{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:18:43Z","timestamp":1742937523214,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030114787"},{"type":"electronic","value":"9783030114794"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11479-4_16","type":"book-chapter","created":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T19:03:33Z","timestamp":1551121413000},"page":"345-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reducing Hierarchical Deep Learning Networks as Game Playing Artefact Using Regret Matching"],"prefix":"10.1007","author":[{"given":"Arindam","family":"Chaudhuri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumya K.","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,26]]},"reference":[{"key":"16_CR1","first-page":"111","volume-title":"Advances in Intelligent Systems and Computing","author":"Arindam Chaudhuri","year":"2018","unstructured":"A. Chaudhuri, S.K. Ghosh, Hierarchical fuzzy deep learning networks for predicting human behavior in strategic setups, in Advances in Intelligent Systems and Computing, ed. by R. Silhavy, et al., vol. 764 (Springer, Switzerland, 2019), pp. 111\u2013121"},{"issue":"1\u20132","key":"16_CR2","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1006\/game.1999.0738","volume":"29","author":"Y Freund","year":"1999","unstructured":"Y. Freund, R. Schapire, Adaptive game playing using multiplicative weights. Games Econ. Behav. 29(1\u20132), 79\u2013103 (1999)","journal-title":"Games Econ. Behav."},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"S. Shalev-Shwartz, Y. Singer, Convex repeated games and Fenchel duality, in Advances in Neural Information Processing Systems, vol. 19 (2006)","DOI":"10.7551\/mitpress\/7503.003.0163"},{"issue":"2\u20133","key":"16_CR4","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s10994-007-5014-x","volume":"69","author":"S Shalev-Shwartz","year":"2007","unstructured":"S. Shalev-Shwartz, Y. Singer, A primal-dual perspective of online learning algorithms. Mach. Learn. 69(2\u20133), 115\u2013142 (2007)","journal-title":"Mach. Learn."},{"key":"16_CR5","unstructured":"O. Tammelin, N. Burch, M. Johanson, M. Bowling, Solving heads-up limit Texas hold\u2019em, in Proceedings of International Joint Conference on Artificial Intelligence, vol. 645\u2013652 (2015)"},{"key":"16_CR6","unstructured":"T.M. Mitchell, Machine Learning (McGraw Hill, 2008)"},{"issue":"5","key":"16_CR7","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1111\/1468-0262.00153","volume":"68","author":"S Hart","year":"2000","unstructured":"S. Hart, A. Mas-Colell, A simple adaptive procedure leading to correlated equilibrium. Econometrica 68(5), 1127\u20131150 (2000)","journal-title":"Econometrica"},{"issue":"9","key":"16_CR8","doi-asserted-by":"publisher","first-page":"2050","DOI":"10.1109\/TIT.2004.833339","volume":"50","author":"N Cesa-Bianchi","year":"2004","unstructured":"N. Cesa-Bianchi, A. Conconi, C. Gentile, On the generalization ability of on-line learning algorithms. IEEE Trans. Inf. Theory 50(9), 2050\u20132057 (2004)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"16_CR9","unstructured":"N. Ratliff, D. Bagnell, M. Zinkevich, Sub-gradient methods for structured prediction, in Proceedings of 11th International Conference on Artificial Intelligence and Statistics, vol. 2, pp. 380\u2013387 (2007)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"N. Ratliff, J.A. Bagnell, M. Zinkevich, Maximum margin planning, in Proceedings of 22nd International Conference on Machine Learning, pp. 729\u2013736 (2006)","DOI":"10.1145\/1143844.1143936"},{"issue":"1","key":"16_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10107-010-0420-4","volume":"127","author":"S Shalev-Shwartz","year":"2011","unstructured":"S. Shalev-Shwartz, Y. Singer, N. Srebro, A. Cotter, Pegasos: primal estimated sub-gradient solver for SVM. Math. Program. 127(1), 3\u201330 (2011)","journal-title":"Math. Program."},{"key":"16_CR12","unstructured":"M. Zinkevich, Online convex programming and generalized infinitesimal gradient ascent, in Proceedings of 20th International Conference on Machine Learning, pp. 928\u2013935 (2003)"},{"key":"16_CR13","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1126\/science.1127207","volume":"313","author":"M Kearns","year":"2006","unstructured":"M. Kearns, S. Suri, N. Montfort, An experimental study of the coloring problem on human subject networks. Science 313, 824\u2013827 (2006)","journal-title":"Science"},{"key":"16_CR14","unstructured":"M. Zinkevich, M. Bowling, M. Johanson, C. Piccione, Regret minimization in games with incomplete information, in Advances in Neural Information Processing Systems, vol. 20 (2007)"},{"key":"16_CR15","unstructured":"D. Balduzzi, Cortical prediction markets, in Proceedings of International Conference on Autonomous Agents and Multi-agent Systems, pp. 1265\u20131272 (2014)"},{"key":"16_CR16","unstructured":"D. Balduzzi, Deep online convex optimization using gated games (2016). http:\/\/arxiv.org\/abs\/1604.01952"},{"issue":"2","key":"16_CR17","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1006\/jcss.1995.1011","volume":"52","author":"K Hoeffgen","year":"1995","unstructured":"K. Hoeffgen, H. Simon, K. Van Horn, Robust trainability of single neurons. J. Comput. Syst. Sci. 52(2), 114\u2013125 (1995)","journal-title":"J. Comput. Syst. Sci."},{"key":"16_CR18","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/978-3-642-10291-2_48","volume-title":"AI*IA 2009: Emergent Perspectives in Artificial Intelligence","author":"Rustam Tagiew","year":"2009","unstructured":"R. Tagiew, Hypotheses about typical general human strategic behavior in a concrete case, in Emergent Perspectives in Artificial Intelligence. AI*IA, ed. by R. Serra, R. Cucchiara, LNCS, vol. 5883 (Springer, Heidelberg, 2009), pp. 476\u2013485"},{"key":"16_CR19","unstructured":"Y. Gal, A. Pfeffer, Modeling reciprocal behavior in human bilateral negotiation, in Proceedings of the 22nd National Conference on Artificial Intelligence, vol. 1, pp. 815\u2013820 (2007)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"M. Zinkevich, M. Littman, The AAAI computer poker competition. J. Int. Comput. Games Assoc. 29 (2006)","DOI":"10.3233\/ICG-2006-29314"},{"issue":"11","key":"16_CR21","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"N. Cesa-Bianchi, G. Lugosi, Prediction, Learning and Games (Cambridge University Press, 2006)","DOI":"10.1017\/CBO9780511546921"},{"key":"16_CR23","unstructured":"A. Rakhlin, K. Sridharan, Optimization, learning, and games with predictable sequences, in Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"16_CR24","unstructured":"V. Syrgkanis, A. Agarwal, H. Luo, R. Schapire, Fast convergence of regularized learning in games, in Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"2","key":"16_CR25","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1006\/inco.1994.1009","volume":"108","author":"N Littlestone","year":"1994","unstructured":"N. Littlestone, M. Warmuth, The weighted majority algorithm. Inf. Comput. 108(2), 212\u2013261 (1994)","journal-title":"Inf. Comput."},{"key":"16_CR26","unstructured":"N. Srinivasan, V. Ravichandran, K. Chan, J. Vidhya, S. Ramakrishnan, S. Krishnan, Exponentiated backpropagation algorithm for multilayer feedforward neural networks, in Proceedings of International Conference on Neural Information Processing, vol. 1 (2002)"},{"key":"16_CR27","unstructured":"G. Gordon, No-regret algorithms for structured prediction problems. Technical Report CMU-CALD-05112, Carnegie Mellon University (2005)"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"G. Gordon, No-regret algorithms for online convex programs, in Advances in Neural Information Processing Systems, vol. 19 (2006)","DOI":"10.7551\/mitpress\/7503.003.0066"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"J. Duchi, S. Shalev-Shwartz, Y. Singer, T. Chandra, Efficient projections onto the l1-ball for learning in high dimensions, in Proceedings of International Conference on Machine Learning, pp. 272\u2013279 (2008)","DOI":"10.1145\/1390156.1390191"},{"issue":"2","key":"16_CR30","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1561\/2200000018","volume":"4","author":"S Shalev-Shwartz","year":"2012","unstructured":"S. Shalev-Shwartz, Online learning and online convex optimization. Found. Trends Mach. Learn. 4(2), 107\u2013194 (2012)","journal-title":"Found. Trends Mach. Learn."},{"key":"16_CR31","unstructured":"D. Schuurmans, M. Zinkevich, Deep learning games, in Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"16_CR32","unstructured":"W. Karush, Minima of functions of several variables with inequalities as side constraints. Master\u2019s Thesis, University of Chicago, Chicago, Illinois (1939)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"H. Kuhn, A. Tucker, Nonlinear programming, in Proceedings of 2nd Berkeley Symposium, University of California Press, pp. 481\u2013492 (1951)","DOI":"10.1525\/9780520411586-036"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"M. Johanson, N. Bard, N. Burch, M. Bowling, Finding optimal abstract strategies in extensive form games, in Proceedings of AAAI Conference on Artificial Intelligence, pp. 1371\u20131379 (2012)","DOI":"10.1609\/aaai.v26i1.8269"},{"key":"16_CR35","unstructured":"J. Lee, M. Simchowitz, M. Jordan, B. Recht, Gradient descent only converges to minimizers, in Proceedings of 29th Annual Conference on Learning Theory, vol. 49, pp. 1246\u20131257 (2016)"},{"key":"16_CR36","first-page":"421","volume-title":"Lecture Notes in Computer Science","author":"L\u00e9on Bottou","year":"2012","unstructured":"L. Bottou, Stochastic gradient descent tricks, Neural Networks: Tricks of the Trade, 2nd edn, pp. 421\u2013436 (2012)"},{"key":"16_CR37","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"J. Duchi, E. Hazan, Y. Singer, Adaptive sub-gradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR38","unstructured":"D. Kingma, J.B. Adam, A method for stochastic optimization (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"16_CR39","unstructured":"I. Sutskever, J. Martens, G. Dahl, G. Hinton, On the importance of initialization and momentum in deep learning, in Proceedings of 29th International Conference on Machine Learning, pp. 1139\u20131147 (2013)"},{"key":"16_CR40","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/3-540-55706-7_4","volume-title":"Algorithm Theory \u2014 SWAT '92","author":"Alexander A. Razborov","year":"1992","unstructured":"A. Razborov, On small depth threshold circuits, in Proceedings of Scandinavian Workshop on Algorithm Theory, pp. 42\u201352 (1992)"},{"issue":"2","key":"16_CR41","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/0022-0000(93)90001-D","volume":"46","author":"A Hajnal","year":"1993","unstructured":"A. Hajnal, Threshold circuits of bounded depth. J. Comput. Syst. Sci. 46(2), 129\u2013154 (1993)","journal-title":"J. Comput. Syst. Sci."}],"container-title":["Smart Innovation, Systems and Technologies","Handbook of Deep Learning Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11479-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T03:18:31Z","timestamp":1721013511000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-11479-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030114787","9783030114794"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11479-4_16","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"26 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}