{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T10:51:47Z","timestamp":1720003907869},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T00:00:00Z","timestamp":1441065600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Regional Development Fund"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Mathematics and Computation"],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1016\/j.amc.2015.04.123","type":"journal-article","created":{"date-parts":[[2015,5,26]],"date-time":"2015-05-26T20:47:48Z","timestamp":1432673268000},"page":"119-138","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["An efficient initialization mechanism of neurons for Winner Takes All Neural Network implemented in the CMOS technology"],"prefix":"10.1016","volume":"267","author":[{"given":"Tomasz","family":"Tala\u015bka","sequence":"first","affiliation":[]},{"given":"Marta","family":"Kolasa","sequence":"additional","affiliation":[]},{"given":"Rafa\u0142","family":"D\u0142ugosz","sequence":"additional","affiliation":[]},{"given":"Pierre-Andr\u00e9","family":"Farine","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.amc.2015.04.123_b0005","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/TNN.2008.2009120","article-title":"Comparison between analog and digital neural network implementations for range-finding applications","volume":"20","author":"Gatet","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"issue":"8","key":"10.1016\/j.amc.2015.04.123_b0010","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1109\/JSSC.2004.831805","article-title":"A high-speed and low-voltage associative co-processor with exact Hamming\/Manhattan-distance estimation using word-parallel and hierarchical search architecture","volume":"39","author":"Oike","year":"2004","journal-title":"IEEE J. Solid-State Circuits"},{"key":"10.1016\/j.amc.2015.04.123_b0015","doi-asserted-by":"crossref","unstructured":"S. Sasaki, M. Yasuda, H.J. Mattausch, Digital associative memory for word-parallel Manhattan-distance-based vector quantization 38th European solid-state circuit conference (ESSCIRC), France, Sept. 2012, pp. 185\u2013188.","DOI":"10.1109\/ESSCIRC.2012.6341289"},{"issue":"Iss. 6","key":"10.1016\/j.amc.2015.04.123_b0020","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1109\/TNN.2010.2046497","article-title":"Realization of the conscience mechanism in CMOS implementation of winner-takes-all self-organizing neural networks","volume":"21","author":"D\u0142ugosz","year":"2010","journal-title":"IEEE Trans. Neural Netw."},{"issue":"Iss. 1","key":"10.1016\/j.amc.2015.04.123_b0025","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/TCSII.2010.2092827","article-title":"Current-mode analog adaptive mechanism for ultra-low power neural networks","volume":"58","author":"D\u0142ugosz","year":"2011","journal-title":"IEEE Trans. Circuits Syst.\u2013II: Express Briefs"},{"issue":"1","key":"10.1016\/j.amc.2015.04.123_b0030","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.mejo.2009.12.009","article-title":"Low power current-mode binary-tree asynchronous min\/max circuit","volume":"41","author":"D\u0142ugosz","year":"2010","journal-title":"Microelectron. J., Elsevier"},{"key":"10.1016\/j.amc.2015.04.123_b0035","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neunet.2011.09.002","article-title":"A programmable triangular neighborhood function for a Kohonen self-organizing map implemented on chip","volume":"25","author":"Kolasa","year":"2012","journal-title":"Neural Netw."},{"issue":"11","key":"10.1016\/j.amc.2015.04.123_b0040","doi-asserted-by":"crossref","DOI":"10.1109\/JSEN.2009.2028775","article-title":"Autonomous sensor nodes for aircraft structural health monitoring","volume":"9","author":"Becker","year":"2009","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.amc.2015.04.123_b0045","doi-asserted-by":"crossref","unstructured":"M. Vodel, M. Lippmann M.W. Hardt, Energy-efficient communication with wake-up receiver technologies and an optimised protocol stack, International Conference on Advances in ICT for Emerging Regions (ICTer), 2013.","DOI":"10.1109\/ICTer.2013.6761175"},{"issue":"1","key":"10.1016\/j.amc.2015.04.123_b0050","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11276-010-0252-4","article-title":"A survey on wireless body area networks","volume":"17","author":"Latr\u00e9","year":"2011","journal-title":"Wireless Netw."},{"key":"10.1016\/j.amc.2015.04.123_b0055","doi-asserted-by":"crossref","unstructured":"D. Nguyen, B. Widrow, Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights, International Joint Conference on Neural Networks (IJCNN), San Diego, USA, pp. 21\u201326 (III), 1990.","DOI":"10.1109\/IJCNN.1990.137819"},{"key":"10.1016\/j.amc.2015.04.123_b0060","unstructured":"K. Kenni, K.Nakayama, H. Shimodaira, Estimation of initial weight and hidden units for fast learning of multi-layer neural network for pattern classification, International Joint Conference on Neural Networks (IJCNN), Washington, USA, vol. 3, pp. 1652\u20131656, 1999."},{"key":"10.1016\/j.amc.2015.04.123_b0065","doi-asserted-by":"crossref","unstructured":"Y.K. Kim, J.B. Ra, Weight value initialization for improving training speed in the backpropagation network, International Joint Conference on Neural Networks (IJCNN), Seattle, USA, Vol. 3, pp. 2396\u20132401, 1991.","DOI":"10.1109\/IJCNN.1991.170747"},{"key":"10.1016\/j.amc.2015.04.123_b0070","unstructured":"T. Tala\u015bka, R. D\u0142ugosz, Initialization mechanism in Kohonen neural network implemented in CMOS technology, in: 11th European Symposium on Artificial Neural Networks (ESANN), 2008, Bruges, Belgium, pp. 337\u2013342."},{"key":"10.1016\/j.amc.2015.04.123_b0075","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/0893-6080(90)90071-R","article-title":"Competitive learning algorithms for vector quantization","volume":"3","author":"Ahalt","year":"1990","journal-title":"Neural Netw."},{"key":"10.1016\/j.amc.2015.04.123_b0080","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/ICNN.1988.23839","article-title":"Adding a conscience to competitive learning","volume":"1","author":"DeSieno","year":"1988","journal-title":"IEEE Conf. Neural Netw."},{"issue":"14","key":"10.1016\/j.amc.2015.04.123_b0085","first-page":"219232","article-title":"A weight initialization method for improving training speed in feedforward neural network","volume":"30","author":"Yam","year":"2000","journal-title":"Neurocomput. Issues"},{"issue":"1","key":"10.1016\/j.amc.2015.04.123_b0090","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1016\/S0925-2312(96)00058-6","article-title":"A new method in determining initial weights of feedforward neural networks for training enhancement","volume":"16","author":"Yam","year":"1997","journal-title":"Neurocomputing"},{"key":"10.1016\/j.amc.2015.04.123_b0095","doi-asserted-by":"crossref","unstructured":"G. Thimm, E. Fiesler, Neural network initialization in from neural to artificial neural computation, in: J. Mira, F. Sandoval (Eds.), International Workshop on Artificial Neural Networks, pp. 535\u2013542, Malaga, 1995.","DOI":"10.1007\/3-540-59497-3_220"},{"key":"10.1016\/j.amc.2015.04.123_b0100","unstructured":"Y. Chen, F. Bastani, ANN with two-dendrite neurons and its weight initialization, in: International Joint Conference on Neural Networks (IJCNN), Baltimore, USA, vol. 3, pp. 139\u2013146, 1992."},{"key":"10.1016\/j.amc.2015.04.123_b0105","series-title":"Self-Organizing Maps","author":"Kohonen","year":"2001"},{"key":"10.1016\/j.amc.2015.04.123_b0110","series-title":"Spatial Tessellations Concepts and Applications of Voronoi Diagrams","author":"Okabe","year":"2000"},{"key":"10.1016\/j.amc.2015.04.123_b0115","article-title":"Principles of artificial neural networks","volume":"vol. 6","author":"Graupe","year":"2007"},{"issue":"2","key":"10.1016\/j.amc.2015.04.123_b0120","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/0098-1354(95)00259-6","article-title":"Counterpropagation neural networks for fault detection and diagnosis","volume":"21","author":"Vora","year":"1997","journal-title":"Comput. Chem. Eng."},{"issue":"1\u20133","key":"10.1016\/j.amc.2015.04.123_b0125","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/S0925-2312(98)00017-4","article-title":"Weight initialization with reference patterns","volume":"20","author":"Lehtokangas","year":"1998","journal-title":"Neurocomputing"},{"key":"10.1016\/j.amc.2015.04.123_b0130","doi-asserted-by":"crossref","first-page":"4979","DOI":"10.1364\/AO.26.004979","article-title":"Counterpropagation networks","volume":"26","author":"Nielsen","year":"1987","journal-title":"Appl. Opt."},{"key":"10.1016\/j.amc.2015.04.123_b0135","unstructured":"S.N. Sivanandam, S. Sumathi, S.N. Deepa, Introduction to neural networks using MATLAB 6.0, Tata McGraw-Hill Computer engineering Series, 2006."},{"issue":"5","key":"10.1016\/j.amc.2015.04.123_b0140","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.2003.816034","article-title":"A new wide range euclidean distance circuit for neural network hardware implementations","volume":"14","author":"Gopalan","year":"2003","journal-title":"IEEE Trans. Neural Netw."},{"issue":"8","key":"10.1016\/j.amc.2015.04.123_b0145","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.1109\/4.604088","article-title":"A low-power CMOS analog vector quantizer","volume":"32","author":"Cauwenberghs","year":"1997","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"2","key":"10.1016\/j.amc.2015.04.123_b0150","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/82.823544","article-title":"A modular current-mode classifier circuit for template matching application","volume":"47","author":"Liu","year":"2000","journal-title":"IEEE Trans. Circuits Syst. II: Analog Digital Signal Processing"},{"key":"10.1016\/j.amc.2015.04.123_b0155","first-page":"350","article-title":"A floating gate CMOS Euclidean distance calculator and its application to hand-written digit recognition","volume":"3","author":"Vlassis","year":"2001","journal-title":"Int. Conf. Image Processing"},{"issue":"3","key":"10.1016\/j.amc.2015.04.123_b0160","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/JSSC.1987.1052733","article-title":"A class of analog CMOS circuits based on the square-law characteristic of an MOS transistors in saturation","volume":"sc-22","author":"Bult","year":"1987","journal-title":"IEEE J. Solid-State Circuits"},{"key":"10.1016\/j.amc.2015.04.123_b0165","doi-asserted-by":"crossref","DOI":"10.4028\/www.scientific.net\/SSP.199.247","article-title":"Power, low chip area, digital distance calculation circuit for self-organizing neural networks realized in the CMOS technology","volume":"199","author":"D\u0142ugosz","year":"2013","journal-title":"Solid State Phenom."},{"key":"10.1016\/j.amc.2015.04.123_b0170","doi-asserted-by":"crossref","unstructured":"T. Tala\u015bka, R. D\u0142ugosz, Current mode Euclidean distance calculation circuit for Kohonens neural network implemented in CMOS 0.18\u03bcm technology, IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Vancouver, Canada, 2007.","DOI":"10.1109\/CCECE.2007.115"},{"key":"10.1016\/j.amc.2015.04.123_b0175","article-title":"Flexible architecture of ultra-low-power current-mode interleaved successive approximation analog-to-digital converter for wireless sensor networks","volume":"vol. 2007","author":"D\u0142ugosz","year":"2007","journal-title":"VLSI Design J., Hindavi Publishing"},{"key":"10.1016\/j.amc.2015.04.123_b0180","unstructured":"R. Dugosz, T. Tala\u015bka, P.A. Farine, W. Pedrycz, Convex combination initialization method for Kohonen neural network implemented in the CMOS technology, in: International Conference Mixed Design of Integrated Circuits and Systems (MIXDES), 2012, Warsaw, Poland."},{"issue":"11","key":"10.1016\/j.amc.2015.04.123_b0185","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/10.959322","article-title":"ECG beat recognition using fuzzy hybrid neural network","volume":"48","author":"Osowski","year":"2001","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.amc.2015.04.123_b0190","first-page":"1053","article-title":"Real-time discrimination of multiple cardiac arrhythmias for wearable systems based on neural networks","volume":"35","author":"Valenza","year":"2008","journal-title":"Comput. Cardiology"},{"issue":"7","key":"10.1016\/j.amc.2015.04.123_b0195","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1109\/10.846677","article-title":"Clustering ECG complexes using hermite functions and self-organizing maps","volume":"47","author":"Lagerholm","year":"2000","journal-title":"IEEE Trans. Biomed. Eng."}],"container-title":["Applied Mathematics and Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0096300315005949?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0096300315005949?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T19:19:09Z","timestamp":1620847149000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0096300315005949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9]]},"references-count":39,"alternative-id":["S0096300315005949"],"URL":"http:\/\/dx.doi.org\/10.1016\/j.amc.2015.04.123","relation":{},"ISSN":["0096-3003"],"issn-type":[{"value":"0096-3003","type":"print"}],"subject":[],"published":{"date-parts":[[2015,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An efficient initialization mechanism of neurons for Winner Takes All Neural Network implemented in the CMOS technology","name":"articletitle","label":"Article Title"},{"value":"Applied Mathematics and Computation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.amc.2015.04.123","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 2015 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}
