{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T05:04:21Z","timestamp":1779858261678,"version":"3.53.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00521-026-12042-x","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:32:02Z","timestamp":1775871122000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Probabilistic Neural Networks (PNNs) with t-distributed outputs: adaptive prediction intervals beyond Gaussian assumptions"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4078-1676","authenticated-orcid":false,"given":"Farhad","family":"Pourkamali-Anaraki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,11]]},"reference":[{"key":"12042_CR1","unstructured":"Wang Q, Ma Y, Zhao K, Tian Y (2020) A comprehensive survey of loss functions in machine learning. Ann Data Sci, 1\u201326"},{"key":"12042_CR2","doi-asserted-by":"crossref","unstructured":"Hu T, Wang J, Wang W, Li Z (2022) Understanding square loss in training overparametrized neural network classifiers. Adv Neural Inf Process Syst, 16495\u201316508","DOI":"10.52202\/068431-1200"},{"issue":"1","key":"12042_CR3","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/TNNLS.2021.3090358","volume":"34","author":"A Akbari","year":"2021","unstructured":"Akbari A, Awais M, Bashar M, Kittler J (2021) A theoretical insight into the effect of loss function for deep semantic-preserving learning. IEEE Trans Neural Netw Learn Syst 34(1):119\u2013133","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"12042_CR4","doi-asserted-by":"crossref","unstructured":"Jadon A, Patil A, Jadon S (2024) A comprehensive survey of regression-based loss functions for time series forecasting. In: International conference on data management, analytics & innovation, pp. 117\u2013147","DOI":"10.1007\/978-981-97-3245-6_9"},{"key":"12042_CR5","doi-asserted-by":"publisher","first-page":"15334","DOI":"10.1109\/ACCESS.2021.3052680","volume":"9","author":"F Pourkamali-Anaraki","year":"2021","unstructured":"Pourkamali-Anaraki F, Hariri-Ardebili M (2021) Neural networks and imbalanced learning for data-driven scientific computing with uncertainties. IEEE Access 9:15334\u201315350","journal-title":"IEEE Access"},{"key":"12042_CR6","doi-asserted-by":"publisher","first-page":"107115","DOI":"10.1016\/j.neunet.2024.107115","volume":"185","author":"J Fan","year":"2025","unstructured":"Fan J, Chen M, Gu Z, Yang J, Wu H, Wu J (2025) Ssim over MSE: a new perspective for video anomaly detection. Neural Netw 185:107115","journal-title":"Neural Netw"},{"key":"12042_CR7","volume-title":"Probabilistic machine learning: an introduction","author":"K Murphy","year":"2022","unstructured":"Murphy K (2022) Probabilistic machine learning: an introduction. MIT press"},{"key":"12042_CR8","doi-asserted-by":"publisher","first-page":"178816","DOI":"10.1109\/ACCESS.2024.3508735","volume":"12","author":"F Pourkamali-Anaraki","year":"2024","unstructured":"Pourkamali-Anaraki F, Husseini J, Stapleton S (2024) Probabilistic neural networks (PNNs) for modeling aleatoric uncertainty in scientific machine learning. IEEE Access 12:178816\u2013178831","journal-title":"IEEE Access"},{"issue":"12","key":"12042_CR9","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1002\/pol.20230649","volume":"62","author":"T Nasrin","year":"2024","unstructured":"Nasrin T, Pourkamali-Anaraki F, Peterson A (2024) Application of machine learning in polymer additive manufacturing: a review. J Polym Sci 62(12):2639\u20132669","journal-title":"J Polym Sci"},{"key":"12042_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106983","volume":"126","author":"F Pourkamali-Anaraki","year":"2023","unstructured":"Pourkamali-Anaraki F, Nasrin T, Jensen R, Peterson A, Hansen C (2023) Evaluation of classification models in limited data scenarios with application to additive manufacturing. Eng Appl Artif Intell 126:106983","journal-title":"Eng Appl Artif Intell"},{"key":"12042_CR11","doi-asserted-by":"crossref","unstructured":"Nix D, Weigend A (1994) Estimating the mean and variance of the target probability distribution. In: IEEE international conference on neural networks, pp. 55\u201360","DOI":"10.1109\/ICNN.1994.374138"},{"key":"12042_CR12","unstructured":"Seitzer M, Tavakoli A, Antic D, Martius G (2022) On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks. In: International conference on learning representations"},{"key":"12042_CR13","doi-asserted-by":"crossref","unstructured":"Immer A, Palumbo E, Marx A, Vogt J (2023) Effective bayesian heteroscedastic regression with deep neural networks. Adv Neural Inf Process Syst, 53996\u201354019","DOI":"10.52202\/075280-2349"},{"key":"12042_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127929","volume":"597","author":"L Sluijterman","year":"2024","unstructured":"Sluijterman L, Cator E, Heskes T (2024) Optimal training of mean variance estimation neural networks. Neurocomputing 597:127929","journal-title":"Neurocomputing"},{"key":"12042_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2024.110513","volume":"253","author":"L Basora","year":"2025","unstructured":"Basora L, Viens A, Chao M, Olive X (2025) A benchmark on uncertainty quantification for deep learning prognostics. Reliab Eng Syst Safety 253:110513","journal-title":"Reliab Eng Syst Safety"},{"key":"12042_CR16","doi-asserted-by":"crossref","unstructured":"Zhang W, Ma Z, Das S, Weng T, Megretski A, Daniel L, Nguyen L (2024) One step closer to unbiased aleatoric uncertainty estimation. In: Proceedings of the AAAI conference on artificial intelligence, pp. 16857\u201316864","DOI":"10.1609\/aaai.v38i15.29627"},{"key":"12042_CR17","unstructured":"Meinshausen N, Ridgeway G (2006) Quantile regression forests. J Mach Learn Res 7(6)"},{"key":"12042_CR18","unstructured":"Romano Y, Patterson E, Candes E (2019) Conformalized quantile regression. In: Advances in neural information processing systems"},{"key":"12042_CR19","unstructured":"Chung Y, Neiswanger W, Char I, Schneider J (2021) Beyond pinball loss: quantile methods for calibrated uncertainty quantification. Adv Neural Inf Process Syst , 10971\u201310984"},{"issue":"4","key":"12042_CR20","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1080\/02331888.2010.535904","volume":"46","author":"G Yanev","year":"2012","unstructured":"Yanev G, Ahsanullah M (2012) Characterizations of student\u2019s t-distribution via regressions of order statistics. Stat 46(4):429\u2013435","journal-title":"Stat"},{"key":"12042_CR21","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s00181-018-1570-0","volume":"58","author":"R Li","year":"2020","unstructured":"Li R, Nadarajah S (2020) A review of student\u2019s t distribution and its generalizations. Empir Econ 58:1461\u20131490","journal-title":"Empir Econ"},{"key":"12042_CR22","unstructured":"Min M, Maaten L, Yuan Z, Bonner A, Zhang Z (2010) Deep supervised t-distributed embedding. In: International conference on machine learning, pp. 791\u2013798"},{"key":"12042_CR23","unstructured":"Dotzel J, Chen Y, Kotb B, Prasad S, Wu G, Li S, Abdelfattah M, Zhang Z (2024) Learning from students: applying t-distributions to explore accurate and efficient formats for LLMs. In: International conference on machine learning, pp. 11573\u201311591"},{"key":"12042_CR24","unstructured":"Stirn A, Wessels H, Schertzer M, Pereira L, Sanjana N, Knowles D (2023) Faithful heteroscedastic regression with neural networks. In: International conference on artificial intelligence and statistics, pp. 5593\u20135613"},{"key":"12042_CR25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.patrec.2024.09.011","volume":"186","author":"S Lind","year":"2024","unstructured":"Lind S, Xiong Z, Forss\u00e9n P, Kr\u00fcger V (2024) Uncertainty quantification metrics for deep regression. Pattern Recogn Lett 186:91\u201397","journal-title":"Pattern Recogn Lett"},{"key":"12042_CR26","doi-asserted-by":"crossref","unstructured":"Bramlage L, Karg M, Curio C (2023) Plausible uncertainties for human pose regression. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 15133\u201315142","DOI":"10.1109\/ICCV51070.2023.01389"},{"issue":"1","key":"12042_CR27","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/s10462-022-10178-5","volume":"56","author":"N Dewolf","year":"2023","unstructured":"Dewolf N, Baets B, Waegeman W (2023) Valid prediction intervals for regression problems. Artif Intell Rev 56(1):577\u2013613","journal-title":"Artif Intell Rev"},{"issue":"1","key":"12042_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-023-01180-8","volume":"9","author":"A Tan","year":"2023","unstructured":"Tan A, Urata S, Goldman S, Dietschreit J, G\u00f3mez-Bombarelli R (2023) Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles. NPJ Comput Mater 9(1):225","journal-title":"NPJ Comput Mater"},{"issue":"5","key":"12042_CR29","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1007\/s10208-019-09427-x","volume":"19","author":"G Lugosi","year":"2019","unstructured":"Lugosi G, Mendelson S (2019) Mean estimation and regression under heavy-tailed distributions: a survey. Found Comput Math 19(5):1145\u20131190","journal-title":"Found Comput Math"},{"key":"12042_CR30","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1007\/s10994-020-05900-9","volume":"109","author":"R Ribeiro","year":"2020","unstructured":"Ribeiro R, Moniz N (2020) Imbalanced regression and extreme value prediction. Mach Learn 109:1803\u20131835","journal-title":"Mach Learn"},{"issue":"1","key":"12042_CR31","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-024-01473-6","volume":"11","author":"L Vazquez-Salazar","year":"2025","unstructured":"Vazquez-Salazar L, K\u00e4ser S, Meuwly M (2025) Outlier-detection for reactive machine learned potential energy surfaces. npj Comput Mater 11(1):33","journal-title":"npj Comput Mater"},{"issue":"3","key":"12042_CR32","doi-asserted-by":"publisher","first-page":"13840","DOI":"10.1111\/exsy.13840","volume":"42","author":"J Wibbeke","year":"2025","unstructured":"Wibbeke J, Rohjans S, Rauh A (2025) Quantification of data imbalance. Expert Syst 42(3):13840","journal-title":"Expert Syst"},{"key":"12042_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128091","volume":"601","author":"W Zhang","year":"2024","unstructured":"Zhang W, Shi P, Jia P, Zhou X (2024) A novel gradient boosting approach for imbalanced regression. Neurocomputing 601:128091","journal-title":"Neurocomputing"},{"issue":"1","key":"12042_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.3150\/10-BEJ267","volume":"17","author":"I Steinwart","year":"2011","unstructured":"Steinwart I, Christmann A (2011) Estimating conditional quantiles with the help of the pinball loss. Bernoulli 17(1):211\u2013225","journal-title":"Bernoulli"},{"issue":"Suppl 1","key":"12042_CR35","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1007\/s10462-023-10562-9","volume":"56","author":"J Gawlikowski","year":"2023","unstructured":"Gawlikowski J, Tassi C, Ali M, Lee J, Humt M, Feng J, Kruspe A, Triebel R, Jung P, Roscher R, Shahzad M, Yang W, Bamler R, Zhu X (2023) A survey of uncertainty in deep neural networks. Artif Intell Rev 56(Suppl 1):1513\u20131589","journal-title":"Artif Intell Rev"},{"key":"12042_CR36","doi-asserted-by":"crossref","unstructured":"He W, Jiang Z, Xiao T, Xu Z, Li Y (2025) A survey on uncertainty quantification methods for deep learning. ACM Comput Surv","DOI":"10.1145\/3786319"},{"key":"12042_CR37","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: International conference on machine learning, pp. 1050\u20131059"},{"key":"12042_CR38","doi-asserted-by":"crossref","unstructured":"Zheng H, Yang Z, Liu W, Liang J, Li Y (2015) Improving deep neural networks using softplus units. In: International joint conference on neural networks, pp. 1\u20134","DOI":"10.1109\/IJCNN.2015.7280459"},{"issue":"29","key":"12042_CR39","doi-asserted-by":"publisher","first-page":"18297","DOI":"10.1007\/s00521-024-10156-8","volume":"36","author":"F Pourkamali-Anaraki","year":"2024","unstructured":"Pourkamali-Anaraki F, Nasrin T, Jensen R, Peterson A, Hansen C (2024) Adaptive activation functions for predictive modeling with sparse experimental data. Neural Comput Appl 36(29):18297\u201318311","journal-title":"Neural Comput Appl"},{"issue":"3","key":"12042_CR40","doi-asserted-by":"publisher","first-page":"315","DOI":"10.2307\/2347257","volume":"25","author":"J Bernardo","year":"1976","unstructured":"Bernardo J (1976) Psi (digamma) function. Appl Stat 25(3):315\u2013317","journal-title":"Appl Stat"},{"key":"12042_CR41","unstructured":"Yin L, Zhang J (2025) On some properties of special functions involving $$k$$-gamma and $$k$$-digamma functions. arXiv:2502.15852"},{"key":"12042_CR42","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980"},{"key":"12042_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109436","volume":"138","author":"F Pourkamali-Anaraki","year":"2024","unstructured":"Pourkamali-Anaraki F, Husseini J, Pineda E, Bednarcyk B, Stapleton S (2024) Two-stage surrogate modeling for data-driven design optimization with application to composite microstructure generation. Eng Appl Artif Intell 138:109436","journal-title":"Eng Appl Artif Intell"},{"key":"12042_CR44","unstructured":"Picard D (2021) Torch. manual_seed (3407) is all you need: on the influence of random seeds in deep learning architectures for computer vision. arXiv:2109.08203"},{"key":"12042_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128130","volume":"599","author":"L Scabini","year":"2024","unstructured":"Scabini L, De Baets B, Bruno O (2024) Improving deep neural network random initialization through neuronal rewiring. Neurocomputing 599:128130","journal-title":"Neurocomputing"},{"key":"12042_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2024.135782","volume":"423","author":"M Hariri-Ardebili","year":"2024","unstructured":"Hariri-Ardebili M, Mahdavi P, Pourkamali-Anaraki F (2024) Benchmarking AutoML solutions for concrete strength prediction: reliability, uncertainty, and dilemma. Constr Build Mater 423:135782","journal-title":"Constr Build Mater"},{"key":"12042_CR47","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1016\/j.enbuild.2012.03.003","volume":"49","author":"A Tsanas","year":"2012","unstructured":"Tsanas A, Xifara A (2012) Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools. Energy Build 49:560\u2013567","journal-title":"Energy Build"},{"key":"12042_CR48","unstructured":"Rastiti R (2024) Students performance index using regression model. https:\/\/rpubs.com\/Rastiti_R\/1156989. Accessed: March 13, 2025"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12042-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-026-12042-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12042-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T04:45:08Z","timestamp":1779857108000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-026-12042-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":48,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["12042"],"URL":"https:\/\/doi.org\/10.1007\/s00521-026-12042-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"16 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no conflicts of interest or competing interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"Upon acceptance of this work, we will provide the PyTorch implementation of the proposed method on GitHub under a permissive license.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"259"}}