Relevant bibliographies by topics / Statistical learning theory / Journal articles

Journal articles on the topic 'Statistical learning theory'

To see the other types of publications on this topic, follow the link: Statistical learning theory.
Author: Grafiati
Published: 4 June 2021
Last updated: 31 July 2024

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Statistical learning theory.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Wu, Yuhai. "Statistical Learning Theory." Technometrics 41, no. 4 (November 1999): 377–78. http://dx.doi.org/10.1080/00401706.1999.10485951.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Vapnik, Vladimir, and Rauf Izmailov. "Rethinking statistical learning theory: learning using statistical invariants." Machine Learning 108, no. 3 (July 18, 2018): 381–423. http://dx.doi.org/10.1007/s10994-018-5742-0.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Vapnik, V. N. "Complete Statistical Theory of Learning." Automation and Remote Control 80, no. 11 (November 2019): 1949–75. http://dx.doi.org/10.1134/s000511791911002x.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Shi, Luyuan. "Statistical Learning in Game Theory." Journal of Applied Mathematics and Physics 11, no. 03 (2023): 663–69. http://dx.doi.org/10.4236/jamp.2023.113043.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Kulkarni, Sanjeev R., and Gilbert Harman. "Statistical learning theory: a tutorial." Wiley Interdisciplinary Reviews: Computational Statistics 3, no. 6 (June 10, 2011): 543–56. http://dx.doi.org/10.1002/wics.179.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Cherkassky, V. "The Nature Of Statistical Learning Theory~." IEEE Transactions on Neural Networks 8, no. 6 (November 1997): 1564. http://dx.doi.org/10.1109/tnn.1997.641482.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Wechsler, H., Z. Duric, F. Li, and V. Cherkassky. "Motion estimation using statistical learning theory." IEEE Transactions on Pattern Analysis and Machine Intelligence 26, no. 4 (April 2004): 466–78. http://dx.doi.org/10.1109/tpami.2004.1265862.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Estes, William K. "Toward a statistical theory of learning." Psychological Review 101, no. 2 (1994): 282–89. http://dx.doi.org/10.1037/0033-295x.101.2.282.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Lippi, Marco. "Statistical Relational Learning for Game Theory." IEEE Transactions on Computational Intelligence and AI in Games 8, no. 4 (December 2016): 412–25. http://dx.doi.org/10.1109/tciaig.2015.2490279.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Vapnik, V. N. "An overview of statistical learning theory." IEEE Transactions on Neural Networks 10, no. 5 (1999): 988–99. http://dx.doi.org/10.1109/72.788640.

Full text
APA, Harvard, Vancouver, ISO, and other styles
11

Sain, Stephan R. "The Nature of Statistical Learning Theory." Technometrics 38, no. 4 (November 1996): 409. http://dx.doi.org/10.1080/00401706.1996.10484565.

Full text
APA, Harvard, Vancouver, ISO, and other styles
12

Bousquet, Olivier. "New approaches to statistical learning theory." Annals of the Institute of Statistical Mathematics 55, no. 2 (June 2003): 371–89. http://dx.doi.org/10.1007/bf02530506.

Full text
APA, Harvard, Vancouver, ISO, and other styles
13

Schölkopf, Bernhard. "Statistical learning theory, capacity, and complexity." Complexity 8, no. 4 (March 2003): 87–94. http://dx.doi.org/10.1002/cplx.10094.

Full text
APA, Harvard, Vancouver, ISO, and other styles
14

YAMADA, Koshi, and Sumio WATANABE. "Statistical Learning Theory of Quasi-Regular Cases." IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E95.A, no. 12 (2012): 2479–87. http://dx.doi.org/10.1587/transfun.e95.a.2479.

Full text
APA, Harvard, Vancouver, ISO, and other styles
15

Konyagin, S. V., and E. D. Livshits. "On adaptive estimators in statistical learning theory." Proceedings of the Steklov Institute of Mathematics 260, no. 1 (April 2008): 185–93. http://dx.doi.org/10.1134/s0081543808010136.

Full text
APA, Harvard, Vancouver, ISO, and other styles
16

Loh, Po-Ling. "On Lower Bounds for Statistical Learning Theory." Entropy 19, no. 11 (November 15, 2017): 617. http://dx.doi.org/10.3390/e19110617.

Full text
APA, Harvard, Vancouver, ISO, and other styles
17

Watanabe, Sumio. "Asymptotic learning curve and renormalizable condition in statistical learning theory." Journal of Physics: Conference Series 233 (June 1, 2010): 012014. http://dx.doi.org/10.1088/1742-6596/233/1/012014.

Full text
APA, Harvard, Vancouver, ISO, and other styles
18

Bilbro, Griff L., and David E. Van den Bout. "Maximum Entropy and Learning Theory." Neural Computation 4, no. 6 (November 1992): 839–53. http://dx.doi.org/10.1162/neco.1992.4.6.839.

Full text
Abstract:
We derive the learning theory recently reported by Tishby, Levin, and Solla (TLS) directly from the principle of maximum entropy instead of statistical mechanics. The theory generally applies to any problem of modeling data. We analyze an elementary example for which we find the predictions consistent with intuition and conventional statistical results and we numerically examine the more realistic problem of training a competitive net to learn a one-dimensional probability density from samples. The TLS theory is useful for predicting average training behavior.
APA, Harvard, Vancouver, ISO, and other styles
19

Jun, Sung-Hae. "A Co-Evolutionary Computing for Statistical Learning Theory." International Journal of Fuzzy Logic and Intelligent Systems 5, no. 4 (December 1, 2005): 281–85. http://dx.doi.org/10.5391/ijfis.2005.5.4.281.

Full text
APA, Harvard, Vancouver, ISO, and other styles
20

Ghosh, S. K. "Subpixel classifiers: fuzzy theory versus statistical learning algorithm." Journal of Applied Remote Sensing 1, no. 1 (June 1, 2007): 013517. http://dx.doi.org/10.1117/1.2759178.

Full text
APA, Harvard, Vancouver, ISO, and other styles
21

Zuo, Yi, A. B. M. Shawkat Ali, and Katsutoshi Yada. "Consumer Purchasing Behavior Extraction Using Statistical Learning Theory." Procedia Computer Science 35 (2014): 1464–73. http://dx.doi.org/10.1016/j.procs.2014.08.209.

Full text
APA, Harvard, Vancouver, ISO, and other styles
22

Cherkassky, Vladimir, and Yunqian Ma. "Another look at statistical learning theory and regularization." Neural Networks 22, no. 7 (September 2009): 958–69. http://dx.doi.org/10.1016/j.neunet.2009.04.005.

Full text
APA, Harvard, Vancouver, ISO, and other styles
23

Evgeniou, Theodoros, Tomaso Poggio, Massimiliano Pontil, and Alessandro Verri. "Regularization and statistical learning theory for data analysis." Computational Statistics & Data Analysis 38, no. 4 (February 2002): 421–32. http://dx.doi.org/10.1016/s0167-9473(01)00069-x.

Full text
APA, Harvard, Vancouver, ISO, and other styles
24

Chaochao, Huang, Wu Xiaodi, and Tong Wuqin. "Infrared Image Simulation Based On Statistical Learning Theory." International Journal of Infrared and Millimeter Waves 28, no. 12 (October 13, 2007): 1143–53. http://dx.doi.org/10.1007/s10762-007-9270-4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
25

Erickson, Lucy C., and Erik D. Thiessen. "Statistical learning of language: Theory, validity, and predictions of a statistical learning account of language acquisition." Developmental Review 37 (September 2015): 66–108. http://dx.doi.org/10.1016/j.dr.2015.05.002.

Full text
APA, Harvard, Vancouver, ISO, and other styles
26

Abbasi, Zhang, Zimbra, Chen, and Nunamaker. "Detecting Fake Websites: The Contribution of Statistical Learning Theory." MIS Quarterly 34, no. 3 (2010): 435. http://dx.doi.org/10.2307/25750686.

Full text
APA, Harvard, Vancouver, ISO, and other styles
27

Jing Sun. "Financial Early Warning Methods Based on Statistical Learning Theory." INTERNATIONAL JOURNAL ON Advances in Information Sciences and Service Sciences 4, no. 19 (October 31, 2012): 636–42. http://dx.doi.org/10.4156/aiss.vol4.issue19.77.

Full text
APA, Harvard, Vancouver, ISO, and other styles
28

Padilla, M., and N. M. Grzywacz. "Is statistical learning theory applicable to the human brain?" Journal of Vision 6, no. 6 (March 18, 2010): 166. http://dx.doi.org/10.1167/6.6.166.

Full text
APA, Harvard, Vancouver, ISO, and other styles
29

Siegelman, Noam, Louisa Bogaerts, Morten H. Christiansen, and Ram Frost. "Towards a theory of individual differences in statistical learning." Philosophical Transactions of the Royal Society B: Biological Sciences 372, no. 1711 (January 5, 2017): 20160059. http://dx.doi.org/10.1098/rstb.2016.0059.

Full text
Abstract:
In recent years, statistical learning (SL) research has seen a growing interest in tracking individual performance in SL tasks, mainly as a predictor of linguistic abilities. We review studies from this line of research and outline three presuppositions underlying the experimental approach they employ: (i) that SL is a unified theoretical construct; (ii) that current SL tasks are interchangeable, and equally valid for assessing SL ability; and (iii) that performance in the standard forced-choice test in the task is a good proxy of SL ability. We argue that these three critical presuppositions are subject to a number of theoretical and empirical issues. First, SL shows patterns of modality- and informational-specificity, suggesting that SL cannot be treated as a unified construct. Second, different SL tasks may tap into separate sub-components of SL that are not necessarily interchangeable. Third, the commonly used forced-choice tests in most SL tasks are subject to inherent limitations and confounds. As a first step, we offer a methodological approach that explicitly spells out a potential set of different SL dimensions, allowing for better transparency in choosing a specific SL task as a predictor of a given linguistic outcome. We then offer possible methodological solutions for better tracking and measuring SL ability. Taken together, these discussions provide a novel theoretical and methodological approach for assessing individual differences in SL, with clear testable predictions. This article is part of the themed issue ‘New frontiers for statistical learning in the cognitive sciences’.
APA, Harvard, Vancouver, ISO, and other styles
30

Amari, Shun-ichi, and Noboru Murata. "Statistical Theory of Learning Curves under Entropic Loss Criterion." Neural Computation 5, no. 1 (January 1993): 140–53. http://dx.doi.org/10.1162/neco.1993.5.1.140.

Full text
Abstract:
The present paper elucidates a universal property of learning curves, which shows how the generalization error, training error, and the complexity of the underlying stochastic machine are related and how the behavior of a stochastic machine is improved as the number of training examples increases. The error is measured by the entropic loss. It is proved that the generalization error converges to H0, the entropy of the conditional distribution of the true machine, as H0 + m*/(2t), while the training error converges as H0 - m*/(2t), where t is the number of examples and m* shows the complexity of the network. When the model is faithful, implying that the true machine is in the model, m* is reduced to m, the number of modifiable parameters. This is a universal law because it holds for any regular machine irrespective of its structure under the maximum likelihood estimator. Similar relations are obtained for the Bayes and Gibbs learning algorithms. These learning curves show the relation among the accuracy of learning, the complexity of a model, and the number of training examples.
APA, Harvard, Vancouver, ISO, and other styles
31

Koltchinskii, V., C. T. Abdallah, M. Ariola, and P. Dorato. "Statistical learning control of uncertain systems: theory and algorithms." Applied Mathematics and Computation 120, no. 1-3 (May 2001): 31–43. http://dx.doi.org/10.1016/s0096-3003(99)00283-0.

Full text
APA, Harvard, Vancouver, ISO, and other styles
32

Guergachi, A. A., and G. G. Patry. "Statistical learning theory, model identification and system information content." International Journal of General Systems 31, no. 4 (July 2002): 343–57. http://dx.doi.org/10.1080/03081070290018056.

Full text
APA, Harvard, Vancouver, ISO, and other styles
33

Brunato, Mauro, and Roberto Battiti. "Statistical learning theory for location fingerprinting in wireless LANs." Computer Networks 47, no. 6 (April 2005): 825–45. http://dx.doi.org/10.1016/j.comnet.2004.09.004.

Full text
APA, Harvard, Vancouver, ISO, and other styles
34

Tsiamis, Anastasios, Ingvar Ziemann, Nikolai Matni, and George J. Pappas. "Statistical Learning Theory for Control: A Finite-Sample Perspective." IEEE Control Systems 43, no. 6 (December 2023): 67–97. http://dx.doi.org/10.1109/mcs.2023.3310345.

Full text
APA, Harvard, Vancouver, ISO, and other styles
35

Moeslund, Thomas B., Sergio Escalera, Gholamreza Anbarjafari, Kamal Nasrollahi, and Jun Wan. "Statistical Machine Learning for Human Behaviour Analysis." Entropy 22, no. 5 (May 7, 2020): 530. http://dx.doi.org/10.3390/e22050530.

Full text
APA, Harvard, Vancouver, ISO, and other styles
36

Bahri, Yasaman, Jonathan Kadmon, Jeffrey Pennington, Sam S. Schoenholz, Jascha Sohl-Dickstein, and Surya Ganguli. "Statistical Mechanics of Deep Learning." Annual Review of Condensed Matter Physics 11, no. 1 (March 10, 2020): 501–28. http://dx.doi.org/10.1146/annurev-conmatphys-031119-050745.

Full text
Abstract:
The recent striking success of deep neural networks in machine learning raises profound questions about the theoretical principles underlying their success. For example, what can such deep networks compute? How can we train them? How does information propagate through them? Why can they generalize? And how can we teach them to imagine? We review recent work in which methods of physical analysis rooted in statistical mechanics have begun to provide conceptual insights into these questions. These insights yield connections between deep learning and diverse physical and mathematical topics, including random landscapes, spin glasses, jamming, dynamical phase transitions, chaos, Riemannian geometry, random matrix theory, free probability, and nonequilibrium statistical mechanics. Indeed, the fields of statistical mechanics and machine learning have long enjoyed a rich history of strongly coupled interactions, and recent advances at the intersection of statistical mechanics and deep learning suggest these interactions will only deepen going forward.
APA, Harvard, Vancouver, ISO, and other styles
37

Arciuli, Joanne. "Reading as Statistical Learning." Language, Speech, and Hearing Services in Schools 49, no. 3S (August 14, 2018): 634–43. http://dx.doi.org/10.1044/2018_lshss-stlt1-17-0135.

Full text
Abstract:
Purpose The purpose of this tutorial is to explain how learning to read can be thought of as learning statistical regularities and to demonstrate why this is relevant for theory, modeling, and practice. This tutorial also shows how triangulation of methods and cross-linguistic research can be used to gain insight. Method The impossibility of conveying explicitly all of the regularities that children need to acquire in a deep orthography, such as English, can be demonstrated by examining lesser-known probabilistic orthographic cues to lexical stress. Detection of these kinds of cues likely occurs via a type of implicit learning known as statistical learning (SL). The first part of the tutorial focuses on these points. Next, studies exploring how individual differences in the capacity for SL relate to variability in word reading accuracy in the general population are discussed. A brief overview of research linking impaired SL and dyslexia is also provided. The final part of the tutorial focuses on how we might supplement explicit literacy instruction with implicit learning methods and emphasizes the value of testing the efficacy of new techniques in the classroom. The basic and applied research reviewed here includes corpus analyses, behavioral testing, computational modeling, and classroom-based research. Although some of these methods are not commonly used in clinical research, the depth and breadth of this body of work provide a compelling case for why reading can be thought of as SL and how this view can inform practice. Conclusion Implicit methods that draw on the principles of SL can supplement the much-needed explicit instruction that helps children learn to read. This synergy of methods has the potential to spark innovative practices in literacy instruction and remediation provided by educators and clinicians to support typical learners and those with developmental disabilities.
APA, Harvard, Vancouver, ISO, and other styles
38

Ran, Zhi-Yong, and Bao-Gang Hu. "Parameter Identifiability in Statistical Machine Learning: A Review." Neural Computation 29, no. 5 (May 2017): 1151–203. http://dx.doi.org/10.1162/neco_a_00947.

Full text
Abstract:
This review examines the relevance of parameter identifiability for statistical models used in machine learning. In addition to defining main concepts, we address several issues of identifiability closely related to machine learning, showing the advantages and disadvantages of state-of-the-art research and demonstrating recent progress. First, we review criteria for determining the parameter structure of models from the literature. This has three related issues: parameter identifiability, parameter redundancy, and reparameterization. Second, we review the deep influence of identifiability on various aspects of machine learning from theoretical and application viewpoints. In addition to illustrating the utility and influence of identifiability, we emphasize the interplay among identifiability theory, machine learning, mathematical statistics, information theory, optimization theory, information geometry, Riemann geometry, symbolic computation, Bayesian inference, algebraic geometry, and others. Finally, we present a new perspective together with the associated challenges.
APA, Harvard, Vancouver, ISO, and other styles
39

Plewczynski, Dariusz. "Mean-field theory of meta-learning." Journal of Statistical Mechanics: Theory and Experiment 2009, no. 11 (November 12, 2009): P11003. http://dx.doi.org/10.1088/1742-5468/2009/11/p11003.

Full text
APA, Harvard, Vancouver, ISO, and other styles
40

Oneto, Luca, Federica Bisio, Erik Cambria, and Davide Anguita. "Statistical Learning Theory and ELM for Big Social Data Analysis." IEEE Computational Intelligence Magazine 11, no. 3 (August 2016): 45–55. http://dx.doi.org/10.1109/mci.2016.2572540.

Full text
APA, Harvard, Vancouver, ISO, and other styles
41

Vidyasagar, M. "Randomized algorithms for robust controller synthesis using statistical learning theory." Automatica 37, no. 10 (October 2001): 1515–28. http://dx.doi.org/10.1016/s0005-1098(01)00122-4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
42

Vidyasagar, M. "An introduction to some statistical aspects of PAC learning theory." Systems & Control Letters 34, no. 3 (June 1998): 115–24. http://dx.doi.org/10.1016/s0167-6911(98)00007-3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
43

Oneto, Luca, Nicolò Navarin, Michele Donini, Alessandro Sperduti, Fabio Aiolli, and Davide Anguita. "Measuring the expressivity of graph kernels through Statistical Learning Theory." Neurocomputing 268 (December 2017): 4–16. http://dx.doi.org/10.1016/j.neucom.2017.02.088.

Full text
APA, Harvard, Vancouver, ISO, and other styles
44

Jun, Sung-Hae. "Collaborative CRM using Statistical Learning Theory and Bayesian Fuzzy Clustering." Communications for Statistical Applications and Methods 11, no. 1 (April 1, 2004): 197–211. http://dx.doi.org/10.5351/ckss.2004.11.1.197.

Full text
APA, Harvard, Vancouver, ISO, and other styles
45

Pociecha, Józef. "The paradigm of statistical inference and the paradigm of statistical learning." Przegląd Statystyczny 68, no. 1 (August 24, 2021): 1–16. http://dx.doi.org/10.5604/01.3001.0015.0375.

Full text
Abstract:
The starting point for the presentation of the similarities and differences between the principles of conducting statistical research according to the rules of both statistical inference and statistical learning is the paradigm theory, formulated by Thomas Kuhn. In the first section of this paper, the essential features of the statistical inference paradigm are characterised, with particular attention devoted to its limitations in contemporary statistical research. Subsequently, the article presents the challenges faced by this research jointly with the expanding opportunities for their effective reduction. The essence of learning from data is discussed and the principles of statistical learning are defined. Moreover, significant features of the statistical learning paradigm are formulated in the context of the differences between the statistical inference paradigm and the statistical learning paradigm. It is emphasised that the statistical learning paradigm, as the more universal one of the two discussed, broadens the possibilities of conducting statistical research, especially in socio-economic sciences.
APA, Harvard, Vancouver, ISO, and other styles
46

Alnuaimi, Amer F. A. H., and Tasnim H. K. Albaldawi. "Concepts of statistical learning and classification in machine learning: An overview." BIO Web of Conferences 97 (2024): 00129. http://dx.doi.org/10.1051/bioconf/20249700129.

Full text
Abstract:
Statistical learning theory serves as the foundational bedrock of Machine learning (ML), which in turn represents the backbone of artificial intelligence, ushering in innovative solutions for real-world challenges. Its origins can be linked to the point where statistics and the field of computing meet, evolving into a distinct scientific discipline. Machine learning can be distinguished by its fundamental branches, encompassing supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Within this tapestry, supervised learning takes center stage, divided in two fundamental forms: classification and regression. Regression is tailored for continuous outcomes, while classification specializes in categorical outcomes, with the overarching goal of supervised learning being to enhance models capable of predicting class labels based on input features. This review endeavors to furnish a concise, yet insightful reference manual on machine learning, intertwined with the tapestry of statistical learning theory (SLT), elucidating their symbiotic relationship. It demystifies the foundational concepts of classification, shedding light on the overarching principles that govern it. This panoramic view aims to offer a holistic perspective on classification, serving as a valuable resource for researchers, practitioners, and enthusiasts entering the domains of machine learning, artificial intelligence and statistics, by introducing concepts, methods and differences that lead to enhancing their understanding of classification methods.
APA, Harvard, Vancouver, ISO, and other styles
47

White, Halbert. "Learning in Artificial Neural Networks: A Statistical Perspective." Neural Computation 1, no. 4 (December 1989): 425–64. http://dx.doi.org/10.1162/neco.1989.1.4.425.

Full text
Abstract:
The premise of this article is that learning procedures used to train artificial neural networks are inherently statistical techniques. It follows that statistical theory can provide considerable insight into the properties, advantages, and disadvantages of different network learning methods. We review concepts and analytical results from the literatures of mathematical statistics, econometrics, systems identification, and optimization theory relevant to the analysis of learning in artificial neural networks. Because of the considerable variety of available learning procedures and necessary limitations of space, we cannot provide a comprehensive treatment. Our focus is primarily on learning procedures for feedforward networks. However, many of the concepts and issues arising in this framework are also quite broadly relevant to other network learning paradigms. In addition to providing useful insights, the material reviewed here suggests some potentially useful new training methods for artificial neural networks.
APA, Harvard, Vancouver, ISO, and other styles
48

Ikeda, Kazushi. "An Asymptotic Statistical Theory of Polynomial Kernel Methods." Neural Computation 16, no. 8 (August 1, 2004): 1705–19. http://dx.doi.org/10.1162/089976604774201659.

Full text
Abstract:
The generalization properties of learning classifiers with a polynomial kernel function are examined. In kernel methods, input vectors are mapped into a high-dimensional feature space where the mapped vectors are linearly separated. It is well-known that a linear dichotomy has an average generalization error or a learning curve proportional to the dimension of the input space and inversely proportional to the number of given examples in the asymptotic limit. However, it does not hold in the case of kernel methods since the feature vectors lie on a submanifold in the feature space, called the input surface. In this letter, we discuss how the asymptotic average generalization error depends on the relationship between the input surface and the true separating hyperplane in the feature space where the essential dimension of the true separating polynomial, named the class, is important. We show its upper bounds in several cases and confirm these using computer simulations.
APA, Harvard, Vancouver, ISO, and other styles
49

Bartlett, Peter L., Andrea Montanari, and Alexander Rakhlin. "Deep learning: a statistical viewpoint." Acta Numerica 30 (May 2021): 87–201. http://dx.doi.org/10.1017/s0962492921000027.

Full text
Abstract:
The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal solutions to non-convex optimization problems, and despite giving a near-perfect fit to training data without any explicit effort to control model complexity, these methods exhibit excellent predictive accuracy. We conjecture that specific principles underlie these phenomena: that overparametrization allows gradient methods to find interpolating solutions, that these methods implicitly impose regularization, and that overparametrization leads to benign overfitting, that is, accurate predictions despite overfitting training data. In this article, we survey recent progress in statistical learning theory that provides examples illustrating these principles in simpler settings. We first review classical uniform convergence results and why they fall short of explaining aspects of the behaviour of deep learning methods. We give examples of implicit regularization in simple settings, where gradient methods lead to minimal norm functions that perfectly fit the training data. Then we review prediction methods that exhibit benign overfitting, focusing on regression problems with quadratic loss. For these methods, we can decompose the prediction rule into a simple component that is useful for prediction and a spiky component that is useful for overfitting but, in a favourable setting, does not harm prediction accuracy. We focus specifically on the linear regime for neural networks, where the network can be approximated by a linear model. In this regime, we demonstrate the success of gradient flow, and we consider benign overfitting with two-layer networks, giving an exact asymptotic analysis that precisely demonstrates the impact of overparametrization. We conclude by highlighting the key challenges that arise in extending these insights to realistic deep learning settings.
APA, Harvard, Vancouver, ISO, and other styles
50

Machado, Liliane S., Ronei M. Moraes, and Elaine AMG Soares. "Learning by Experimentation: The Calculatora Estatística Visual." International Journal of Online and Biomedical Engineering (iJOE) 9, S8 (December 4, 2013): 50. http://dx.doi.org/10.3991/ijoe.v9is8.3382.

Full text
Abstract:
Learning from experimentation is the basis of the pedagogical theory called Constructivism. The system Calculadora Estatística is a Web-based tool to reinforce learning of statistical techniques, developed by the application of that theory. From a study about human-computer interaction, its newest version, the Calculadora Estatística Visual, was designed with visual programming features to provide an iconic and flowchart-based interface that allow users visualizing the steps necessary to perform a statistical analysis. It is composed by an interface that works on a statistical package to check users requests in order to guarantee the correctness of the statistical operations sequence.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the bibliographies on the topic 'Statistical learning theory' for other source types:
Dissertations / Theses Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography