{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T14:21:57Z","timestamp":1790518917449,"version":"4.1.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319950976","type":"print"},{"value":"9783319950983","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,7,22]],"date-time":"2018-07-22T00:00:00Z","timestamp":1532217600000},"content-version":"unspecified","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\/978-3-319-95098-3_7","type":"book-chapter","created":{"date-parts":[[2018,7,21]],"date-time":"2018-07-21T10:22:26Z","timestamp":1532168546000},"page":"73-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Learning Activation Functions from Data Using Cubic Spline Interpolation"],"prefix":"10.1007","author":[{"given":"Simone","family":"Scardapane","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Scarpiniti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danilo","family":"Comminiello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelio","family":"Uncini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,7,22]]},"reference":[{"key":"7_CR1","unstructured":"Agostinelli, F., Hoffman, M., Sadowski, P., Baldi, P.: Learning activation functions to improve deep neural networks (2014). arXiv preprint arXiv:1412.6830"},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.neucom.2004.04.001","volume":"61","author":"P Chandra","year":"2004","unstructured":"Chandra, P., Singh, Y.: An activation function adapting training algorithm for sigmoidal feedforward networks. Neurocomputing 61, 429\u2013437 (2004)","journal-title":"Neurocomputing"},{"issue":"4","key":"7_CR3","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1016\/0893-6080(96)00006-8","volume":"9","author":"CT Chen","year":"1996","unstructured":"Chen, C.T., Chang, W.D.: A feedforward neural network with function shape autotuning. Neural Netw. 9(4), 627\u2013641 (1996)","journal-title":"Neural Netw."},{"key":"7_CR4","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"issue":"8","key":"7_CR5","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/S0893-6080(03)00139-4","volume":"16","author":"S Goh","year":"2003","unstructured":"Goh, S., Mandic, D.: Recurrent neural networks with trainable amplitude of activation functions. Neural Netw. 16(8), 1095\u20131100 (2003)","journal-title":"Neural Netw."},{"issue":"3","key":"7_CR6","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1109\/72.761726","volume":"10","author":"S Guarnieri","year":"1999","unstructured":"Guarnieri, S., Piazza, F., Uncini, A.: Multilayer feedforward networks with adaptive spline activation function. IEEE Trans. Neural Netw. 10(3), 672\u2013683 (1999)","journal-title":"IEEE Trans. Neural Netw."},{"key":"7_CR7","unstructured":"Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Pearson Education (2009)"},{"key":"7_CR8","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. In: 3rd International Conference for Learning Representations (2015). arXiv preprint arXiv:1412.6980"},{"key":"7_CR9","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in Network (2013). arXiv preprint arXiv:1312.4400"},{"issue":"4","key":"7_CR10","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1109\/TNN.2005.851786","volume":"16","author":"L Ma","year":"2005","unstructured":"Ma, L., Khorasani, K.: Constructive feedforward neural networks using hermite polynomial activation functions. IEEE Trans. Neural Netw. 16(4), 821\u2013833 (2005)","journal-title":"IEEE Trans. Neural Netw."},{"key":"7_CR11","unstructured":"Piazza, F., Uncini, A., Zenobi, M.: Artificial neural networks with adaptive polynomial activation function. In: International Joint Conference on Neural Networks, vol.\u00a02, pp. II\u2013343. IEEE\/INNS (1992)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.: Gaussian Processes for Machine Learning. MIT Press (2006)","DOI":"10.7551\/mitpress\/3206.001.0001"},{"issue":"4","key":"7_CR13","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1016\/j.sigpro.2012.09.021","volume":"93","author":"M Scarpiniti","year":"2013","unstructured":"Scarpiniti, M., Comminiello, D., Parisi, R., Uncini, A.: Nonlinear spline adaptive filtering. Signal Process. 93(4), 772\u2013783 (2013)","journal-title":"Signal Process."},{"issue":"4","key":"7_CR14","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TSP.2015.2493986","volume":"64","author":"M Scarpiniti","year":"2016","unstructured":"Scarpiniti, M., Comminiello, D., Scarano, G., Parisi, R., Uncini, A.: Steady-state performance of spline adaptive filters. IEEE Trans. Signal Process. 64(4), 816\u2013828 (2016)","journal-title":"IEEE Trans. Signal Process."},{"key":"7_CR15","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"issue":"4","key":"7_CR16","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1016\/S0893-6080(01)00028-4","volume":"14","author":"E Trentin","year":"2001","unstructured":"Trentin, E.: Networks with trainable amplitude of activation functions. Neural Netw. 14(4), 471\u2013493 (2001)","journal-title":"Neural Netw."},{"issue":"2","key":"7_CR17","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/S0893-6080(97)00118-4","volume":"11","author":"L Vecci","year":"1998","unstructured":"Vecci, L., Piazza, F., Uncini, A.: Learning and approximation capabilities of adaptive spline activation function neural networks. Neural Netw. 11(2), 259\u2013270 (1998)","journal-title":"Neural Netw."},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Wahba, G.: Spline Models for Observational Data. SIAM (1990)","DOI":"10.1137\/1.9781611970128"},{"issue":"1","key":"7_CR19","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/72.977302","volume":"13","author":"M Zhang","year":"2002","unstructured":"Zhang, M., Xu, S., Fulcher, J.: Neuron-adaptive higher order neural-network models for automated financial data modeling. IEEE Trans. Neural Netw. 13(1), 188\u2013204 (2002)","journal-title":"IEEE Trans. Neural Netw."}],"container-title":["Smart Innovation, Systems and Technologies","Neural Advances in Processing Nonlinear Dynamic Signals"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-95098-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T04:06:14Z","timestamp":1571630774000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-95098-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,22]]},"ISBN":["9783319950976","9783319950983"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-95098-3_7","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"value":"2190-3018","type":"print"},{"value":"2190-3026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,22]]}}}