{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:17:34Z","timestamp":1742912254904,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863791"},{"type":"electronic","value":"9783030863807"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86380-7_21","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T12:03:14Z","timestamp":1631275394000},"page":"253-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Channel Capacity of Neural Networks"],"prefix":"10.1007","author":[{"given":"Gen","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"21_CR1","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016)"},{"issue":"9","key":"21_CR2","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1109\/TPAMI.2019.2909031","volume":"42","author":"RA Amjad","year":"2019","unstructured":"Amjad, R.A., Geiger, B.C.: Learning representations for neural network-based classification using the information bottleneck principle. IEEE Trans. Pattern Anal. Mach. Intell. 42(9), 2225\u20132239 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR3","unstructured":"Belghazi, M.I., et al.: Mutual information neural estimation. In: International Conference on Machine Learning, pp. 531\u2013540. PMLR (2018)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Boulanger-Lewandowski, N., Pascanu, R.: Advances in optimizing recurrent networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8624\u20138628. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"21_CR5","unstructured":"Cover, T.M.: Elements of Information Theory. John Wiley & Sons (1999)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"El Gamal, A., Kim, Y.H.: Network Information Theory. Cambridge University Press (2011)","DOI":"10.1017\/CBO9781139030687"},{"key":"21_CR7","unstructured":"Foggo, B., Yu, N.: On the maximum mutual information capacity of neural architectures. arXiv preprint arXiv:2006.06037 (2020)"},{"key":"21_CR8","unstructured":"Gao, S., Ver Steeg, G., Galstyan, A.: Efficient estimation of mutual information for strongly dependent variables. In: Artificial Intelligence and Statistics, pp. 277\u2013286. PMLR (2015)"},{"key":"21_CR9","unstructured":"Hafez-Kolahi, H., Kasaei, S.: Information bottleneck and its applications in deep learning. arXiv preprint arXiv:1904.03743 (2019)"},{"key":"21_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"21_CR11","unstructured":"Henaff, O.: Data-efficient image recognition with contrastive predictive coding. In: International Conference on Machine Learning, pp. 4182\u20134192. PMLR (2020)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., van Camp, D.: Keeping the neural networks simple by minimizing the description length of the weights. In: Proceedings of the Sixth Annual Conference on Computational Learning Theory, pp. 5\u201313 (1993)","DOI":"10.1145\/168304.168306"},{"key":"21_CR13","unstructured":"Ishida, T., Yamane, I., Sakai, T., Niu, G., Sugiyama, M.: Do we need zero training loss after achieving zero training error? arXiv preprint arXiv:2002.08709 (2020)"},{"key":"21_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"issue":"12","key":"21_CR15","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.3390\/e21121181","volume":"21","author":"A Kolchinsky","year":"2019","unstructured":"Kolchinsky, A., Tracey, B.D., Wolpert, D.H.: Nonlinear information bottleneck. Entropy 21(12), 1181 (2019)","journal-title":"Entropy"},{"key":"21_CR16","unstructured":"Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: Advances in Neural Information Processing Systems, pp. 950\u2013957 (1992)"},{"issue":"4","key":"21_CR17","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"issue":"3","key":"21_CR18","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/2.36","volume":"21","author":"R Linsker","year":"1988","unstructured":"Linsker, R.: Self-organization in a perceptual network. Computer 21(3), 105\u2013117 (1988)","journal-title":"Computer"},{"key":"21_CR19","unstructured":"MacKay, D.J.: Information Theory, Inference and Learning Algorithms. Cambridge University Press (2003)"},{"key":"21_CR20","unstructured":"Pereyra, G., Tucker, G., Chorowski, J., Kaiser, \u0141., Hinton, G.: Regularizing neural networks by penalizing confident output distributions. In: International Conference on Learning Representations Workshop (2017)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Saxe, A.M., et al.: On the information bottleneck theory of deep learning. J. Statist. Mech. Theor. Exp. 2019(12), 124020 (2019)","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"21_CR22","unstructured":"Shwartz-Ziv, R., Tishby, N.: Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810 (2017)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. arXiv preprint arXiv:1906.05849 (2019)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"21_CR25","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. In: Proceedings of the 37-th Annual Allerton Conference on Communication, Control and Computing, pp. 368\u2013377 (1999)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: 2015 IEEE Information Theory Workshop (ITW), pp. 1\u20135. IEEE (2015)","DOI":"10.1109\/ITW.2015.7133169"},{"key":"21_CR27","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., Lucic, M.: On mutual information maximization for representation learning. In: International Conference on Learning Representations (2020)"},{"key":"21_CR28","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/978-3-642-02962-2_49","volume-title":"Rough Sets and Knowledge Technology","author":"J Walters-Williams","year":"2009","unstructured":"Walters-Williams, J., Li, Y.: Estimation of mutual information: a survey. In: Wen, P., Li, Y., Polkowski, L., Yao, Y., Tsumoto, S., Wang, G. (eds.) RSKT 2009. LNCS (LNAI), vol. 5589, pp. 389\u2013396. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-02962-2_49"},{"key":"21_CR29","unstructured":"Yoshida, Y., Miyato, T.: Spectral norm regularization for improving the generalizability of deep learning. arXiv preprint arXiv:1705.10941 (2017)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86380-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,12]],"date-time":"2022-02-12T14:05:41Z","timestamp":1644674741000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86380-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863791","9783030863807"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86380-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"265","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"53% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}