                    <jats:italic>\u03b2<\/jats:italic>\n                    will be incorporated in the formula in updating the weights between the input layer and the hidden layer. The elimination process is performed based on criterion that depends on\n                    <jats:italic>\u03a9<\/jats:italic>\n                    factor that represents a threshold value for a certain input attribute for all instances. It is worth mentioning that the pruning is performed within the usual training phases. The proposed algorithm has been tested through three types of experiments, a comparison between backpropgation and NNPII, Applying NNPII with various parameter values and finally comparing NNPII with other various pruning algorithms. Results show that NNPII performs well and compete with other pruning algorithms. NNPII outperforms all other algorithms when the classes are fairly distributed in the datasets.\n                  <\/jats:p>","DOI":"10.3233\/jifs-182544","type":"journal-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T11:29:34Z","timestamp":1565695774000},"page":"2243-2252","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["Neural network pruning based on input importance"],"prefix":"10.1177","volume":"37","author":[{"given":"Nabil M.","family":"Hewahi","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of IT, University of Bahrain, Sakheer, Manama, Bahrain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2019,8,7]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"R.Abbasi-Asl and B.Yu Structural Compression of Convolutional Neural Networks Based on Greedy Filter Pruning Cornell University arXiv:1705.07356v3 [cs.CV] 21 Jul 2017."},{"key":"e_1_3_1_3_2","unstructured":"R.Abbasi-Asl and B.Yu Interpreting Convolutional Neural Networks Through Compression Cornell University arXiv:1711.02329v1 [stat.ML] presented at NIPS 2017 Symposium on Interpretable Machine Learning 7 Nov 2017."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-011-9196-7"},{"issue":"3","key":"e_1_3_1_5_2","first-page":"105","article-title":"Pruning algorithms of neural networks - a comparative study","volume":"3","author":"Augasta M.","year":"2013","unstructured":"M.Augasta and T.Kathirvalavakumar, Pruning algorithms of neural networks - a comparative study, Central European Journal of Computer Science 3(3) (2013), 105\u2013115.","journal-title":"Central European Journal of Computer Science"},{"key":"e_1_3_1_6_2","volume-title":"proceedings of the 29th Conference on Neural Information Processing Systems (NIPS)","author":"Babaeizadeh M.","year":"2016","unstructured":"M.Babaeizadeh, P.Smaragdis and R.Campbell, NoiseOut: A SimpleWay to Prune Neural Networks, in the proceedings of the 29th Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain, 2016."},{"key":"e_1_3_1_7_2","first-page":"22","article-title":"Neurons vs Weights Pruning in Artificial Neural Networks","author":"Bondarenko A.","year":"2015","unstructured":"A.Bondarenko, A.Borisov and L.Aleksejeva, Neurons vs Weights Pruning in Artificial Neural Networks, Environment Technology, Resources III (2015), 22\u201328.","journal-title":"Environment Technology, Resources"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.572092"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.963775"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(94)90055-8"},{"key":"e_1_3_1_11_2","volume-title":"Proceedings of Neural Information Processing System Conference, NIPS 2015, poster","author":"Han S.","year":"2015","unstructured":"S.Han, J.Pool, J.Tran and W.Dally, Learning both Weights and Connections for Efficient Neural Networks, Proceedings of Neural Information Processing System Conference, NIPS 2015, poster, 2015."},{"key":"e_1_3_1_12_2","first-page":"293","volume-title":"Proceedings of IEEE  ICNN\u201993,1, WDS\u201908 Proceedings of Contributed Papers, Part I","author":"Hassibi B.","year":"2008","unstructured":"B.Hassibi, D.G.Stork and G.J.Wolf, Optimal brain surgeon and general network pruning, Proceedings of IEEE ICNN\u201993,1, WDS\u201908 Proceedings of Contributed Papers, Part I, (2008), 293\u2013299."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2001.939461"},{"key":"e_1_3_1_14_2","first-page":"598","article-title":"Optimal brain damage","volume":"2","author":"Le Cun Y.","year":"1990","unstructured":"Y.Le Cun, J.S.Denker and S.A.Solla, In. D. S.Touretzky (Ed.), Optimal brain damage, Advances in neural information processing systems (Morgan Kaufmann, San Mateo, 1990) 2 (1990), 598\u2013605.","journal-title":"Advances in neural information processing systems (Morgan Kaufmann, San Mateo, 1990)"},{"key":"e_1_3_1_15_2","volume-title":"5th International Conference on Learning Representations (ICLR 2017)","author":"Molchanov P.","year":"2017","unstructured":"P.Molchanov, S.Tyree, T.Karras, T.Aila and J.Kautz, Pruning convolutional neural networks for resource efficient inference, 5th International Conference on Learning Representations (ICLR 2017), Toulon, France, April 24 - 26, 2017."},{"key":"e_1_3_1_16_2","unstructured":"W.Pan H.Dong and Y.Guo DropNeuron: Simplifying the Structure of Deep Neural Networks Cornell University arXiv :1606.07326v3 [cs.CV] 3 Jul 2016."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.774273"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","unstructured":"C.Sabo and X.Yu A new pruning algorithm for neural network dimension analysis International Joint Conference on Neural Networks (2008) 3313\u20133318.","DOI":"10.1109\/IJCNN.2008.4634268"},{"issue":"1","key":"e_1_3_1_19_2","first-page":"75","article-title":"Two methods for pruning neural networks: A performance evaluation","volume":"13","author":"Schiavo R.","year":"2001","unstructured":"R.Schiavo, Two methods for pruning neural networks: A performance evaluation, Statistica Applicata 13(1) (2001), 75\u201388.","journal-title":"Statistica Applicata"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01501173"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009639214138"},{"key":"e_1_3_1_22_2","unstructured":"UCI Machine Learning repository https:\/\/archive.ics.uci.edu\/ml\/datasets.html"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005604"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1590\/S1982-21702013000400003"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-182544","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-182544","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-182544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:38:55Z","timestamp":1777455535000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-182544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,7]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,9,9]]}},"alternative-id":["10.3233\/JIFS-182544"],"URL":"https:\/\/doi.org\/10.3233\/jifs-182544","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,7]]}}}