Probabilistic machine learning and artificial intelligence
The DOI matches its Crossref record; 104 of the 108 references it cites were found in a registry or an index.
Abstract
How can a machine learn from experience? Probabilistic modelling provides a framework for understanding what learning is, and has therefore emerged as one of the principal theoretical and practical approaches for designing machines that learn from data acquired through experience. The probabilistic framework, which describes how to represent and manipulate uncertainty about models and predictions, has a central role in scientific data analysis, machine learning, robotics, cognitive science and artificial intelligence. This Review provides an introduction to this framework, and discusses some of the state-of-the-art advances in the field, namely, probabilistic programming, Bayesian optimization, data compression and automatic model discovery.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deriving from the Bayesian framework, GPR models have been widely applied to prognostic analysis as they are flexible, nonparametric and probabilistic [139].”
From Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review (2019) · cites this paper as [139]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“To ameliorate this in GPR, one way is to minimize the negative log marginal likelihood [139].”
From Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review (2019) · cites this paper as [139]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The performance of GPR is highly sensitive on the covariance function and the kernels should therefore be carefully selected to achieve high prediction accuracy [139].”
From Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review (2019) · cites this paper as [139]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“These methods can be broadly classified into two categories: Bayesian approaches [40,90,106] and Frequentist, approaches [14,70,113]”
From Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty (2021) · cites this paper as [40]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“recent advances using deep neural networks to solve challenging pattern recognition problems such as speech recognition [5], image classification [6, 7], and prediction of words in text [8], do not overtly represent the uncertainty in the structure or parameters of those neural networks.”
BackgroundA Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb00917.x · Cited by 48,949
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 1×
“The HMM is a widely used probabilistic model for sequential and time-series data, which assumes the data were obtained by transitioning stochastically between a discrete number of hidden states 98 .”
MethodBook Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Artificial intelligence: a modern approach
(1995) · Choice Reviews Online · doi:10.5860/choice.33-1577 · Cited by 21,974
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“The model could have a large number of parameters compared with the data set (for example, the neural network recently used to achieve translations of English and French sentences that approached the accuracy of state-of-the-art methods is a probabilistic model with 384 million parameters 29 ).”
MethodGaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
Artificial intelligence: A modern approach
Nilsson, N. J. (1996) · Artificial Intelligence · doi:10.1016/0004-3702(96)00007-0 · Cited by 10,583
Research works printed but not linked: 14
- [8] Bengio, Y., Ducharme, R., Vincent, P. & Janvin, C. A neural probabilistic language model. The Journal of Machine Learning Research 3 , 1137-1155 (2003). -
- Hinton, G. E., McClelland, J. L. & Rumelhart, D. E. in Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations 77–109 (MIT Press, 1986).
- Goodman, N. D. & Stuhlmüller, A. The Design and Implementation of Probabilistic Programming Languages. Available at http://dippl.org (2015).
- Mansinghka, V., Kulkarni, T. D., Perov, Y. N. & Tenenbaum, J. Approximate Bayesian image interpretation using generative probabilistic graphics programs. In Proc. Advances in Neural Information Processing Systems 26 1520–1528 (2013).
- Minka, T. P., Winn, J. M., Guiver, J. P. & Knowles, D. A. Infer.NET 2.4. http://research.microsoft.com/infernet (Microsoft Research, 2010).
- Pfeffer, A. Figaro: An Object-Oriented Probabilistic Programming Language. Tech. Rep. (Charles River Analytics, 2009).
- Mansinghka, V., Selsam, D. & Perov, Y. Venture: a higher-order probabilistic programming platform with programmable inference. Preprint at http://arxiv.org/abs/1404.0099 (2014). · arXiv
- Li, L., Wu, Y. & Russell, S. J. SWIFT: Compiled Inference for Probabilistic Programs. Report No. UCB/EECS-2015–12 (Univ. California, Berkeley, 2015).
- Bergstra, J. et al. Theano: a CPU and GPU math expression compiler. In Proc. 9th Python in Science Conference http://conference.scipy.org/proceedings/scipy2010/ (2010).
- Poupart, P. in Encyclopedia of Machine Learning 90–93 (Springer, 2010).
- Grosse, R. B., Salakhutdinov, R. & Tenenbaum, J. B. Exploiting compositionality to explore a large space of model structures. In Proc. Conference on Uncertainty in Artificial Intelligence 306–315 (2012).
- Welling, M. et al. Bayesian inference with big data: a snapshot from a workshop. ISBA Bulletin 21, https://bayesian.org/sites/default/files/fm/bulletins/1412.pdf (2014).
- Bakker, B. & Heskes, T. Task clustering and gating for Bayesian multitask learning. J. Mach. Learn. Res. 4, 83–99 (2003).
- Hensman, J., Fusi, N. & Lawrence, N. D. Gaussian processes for big data. In Proc. Conference on Uncertainty in Artificial Intelligence 244 (UAI, 2013).
Cited by
Items 801–900 of 1,004
Uncertainty estimation using Bayesian convolutional neural network for automatic channel detection
Pham, N. H., & Fomel, S. B. (2020) · Second International Meeting for Applied Geoscience & Energy · doi:10.1190/segam2020-3427239.1 · Cited by 17
Shojaei, K., & Mangolini, L. (2021) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/abf61e · Cited by 17
Ramos, D., Ramirez-Hereza, P., Toledano, D. T., González-Rodríguez, J., Ariza-Velazquez, A., Solis-Tovar, D., & Muñoz-Reja, C. (2021) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2021.104327 · Cited by 17
Ramos, D., Maroñas, J., & Almirall, J. R. (2021) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2021.104399 · Cited by 17
Roberson, M. M., Inman, K., Carey, A. S., Howard, I. L., & Shannon, J. (2021) · Computers & Structures · doi:10.1016/j.compstruc.2021.106707 · Cited by 17
Evans, D. E., Stewart, S., Stewart, D. C., Han, Z., Han, Y., & Able, J. A. (2021) · Journal of the American Society of Brewing Chemists · doi:10.1080/03610470.2021.1979891 · Cited by 19
“It seems clear that MLR algorithms will in the future need to take advantage of machine learning, which is rapidly developing and available with increasing commercial access for routine malt quality analysis.[79,80]”
BackgroundQuazi, S., Jangi, R., Gavas, S., & Karpiński, T. M. M. (2022) · Advances in bioinformatics and biomedical engineering book series · doi:10.4018/978-1-7998-8908-3.ch002 · Cited by 18
State sensing of bubble jet flow based on acoustic recognition and deep learning
Mikami, N., Ueki, Y., Shibahara, M., Aizawa, K., & Ara, K. (2022) · International Journal of Multiphase Flow · doi:10.1016/j.ijmultiphaseflow.2022.104340 · Cited by 18
Deep learning for situational understanding
Chakraborty, S., Preece, A. D., Alzantot, M., Xing, T., Braines, D., & Srivastava, M. B. (2017) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2017.8009785 · Cited by 18
“This observation has been exploited in recent work on probabilistic machine learning in general (see [35] and references therein) and Bayesian Deep Learning (BDL) in particular [36].”
MethodModeling and Predicting Carbon and Water Fluxes Using Data-Driven Techniques in a Forest Ecosystem
Dou, X., & Yang, Y. (2017) · Forests · doi:10.3390/f8120498 · Cited by 20
Artificial Intelligence and Health Care
Peyrou, B., Vignaux, J.-J., & André, A. (2018) · Health informatics · doi:10.1007/978-3-319-98216-8_3 · Cited by 18
Building Nonparametric n-Body Force Fields Using Gaussian Process Regression
Glielmo, A., Zeni, C., Fekete, Á., & Vita, A. D. (2020) · Lecture notes in physics · doi:10.1007/978-3-030-40245-7_5 · Cited by 19
Learning machines in Internet-delivered psychological treatment
Boman, M., Abdesslem, F. B., Forsell, E., Gillblad, D., Görnerup, O., Isacsson, N. H., Sahlgren, M., & Kaldo, V. (2019) · Progress in Artificial Intelligence · doi:10.1007/s13748-019-00192-0 · Cited by 20
Estimating underdiagnosis of COVID-19 with nowcasting and machine learning
Garcia, L. P., Gonçalves, A. V., de Andrade, M. P., Pedebôs, L. A., Vidor, A. C., Zaina, R., Hallal, A. L. C., Canto, G. D. L., Traebert, J. L., de Araújo, G. M., et al. (2021) · Revista Brasileira de Epidemiologia · doi:10.1590/1980-549720210047 · Cited by 18
Tractable Approximate Gaussian Inference for Bayesian Neural NetworksPreprint
Goulet, J.-A., Nguyen, L. H., & Amiri, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.09281 · Cited by 47
“…in many domains of applications, it is recognized that they fall short in situations where, for instance, datasets are small, when the task requires quantifying the uncertainty about the prediction made, and for continual learning (Ghahramani, 2015; Kendall & Gal, 2017; Farquhar & Gal, 2019).”
BackgroundOn the Semantic Interpretability of Artificial Intelligence ModelsPreprint
Silva, V. S., Freitas, A., & Handschuh, S. (2019) · Alexandria (UniSG) (University of St.Gallen) · doi:10.48550/arxiv.1907.04105 · Cited by 21
“The discovered model’s components are then translated into English phrases, resulting in a report with text, figures, and tables, detailing what has been inferred about the data, besides model checking and criticism (Ghahramani, 2015).”
MethodMeng, W., Ren, Y., & Miao, S. (2025) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2025.105234 · Cited by 16
A Systematic Review of AI-Enabled Predictive Quality Control in Advanced Metal Manufacturing Systems
Rainy, T. A., & Siddiquee, M. A. (2026) · American Journal of Interdisciplinary Studies · doi:10.63125/n73j2x72 · Cited by 16
A backward SDE method for uncertainty quantification in deep learning
Archibald, R. K., Bao, F., Cao, Y., & Zhang, H. (2022) · Discrete and Continuous Dynamical Systems - S · doi:10.3934/dcdss.2022062 · Cited by 23
Generative Models: An Interdisciplinary Perspective
Sankaran, K., & Holmes, S. (2022) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-033121-110134 · Cited by 23
“Moreover, concerns about flexibility have been addressed by advances in the number and variety of base modules amenable to computation and inference (Ghahramani, 2015, van de Meent et al., 2018).”
BackgroundZhang, Y., Zhang, D., Zhang, X., Qiu, L., Chan, F. T. S., Wang, Z., & Zhang, S. (2023) · Applied Mathematical Modelling · doi:10.1016/j.apm.2023.03.025 · Cited by 18
Senoner, J., Kratzwald, B., Kuzmanovic, M., Netland, T. H., & Feuerriegel, S. (2023) · Production and Operations Management · doi:10.1111/poms.14021 · Cited by 19
“Predictive analytics deals with the problem of inference; that is, analyzing patterns and making predictions from observational data (Ghahramani, 2015; Hastie et al., 2009).”
BackgroundLi, W., Cai, J., Lu, H., Wang, J., Cai, L., Tang, Z., Li, J., & Wang, C. (2023) · Annals of Nuclear Energy · doi:10.1016/j.anucene.2023.110016 · Cited by 19
AFL-HCS: asynchronous federated learning based on heterogeneous edge client selection
Tang, B., Xiao, Y., Zhang, L., Cao, B., Tang, M., & Yang, Q. (2024) · Cluster Computing · doi:10.1007/s10586-024-04314-9 · Cited by 16
“The fast increase of computing power and the evolution of communication infrastructure have directly resulted in the vigorous development of machine learning, which is a crucial driver of many current technologies [25, 26].”
Multidimensional Trajectory Prediction of UAV Swarms Based on Dynamic Graph Neural Network
An, Y., Liu, A., Liu, H., & Geng, L. (2024) · IEEE Access · doi:10.1109/access.2024.3391374 · Cited by 16
Geer, A. (2024) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2023ms004080 · Cited by 17
“Hence, Figure 1 also represents the problem as a Bayesian network (e.g., Ghahramani, 2015), in particular mapping onto the graphical representation of data assimilation and machine learning used by Geer (2021).”
Bayesian autoregressive online change-point detection with time-varying parameters
Tsaknaki, I.-Y., Lillo, F., & Mazzarisi, P. (2024) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2024.108500 · Cited by 17
Machine learning helps reveal key factors affecting tire wear particulate matter emissions
Jia, Z., Yin, J., Fang, T., Jiang, Z., Zhong, C., Cao, Z., Wu, L., Wei, N., Men, Z., Yang, L. X., et al. (2024) · Environment International · doi:10.1016/j.envint.2024.109224 · Cited by 17
The role of cognitive computing in NLP
Orynbay, L., Bekmanova, G., Yergesh, B., Omarbekova, A., Sairanbekova, A., & Sharipbay, A. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1486581 · Cited by 20
“Combining these technologies not only improves the understanding and interaction of machines but also opens the way for advancements in various fields such as education, finance and social network (Ghahramani, 2015).”
Taguelmimt, K., Andrade-Miranda, G. X., Harb, H., Thanh, T. T., Dang, H.-P., Malavaud, B. A., & Bert, J. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110440 · Cited by 18
SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs
Li, K., Chen, J. F., Chen, W., & Zhu, J. (2017) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3037697.3037740 · Cited by 16
An intelligent sampling framework for multi-objective optimization in high dimensional design space
Ling, Y., Ghosh, S., Asher, I., Kristensen, J., Ryan, K. M., & Wang, L. (2018) · AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference (SDM) · doi:10.2514/6.2018-0912 · Cited by 16
Multi-Features Fusion for Fault Diagnosis of Pedal Robot Using Time-Speed Signals
Zhu, Y., Fu, Z., Fu, Z., Chen, X., & Wu, E. Q. (2019) · Sensors · doi:10.3390/s19010163 · Cited by 16
“It can effectively classify nonlinear samples [18].”
The Application of Artificial Intelligence in Agriculture
Zhao, B. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1574/1/012139 · Cited by 18
“Based on the latest development of artificial intelligence technology in the field of agriculture, this paper conducts an in-depth study on the current issues of intelligent development of agricultural management, so as to provide practical thinking and theoretical reference for the further strengthening of intelligen…”
Analysis of Bayesian Networks via Prob-Solvable Loops
Bartocci, E., Kovács, L., & Stankovič, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64276-1_12 · Cited by 16
Uncertainty-aware body composition analysis with deep regression ensembles on UK Biobank MRI
Langner, T., Gustafsson, F., Avelin, B., Strand, R., Ahlström, H. K., & Kullberg, J. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101994 · Cited by 19
Uncertainties in Neural Networks : A System Identification Approach
Malmström, M. (2021) · Linköping studies in science and technology. Thesis · doi:10.3384/lic.diva-174720 · Cited by 22
Uncertainty and interpretability analysis of encoder-decoder architecture for channel detection
Pham, N. H., & Fomel, S. B. (2021) · Geophysics · doi:10.1190/geo2020-0409.1 · Cited by 16
Improved density prediction model based on global optimization algorithm for GPR system
Chen, Y., Li, F., Zhou, S., & Zhang, X. (2024) · Measurement · doi:10.1016/j.measurement.2024.115243 · Cited by 16
Bayesian Nonnegative CP Decomposition-based Feature Extraction Algorithm for Drowsiness Detection
Dong, Q., Wang, B., Qing, Y., Zhang, T., Zhang, Y., Wang, X., & Nakamura, M. (2016) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2016.2618902 · Cited by 16
Symmetric Non-negative Latent Factor Models for Undirected Large Networks
Luo, X., & Shang, M. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/339 · Cited by 16
A computational cognitive framework of spatial memory in brains and robots
Madl, T., Franklin, S., Chen, K., & Trappl, R. (2017) · Cognitive Systems Research · doi:10.1016/j.cogsys.2017.08.002 · Cited by 16
“Probabilistic models use probability distributions to represent quantities and the uncertainties associated with them, utilizing probability theory to manipulate these distributions (Ghahramani, 2015).”
BackgroundZhou, R., Feng, J., Chen, Y., Chang, H., & Zhou, Y. (2019) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2019.2950883 · Cited by 16
Anomaly Detection System for Water Networks in Northern Ethiopia Using Bayesian Inference
Tashman, Z., Gorder, C., Parthasarathy, S., Nasr‐Azadani, M. M., & Webre, R. (2020) · Sustainability · doi:10.3390/su12072897 · Cited by 16
Momentum-Incorporated Symmetric Non-Negative Latent Factor Models
Zhong, Y., Jin, L., Shang, M., & Luo, X. (2020) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2020.3012656 · Cited by 34
Data Science and Machine Learning in Geo-Electromagnetics: A Review
Huang, Q., Wu, S., & Xue, J. (2025) · Surveys in Geophysics · doi:10.1007/s10712-025-09904-9 · Cited by 25
Zhang, R., Li, X., Wan, C., Hoffmann, R., Hindenberg, M., Xu, Y., Liu, S., Kong, D., Xiong, S., He, S., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-66864-9 · Cited by 16
An efficient probabilistic hardware architecture for diffusion-like models
Jelinčič, A., Lockwood, O., Garlapati, A., Schillinger, P., Chuang, I. L., Verdon, G., & McCourt, T. (2026) · npj Unconventional Computing · doi:10.1038/s44335-026-00075-3 · Cited by 21
“The challenge with EBMs The fundamental problem of machine learning is inferring the probability distribution that underlies some data 37,38 .”
AVEI-BO: an efficient Bayesian optimization using adaptively varied expected improvement
Yan, C., Du, H., Kang, E., Mi, D., Liu, H., & You, Y. (2022) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-022-03256-3 · Cited by 15
“Therefore, non-parametric models have high scalability and flexibility, reducing the occurrence of ”overfitting” (Ghahramani 2015).”
BackgroundNasejje, J. B., Whata, A., & Chimedza, C. (2022) · PLoS ONE · doi:10.1371/journal.pone.0279435 · Cited by 14
“There has therefore been a shift in research on making sure that robust tests are developed to make sure that the machine learning and statistical models agree at least on the basics or the building blocks of statistical theory [3].”
BackgroundTriboelectric nanogenerators as self-powered sensors for biometric authentication
Shi, X., Han, K., Pang, Y., Mai, W., & Luo, J. (2023) · Nanoscale · doi:10.1039/d3nr01334k · Cited by 15
Chegini, M., & Far, A. M. (2023) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2023.2297983 · Cited by 24
“Gal and Ghahramani (2015) proposed a new framework that use dropout in deep neural networks as approximate Bayesian inference while mitigate the problem of quantifying uncertainty in deep learning without suffering computational complexity or decreasing test accuracy.”
InfluentialAutoSMC: An Automated Machine Learning Framework for Signal Modulation Classification
Wang, Y., Bai, J., Xiao, Z. Q., Chen, Z., Xiong, Y., Jiang, H., & Jiao, L. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3414249 · Cited by 15
“BO fully meets this requirement [41].”
Emerging strategies for addressing flood-damage modeling issues: A review
Tilano, S. A. R., Boucher, M., & Lacey, J. R. W. (2024) · International Journal of Disaster Risk Reduction · doi:10.1016/j.ijdrr.2024.105058 · Cited by 19
Paik, S., Novozhilova, E., Mays, K. K., & Katz, J. E. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00235-7 · Cited by 17
“Today’s AI systems—a combination of generative AI and prior machine learning (ML) models— are probabilistic in that they make inferences by learning from existing patterns of historical data and providing predictions for unknown data [42].”
Albanwan, H., & Qin, R. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.05.020 · Cited by 15
Zhang, L., & Zhang, J. (2020) · IEEE Access · doi:10.1109/access.2020.3047928 · Cited by 15
“Thus, the prognostics of both performance degradation and failure probability are necessary for comprehensively evaluating the variability and uncertainty in the degradation process [5], [6].”
BackgroundIntrospective Failure Prediction for Semantic Image Segmentation
Kuhn, C. B., Hofbauer, M., Lee, S., Petrović, G., & Steinbach, E. G. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294308 · Cited by 16
Word Level LSTM and Recurrent Neural Network for Automatic Text Generation
Buddana, H. V. K. S., Kaushik, S. S., Manogna, P., & Shijin Kumar, P. S. (2021) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci50826.2021.9402488 · Cited by 15
Multi label restaurant classification using support vector machine
AL-Bakri, N. F., Al-zubidi, A. F., Alnajjar, A. B., & Ahmed, E. Q. (2021) · Periodicals of Engineering and Natural Sciences (PEN) · doi:10.21533/pen.v9.i2.782 · Cited by 15
Uncertainty-Aware Label Rectification for Domain Adaptive Mitochondria Segmentation
Wu, S., Chen, C., Xiong, Z., Chen, X., & Sun, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87199-4_18 · Cited by 25
Tomczak, J. M. (2021) · Springer eBooks · doi:10.1007/978-3-030-93158-2_1 · Cited by 24
Zhou, Y., Wang, M., Zhao, S., & Yan, Y. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/7167066 · Cited by 16
“Machine learning (ML) refers to a technology to make computer simulate or implement human learning activities, which can make full use of information via algorithms to obtain hidden, efective, and under-standable knowledge from massive data, so as to build predictive models [10].”
RetractedOyebisi, S. O., Owamah, H. I., & Omeje, M. (2023) · Cleaner Engineering and Technology · doi:10.1016/j.clet.2023.100629 · Cited by 15
Tsang, B., Gupta, A., Takahashi, M. S., Baffi, H. C., Ola, T., & Doria, A. S. (2023) · Japanese Journal of Radiology · doi:10.1007/s11604-023-01437-8 · Cited by 16
“Artificial intelligence (AI) is a branch of computer science described as simulating intelligent human behaviour [1, 2].”
Movaghar, A., Seltzer, M. M., Sterling, A. M., Greenberg, J. S., & Saha, K. (2017) · Scientific Reports · doi:10.1038/s41598-017-02682-4 · Cited by 15
Good Initializations of Variational Bayes for Deep Models
Rossi, S., Pietro Michiardi, A., & Filippone, M. (2018) · Graduate School and Research Center in Digital Science (EURECOM) · doi:10.48550/arxiv.1810.08083 · Cited by 15
“In the case of CNNs, we also compare with Monte Carlo Dropout (MCD; Gal & Ghahramani (2016a)) and Natural Noisy Gradients (NOISY-KFAC; Zhang et al.”
BackgroundMethodInfluentialBig Earth Data: a comprehensive analysis of visualization analytics issues
Merritt, P., Bi, H., Davis, B. M., Windmill, C., & Xue, Y. (2018) · Big Earth Data · doi:10.1080/20964471.2019.1576260 · Cited by 16
“…as topics for further reading including: machine learning (SAS Institute, 2018b; Suthaharan, 2014); reinforcement learning (Qiu, Wu, Ding, Xu, & Feng, 2016; Zhou, Pan, Wang, & Vasilakos, 2017); probabilistic learning (Ghahramani, 2015); and Big Data mining (IBM, Zikopoulos & Eaton, 2011).”
Cryptosystem Identification Scheme Based on ASCII Code Statistics
Zhang, W., Zhao, Y., & Fan, S. (2020) · Security and Communication Networks · doi:10.1155/2020/8875864 · Cited by 15
“*e experimental evaluation indicator A in the above definition usually refers to the machine learning classification evaluation indicator, precision, recall rate, F1-score, and accuracy, which is slightly different from the identification accuracy under pattern identification [13].”
MethodSu, J., Zhao, Y., He, T., & Luo, P. (2021) · Oil & Gas Science and Technology – Revue d’IFP Energies nouvelles · doi:10.2516/ogst/2021003 · Cited by 15
Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulationsPreprint
Anderson, G. J., Gaffney, J., Spears, B. K., Bremer, P., Anirudh, R., & Thiagarajan, J. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13749 · Cited by 15
“A key drawback of standard DNNs is that they do not supply their predictions with a measure of uncertainty, making their use problematic in the sciences (and many other disciplines), where prediction uncertainties are typically as important as the prediction itself [2].”
BackgroundZe-HB Hierarchical Bayesian Extension of the ZePreprint
Tqemaladze, J. (2025) · Preprints.org · doi:10.20944/preprints202512.0103.v1 · Cited by 15
CuInS2-based S-scheme heterojunction photocatalysts for efficient photocatalytic hydrogen evolution
Zhai, J., Lin, J., Yang, F., Li, J., Shi, X., Xiao, Y., Tian, X., & Liu, Y. (2026) · Coordination Chemistry Reviews · doi:10.1016/j.ccr.2026.218025 · Cited by 15
Artistic Style Meets Artificial Intelligence
Choi, S. K., DiPaola, S., & Töyrylä, H. (2021) · Journal of Perceptual Imaging · doi:10.2352/j.percept.imaging.2021.4.2.020501 · Cited by 14
Müllner, J., Moosbrugger, M., & Kovács, L. (2024) · Proceedings of the ACM on Programming Languages · doi:10.1145/3632872 · Cited by 14
Unsupervised data imputation with multiple importance sampling variational autoencoders
Kuang, S., Huang, Y., & Song, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-87641-0 · Cited by 14
Zhuge, Y., Ren, Z., Xiao, Z., Zhang, Z., Liu, X., Liu, W., Xu, S., Ho, C. P., Li, N., & Lee, C. (2025) · Advanced Science · doi:10.1002/advs.202500525 · Cited by 16
Moqadam, H., & Eisen, O. (2025) · The Cryosphere · doi:10.5194/tc-19-2159-2025 · Cited by 16
Supermartingale Certificates for Quantitative Omega-Regular Verification and Control
Henzinger, T. A., Mallik, K., Sadeghi, P., & Žikelić, Đ. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98679-6_2 · Cited by 14
Sparse Gaussian Processes on Discrete Domains
Fortuin, V., Dresdner, G., Strathmann, H., & Rätsch, G. (2021) · IEEE Access · doi:10.1109/access.2021.3082761 · Cited by 14
Physics-Prior Bayesian Neural Networks in Semiconductor Processing
Chen, C. H., Parashar, P., Akbar, C., Fu, S. M., Syu, M.-Y., & Lin, A. S. (2019) · IEEE Access · doi:10.1109/access.2019.2940130 · Cited by 14
Soize, C., & Orcesi, A. (2020) · Structure and Infrastructure Engineering · doi:10.1080/15732479.2020.1811991 · Cited by 14
Neuro-Symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels
Lavin, A. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-93080-6_5 · Cited by 20
Zhou, J., Zhang, Q., & Li, X. (2020) · Information Sciences · doi:10.1016/j.ins.2020.09.067 · Cited by 14
Marquez, P., Volk, G. F., Maule, F., Korth, D., Bitter, T., Koscielny, S., Aschenbach, R., & Guntinas‐Lichius, O. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02288-8 · Cited by 14
The role of AI and machine learning in contemporary orthodontics
Retrouvey, J.-M. (2021) · APOS Trends in Orthodontics · doi:10.25259/apos_148_2020 · Cited by 18
“[27] Data are the key ingredient of machine learning[28] as Modern software programs, sophisticated statistical analyzes, and algorithms require a tremendous amount of data to be able to predict treatment outcomes and analyze the shortcoming of past-approaches.”
BackgroundStatistical robustness of Markov chain Monte Carlo accelerators
Zhang, X., Bashizade, R., Wang, Y., Mukherjee, S., & Lebeck, A. R. (2021) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3445814.3446697 · Cited by 14
“Compared with Deep Neural Networks, probabilistic models are conceptually simple, compositional, and interpretable [27].”
BackgroundA Marr's Three‐Level Analytical Framework for Neuromorphic Electronic Systems
Guo, Y., Zou, X., Hu, Y., Yang, Y., Wang, X., He, Y., Kong, R., Guo, Y., Li, G., Zhang, W., et al. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100054 · Cited by 16
Zhao, Y., Shen, J., Feng, J., Sun, Z., Sun, T., Liu, D., Xi, M., Li, R. S., & Wang, X. (2021) · Water · doi:10.3390/w13243629 · Cited by 14
“In addition, machine learning models can be trained for several key environmental quality parameters and the final environmental outcomes, using the current archived data, and can further predict future results after inputting new parameters [18].”
BackgroundAccelerating Bayesian Neural Networks via Algorithmic and Hardware Optimizations
Fan, H., Ferianc, M., Que, Z., Niu, X., Rodrigues, M. R. D., & Luk, W. W. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3153682 · Cited by 14
“By augmenting NNs with the capability of Bayesian inference, they become more robust against overfitting, even when dealing with datasets with fewer samples [10].”
BackgroundMarino, A., Pariso, P., & Picariello, M. (2022) · Journal of Entrepreneurship and Sustainability Issues · doi:10.9770/jesi.2022.9.3(21 · Cited by 14
Berns, F., Hüwel, J. D., & Beecks, C. (2022) · SN Computer Science · doi:10.1007/s42979-022-01186-x · Cited by 14
“Overall, they are considered a prominent method in the field of probabilistic machine learning [15].”
MethodBaumeister, H., & Montag, C. (2022) · Studies in neuroscience, psychology and behavioral economics · doi:10.1007/978-3-030-98546-2_1 · Cited by 14
Gaussian Processes for radiation dose prediction in nuclear power plant reactors
Balanya, S. A., Ramos, D., Ramirez-Hereza, P., Toledano, D. T., González-Rodríguez, J., Ariza-Velazquez, A., Orlovac, J. V., & Doncel, N. (2022) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2022.104652 · Cited by 14
Investigation of social media representation bias in disasters: Towards a systematic framework
Chen, Y., He, S., & Zhou, Z. (2022) · International Journal of Disaster Risk Reduction · doi:10.1016/j.ijdrr.2022.103312 · Cited by 14
Abbas, J., Yousef, M., Peled, N., Hershkovitz, I., & Hamoud, K. (2023) · BMC Musculoskeletal Disorders · doi:10.1186/s12891-023-06330-z · Cited by 18
“Machine learning (ML) is defined as a series of computational tools that are capable of determining the association between material data and do not required a specific setup [9].”
BackgroundYu, C., Li, Y., Liu, Y., Ge, L., Wang, H., Luo, Y., & Pan, L. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111059 · Cited by 14
Robson, B., & Boray, S. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.103369 · Cited by 14
Sweep-Net: An Artificial Neural Network for radiation transport solves
Tano, M., & Ragusa, J. C. (2020) · Journal of Computational Physics · doi:10.1016/j.jcp.2020.109757 · Cited by 14
Does Dataset Complexity Matters for Model Explainers?
Ribeiro, J., da Silva, R. L. S., Cardoso, L., & Alves, R. C. D. O. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671630 · Cited by 15
“Thus, growing the need for machine learning models to solve increasingly complex problems that demand, in addition to high performance in the resolution, characteristics that justify decision-making[33][18].”
Background
Metadata
- Authors
- Ghahramani, Z.
- Venue
- Nature
- Published
- 2015-05-27
- Volume
- 521
- Issue
- 7553
- Pages
- 452-459
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- OpenAlex
- W1494192115
- Cited by
- 1,995
- References
- 108
- Citations by year
- 2026: 166 · 2025: 231 · 2024: 228 · 2023: 206 · 2022: 217 · 2021: 265 · 2020: 235 · 2019: 210 · 2018: 102 · 2017: 84 · 2016: 39 · 2015: 11
- FWCI
- 2.97
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Nature (publishedVersion)
- PubMed (publishedVersion)
- Apollo (University of Cambridge) (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Cambridge University Engineering Department Publications Database (submittedVersion)
- Funders
- Engineering and Physical Sciences Research Council (EP/I036575/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- stochastic modeling, machine learning, artificial intelligence, uncertainty representation, probabilistic programming, Bayesian optimization, data compression, experiential learning
- MeSH terms
- Artificial Intelligence, Automation, Bayes Theorem, Models, Statistical, Statistics, Nonparametric, Uncertainty, Data Compression
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.