{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T22:37:12Z","timestamp":1778193432131,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031789762","type":"print"},{"value":"9783031789779","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78977-9_18","type":"book-chapter","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T10:13:23Z","timestamp":1737972803000},"page":"275-291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["SwitchPath: Enhancing Exploration in\u00a0Neural Networks Learning Dynamics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9070-4663","authenticated-orcid":false,"given":"Antonio","family":"Di Cecco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8024-2768","authenticated-orcid":false,"given":"Andrea","family":"Papini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9325-8232","authenticated-orcid":false,"given":"Carlo","family":"Metta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0708-5495","authenticated-orcid":false,"given":"Marco","family":"Fantozzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2770-0344","authenticated-orcid":false,"given":"Silvia Giulia","family":"Galfr\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2022-2300","authenticated-orcid":false,"given":"Francesco","family":"Morandin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4905-3544","authenticated-orcid":false,"given":"Maurizio","family":"Parton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"18_CR1","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML, pp. 214\u2013223 (2017)"},{"key":"18_CR2","first-page":"1","volume":"23","author":"B Avelin","year":"2022","unstructured":"Avelin, B.: Deep limits and a cut-off phenomenon for neural networks. J. Mach. Learn. Res. 23, 1\u201329 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR3","unstructured":"Aytekin, C.: Neural networks are decision trees. CoRR abs\/1308.3432 (2022)"},{"key":"18_CR4","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.C.: Estimating or propagating gradients through stochastic neurons for conditional computation abs\/1308.3432 (2013)"},{"issue":"12","key":"18_CR5","first-page":"656","volume":"17","author":"GD Birkhoff","year":"1931","unstructured":"Birkhoff, G.D.: Proof of the ergodic theorem. MAS 17(12), 656\u2013660 (1931)","journal-title":"MAS"},{"key":"18_CR6","volume-title":"Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach","author":"KP Burnham","year":"2002","unstructured":"Burnham, K.P., Anderson, D.R.: Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach. Springer, New York (2002)"},{"key":"18_CR7","unstructured":"Dann, C., Mansour, Y., Mohri, M., Sekhari, A., Sridharan, K.: Guarantees for epsilon-greedy reinforcement learning with function approximation. In: ICML, pp. 1245\u20131254 (2022)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Di\u00a0Cecco, A., Metta, C., Fantozzi, M., Morandin, F., Parton, M.: Glonets: globally connected neural networks. In: IDA. LNCS, vol. 14641, pp. 53\u201364. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-58547-0_5"},{"key":"18_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"issue":"1","key":"18_CR10","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1038\/s41467-022-30305-8","volume":"13","author":"S Dutta","year":"2022","unstructured":"Dutta, S., Detorakis, G., Khanna, A., Grisafe, B., Neftci, E., Datta, S.: Neural sampling machine with stochastic synapse allows brain-like learning and inference. Nat. Commun. 13(1), 1899 (2022)","journal-title":"Nat. Commun."},{"key":"18_CR11","unstructured":"Frosst, N., Hinton, G.: Distilling a neural network into a soft decision tree. In: International Workshop on Comprehensibility and Explanation in AI and ML (2017)"},{"key":"18_CR12","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML, vol.\u00a048, pp. 1050\u20131059 (2016)"},{"key":"18_CR13","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: AISTATS, pp. 315\u2013323. JMLR Workshop and Conference Proceedings (2011)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. ACM 63(11) (2020)","DOI":"10.1145\/3422622"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Gregnanin, M., De\u00a0Smedt, J., Gnecco, G., Parton, M.: Signature-based community detection for time series. In: COMPLEX NETWORKS 2023. Studies in Computational Intelligence, vol.\u00a01142, pp. 146\u2013158 (2023)","DOI":"10.1007\/978-3-031-53499-7_12"},{"key":"18_CR16","unstructured":"Gulcehre, C., Moczulski, M., Denil, M., Bengio, Y.: Noisy activation functions. In: ICML, pp. 3059\u20133068. JMLR.org (2016)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"18_CR18","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":"18_CR19","unstructured":"Hinton, G.: Neural networks for machine learning (2012). https:\/\/www.coursera.org\/learn\/neural-networks. Lecture series, Coursera"},{"key":"18_CR20","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors (2012)"},{"key":"18_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"18_CR22","unstructured":"Kandel, E.R., et al.: Principles of Neural Science, vol.\u00a04. McGraw-Hill, New York (2000)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Kauffman, S.A.: Investigations. OUP (2000)","DOI":"10.1093\/oso\/9780195121049.001.0001"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Khalid, M., Baber, J., Kasi, M.K., Bakhtyar, M., Devi, V., Sheikh, N.: Empirical evaluation of activation functions in deep convolution neural network for facial expression recognition. In: TSP, pp. 204\u2013207 (2020)","DOI":"10.1109\/TSP49548.2020.9163446"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Krengel, U.: Ergodic theorems, vol.\u00a06. Walter de Gruyter Pub. (1985)","DOI":"10.1515\/9783110844641"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Metta, C., et al.: Increasing biases can be more efficient than increasing weights. In: IEEE\/CVF, Winter Conference on Applications of Computer Vision WACV, pp. 2798\u20132807 (2024)","DOI":"10.1109\/WACV57701.2024.00279"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Metta, C., et al.: Increasing biases can be more efficient than increasing weights. In: IEEE\/CVF, pp. 2798\u20132807 (2024)","DOI":"10.1109\/WACV57701.2024.00279"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518 (2015)","DOI":"10.1038\/nature14236"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Morandin, F., Amato, G., Fantozzi, M., Gini, R., Metta, C., Parton, M.: SAI: a sensible artificial intelligence that plays with handicap and targets high scores in 9$$\\times $$9 go. In: ECAI 2020, vol.\u00a0325, pp. 403\u2013410 (2020). https:\/\/doi.org\/10.3233\/FAIA200119","DOI":"10.3233\/FAIA200119"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Morandin, F., Amato, G., Gini, R., Metta, C., Parton, M., Pascutto, G.: SAI: a sensible artificial intelligence that plays go. In: IJCNN, pp.\u00a01\u20138 (2019)","DOI":"10.1109\/IJCNN.2019.8852266"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Parton, M., Fois, A., Vegli\u00f2, M., Metta, C., Gregnanin, M.: Predicting the failure of component X in the scania dataset with graph neural networks. In: IDA 2024. LNCS, vol. 14642, pp. 251\u2013259 (2024)","DOI":"10.1007\/978-3-031-58553-1_20"},{"issue":"11","key":"18_CR32","doi-asserted-by":"publisher","first-page":"307","DOI":"10.3390\/a13110307","volume":"13","author":"L Pasqualini","year":"2020","unstructured":"Pasqualini, L., Parton, M.: Pseudo random number generation through reinforcement learning and recurrent neural networks. Algorithms 13(11), 307 (2020)","journal-title":"Algorithms"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Pasqualini, L., et al.: Score vs. winrate in score-based games: which reward for reinforcement learning? In: ICMLA, pp. 573\u2013578 (2022)","DOI":"10.1109\/ICMLA55696.2022.00099"},{"key":"18_CR34","unstructured":"Ramachandran, P., Zoph, B., Le, Q.: Searching for activation functions. In: ICLR (2018)"},{"key":"18_CR35","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIps, pp. 2234\u20132242 (2016)"},{"issue":"7587","key":"18_CR36","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"issue":"56","key":"18_CR37","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR38","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT (2018)"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Tokic, M.: Adaptive $$\\varepsilon $$-greedy exploration in reinforcement learning based on value differences. In: AAAI, pp. 203\u2013210. Springer (2010)","DOI":"10.1007\/978-3-642-16111-7_23"},{"key":"18_CR40","unstructured":"Wan, L., Zeiler, M.D., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: ICML, pp. 1058\u20131066 (2013)"},{"key":"18_CR41","unstructured":"Wu, D.J.: Accelerating Self-Play Learning in Go. AAAI20-RLG workshop (2020). https:\/\/arxiv.org\/abs\/1902.10565"},{"key":"18_CR42","unstructured":"Zhang, F.: Deep neural networks from the perspective of ergodic theory. arXiv preprint arXiv:2308.03888 (2023)"},{"key":"18_CR43","unstructured":"Zhang, J., Li, H., Sra, S., Jadbabaie, A.: Neural network weights do not converge to stationary points: an invariant measure perspective. In: ICML (2021)"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"\u0130rsoy, O., Y\u0131ld\u0131z, O., Alpayd\u0131n, E.: Soft decision trees. In: ICPR (2012)","DOI":"10.1007\/978-3-319-01604-7_2"}],"container-title":["Lecture Notes in Computer Science","Discovery Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78977-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T10:13:43Z","timestamp":1737972823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78977-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031789762","9783031789779"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78977-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Discovery Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pisa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ds2024.isti.cnr.it\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}