The Shape of Learning Curves: a Review

E. J. Swift, “Studies in the psychology and physiology of learning,” Am. J. Psychol. , vol. 14, no. 2, pp. 201–251, 1903

1903

Earlier work this paper cites.

O. Lipmann, “Der einfluss der einzelnen wiederholungen auf verschieden starke und verschieden alte associationen,” Z. Psychol. Physiol. Si. , vol. 35, pp. 195–233, 1904

1904

Earlier work this paper cites.

K. W. Spence, “The differential response in animals to stimuli varying within a single dimension.” Psychol. Rev. , vol. 44, no. 5, p. 430, 1937

1937

Earlier work this paper cites.

E. E. Ghiselli, “A comparison of methods of scoring maze and discrimination learning,” J.Gen.Psychol. , vol. 17, no. 1, p. 15, 1937

1937

Earlier work this paper cites.

L. J. Savage, The foundations of statistics . John Wiley, Inc., 1954

1954

Earlier work this paper cites.

A. Ritchie, “Thinking and machines,” Philos. , vol. 32, no. 122, p. 258, 1957

1957

Earlier work this paper cites.

F. Rosenblatt, “The perceptron: a probabilistic model for information storage and organization in the brain.” Psychol. Rev. , vol. 65, no. 6, p. 386, 1958

1958

Earlier work this paper cites.

T. M. Cover, “Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition,” IEEE Trans. Electron. , vol. 14, no. 3, pp. 326–334, 1965

1965

Earlier work this paper cites.

T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. IT , vol. 13, no. 1, pp. 21–27, 1967

1967

Earlier work this paper cites.

I. J. Good, “On the principle of total evidence,” Br. J. Philos. Sci. , vol. 17, no. 4, pp. 319–321, 1967

1967

Earlier work this paper cites.

G. Hughes, “On the mean accuracy of statistical pattern recognizers,” IEEE Trans. IT , vol. 14, no. 1, pp. 55–63, 1968

1968

Earlier work this paper cites.

T. M. Cover, “Rates of convergence for nearest neighbor procedures,” in Hawaii Int. Conf. on Systems Sci. , vol. 415, 1968

1968

Earlier work this paper cites.

S. Raudys, “On the problems of sample size in pattern recognition (in Russian),” in 2nd All-Union Conf. on Stat. Meth. in Contr. Theory . Nauka, 1970

1970

Earlier work this paper cites.

D. Peterson, “Some convergence properties of a nearest neighbor decision rule,” IEEE Trans. IT , vol. 16, no. 1, pp. 26–31, 1970

1970

Earlier work this paper cites.

L. Kanal and B. Chandrasekaran, “On dimensionality and sample size in statistical pattern classification,” Pattern Recognit. , vol. 3, no. 3, pp. 225–234, 1971

1971

Earlier work this paper cites.

D. H. Foley, “Considerations of Sample and Feature Size,” IEEE T. Inform. Theory , vol. 18, no. 5, pp. 618–626, 1972

1972

Earlier work this paper cites.

M. Osborne, “A modification of veto logic for a committee of threshold logic units and the use of 2-class classifiers for function estimation,” Ph.D. dissertation, Oregon State University, 1975

1975

Earlier work this paper cites.

R. Duin, “On the choice of smoothing parameters for parzen estimators of probability density functions,” IEEE T Comput. , vol. 25, no. 11, pp. 1175–1179, 1976

1976

Earlier work this paper cites.

J. M. Van Campenhout, “On the peaking of the hughes mean recognition accuracy: the resolution of an apparent paradox,” IEEE T Syst. Man Cy. , vol. 8, no. 5, pp. 390–395, 1978

1978

Earlier work this paper cites.

A. K. Jain and W. G. Waller, “On the optimal number of features in the classification of multivariate gaussian data,” Pattern Recognit. , vol. 10, no. 5-6, pp. 365–374, 1978

1978

Earlier work this paper cites.

R. P. W. Duin, “On the accuracy of statistical pattern recognizers,” Ph.D. dissertation, Technische Hogeschool Delft, 1978

1978

Earlier work this paper cites.

L. E. Yelle, “The learning curve: Historical review and comprehensive survey,” Decision sciences , vol. 10, no. 2, pp. 302–328, 1979

1979

Earlier work this paper cites.

S. Raudys and V. Pikelis, “On dimensionality, sample size, classification error, and complexity of classification algorithm in pattern recognition,” IEEE Trans Pattern Anal. Mach. Intell. , no. 3, pp. 242–252, 1980

1980

Earlier work this paper cites.

C. A. Michelli and G. Wahba, “Design problems for optimal surface interpolation,” Approx. Theory Appl. , pp. 329–348, 1981

1981

Earlier work this paper cites.

A. Jain and B. Chandrasekaran, “Dimensionality and Sample Size Considerations in Pattern Recognition Practice,” Handbook of Statistics , vol. 2, pp. 835–855, 1982

1982

Earlier work this paper cites.

A. K. Jain and B. Chandrasekaran, “Dimensionality and sample size considerations in pattern recognition practice,” in Handbook of statistics , P. Krishnaiah and L. Kanal, Eds. Elsevier, 1982, vol. 2, ch. 39, pp. 835–855

1982

Earlier work this paper cites.

V. Vapnik, Estimation of Dependences Based on Empirical Data Berlin . Springer, 1982

1982

Earlier work this paper cites.

B. Efron, “Estimating the error rate of a prediction rule: improvement on cross-validation,” JASA , vol. 78, no. 382, p. 316, 1983

1983

Earlier work this paper cites.

A. K. Jain et al. , “Bootstrap techniques for error estimation,” IEEE Trans Pattern Anal. Mach. Intell. , no. 5, pp. 628–633, 1987

1987

Earlier work this paper cites.

S. Patarnello and P. Carnevali, “Learning networks of neurons with boolean logic,” Europhys. Lett. , vol. 4, no. 4, p. 503, 1987

1987

Earlier work this paper cites.

P. Langley, “Machine Learning as an Experimental Science,” Mach. Learn. , vol. 3, no. 1, pp. 5–8, 1988

1988

Earlier work this paper cites.

S. Ahmad and G. Tesauro, “Study of scaling and generalization in neutral networks,” Neural Netw. , vol. 1, no. 1, p. 3, 1988

1988

Earlier work this paper cites.

F. Vallet et al. , “Linear and nonlinear extension of the pseudo-inverse solution for learning boolean functions,” Europhys. Lett. , vol. 9, no. 4, p. 315, 1989

1989

Earlier work this paper cites.

W. L. Buntine, “A critique of the valiant model.” in IJCAI , 1989, pp. 837–842

1989

Earlier work this paper cites.

W. E. Sarrett and M. J. Pazzani, “Average case analysis of empirical and explanation-based learning algorithms,” Dept. of Information & CS, UC Irvine, Tech. Rep. 89-35, 1989

1989

Earlier work this paper cites.

N. Tishby et al. , “Consistent inference of probabilities in layered networks: Predictions and generalization,” in IJCNN , vol. 2, 1989, pp. 403–409

1989

Earlier work this paper cites.

E. Levin et al. , “A statistical approach to learning and generalization in layered neural networks,” COLT , vol. 78, p. 245, 1989

1989

Earlier work this paper cites.

P. R. Graves, “The total evidence theorem for probability kinematics,” Philos. Sci. , vol. 56, no. 2, pp. 317–324, 1989

1989

Earlier work this paper cites.

L. E. Atlas et al. , “Training connectionist networks with queries and selective sampling,” in NeurIPS , 1990, pp. 566–573

1990

Earlier work this paper cites.

H. Sompolinsky et al. , “Learning from examples in large neural networks,” Phys. Rev. Lett. , vol. 65, no. 13, p. 1683, 1990

1990

Earlier work this paper cites.

M. Opper et al. , “On the ability of the optimal perceptron to generalise,” J. Phys. A , vol. 23, no. 11, p. L581, 1990

1990

Earlier work this paper cites.

D. B. Schwartz et al. , “Exhaustive Learning,” Neural Comput. , vol. 2, no. 3, pp. 374–385, 1990

1990

Earlier work this paper cites.

G. Györgyi, “First-order transition to perfect generalization in a neural network with binary synapses,” Phys. Rev. A , vol. 41, no. 12, pp. 7097–7100, 1990

1990

Earlier work this paper cites.

S. Raudys and A. Jain, “Small sample size effects in statistical pattern recognition: recommendations for practitioners,” IEEE Trans Pattern Anal. Mach. Intell. , vol. 13, no. 3, pp. 252–264, 1991

1991

Earlier work this paper cites.

J. W. Shavlik et al. , “Symbolic and neural learning algorithms: An experimental comparison,” Mach. Learn. , vol. 6, no. 2, pp. 111–143, 1991

1991

Earlier work this paper cites.

D. Cohn and G. Tesauro, “Can neural networks do better than the vapnik-chervonenkis bounds?” in NeurIPS , 1991, pp. 911–917

1991

Earlier work this paper cites.

M. Opper and D. Haussler, “Calculation of the learning curve of bayes optimal classification algorithm for learning a perceptron with noise,” in COLT , vol. 91, 1991, pp. 75–87

1991

Earlier work this paper cites.

S. Amari, “Universal property of learning curves under entropy loss,” in IJCNN , vol. 2, 1992, pp. 368–373 vol.2

1992

Earlier work this paper cites.

S.-i. Amari et al. , “Four types of learning curves,” Neural Comput. , vol. 4, no. 4, pp. 605–618, 1992

1992

Earlier work this paper cites.

H. S. Seung et al. , “Statistical mechanics of learning from examples,” Phys. Rev. A , vol. 45, no. 8, p. 6056, 1992

1992

Earlier work this paper cites.

D. Hansel et al. , “Memorization without generalization in a multilayered neural network,” Europhys. Lett. , vol. 20, no. 5, pp. 471–476, 1992

1992

Earlier work this paper cites.

T. L. Watkin et al. , “The statistical mechanics of learning a rule,” Rev. Mod. Phys. , vol. 65, no. 2, p. 499, 1993

1993

Earlier work this paper cites.

D. Haussler and M. Warmuth, “The probably approximately correct (pac) and other learning models,” in Foundations of Knowledge Acquisition . Springer, 1993, pp. 291–312

1993

Earlier work this paper cites.

S.-i. Amari, “A universal theorem on learning curves,” Neural Netw. , vol. 6, no. 2, pp. 161–166, jan 1993

1993

Earlier work this paper cites.

S.-i. Amari and N. Murata, “Statistical Theory of Learning Curves under Entropic Loss Criterion,” Neural Comput. , vol. 5, no. 1, pp. 140–153, 1993

1993

Earlier work this paper cites.

T. L. H. Watkin et al. , “The Statistical Mechanics of Learning a Rule,” Rev. Mod. Phys. , vol. 65, no. 2, pp. 499–556, 1993

1993

Earlier work this paper cites.

K. Kang et al. , “Generalization in a two-layer neural network,” Phys. Rev. E , vol. 48, no. 6, p. 4805, 1993

1993

Earlier work this paper cites.

H. Schwarze and J. A. Hertz, “Statistical Mechanics of Learning in a Large Committee Machine,” NeurIPS , pp. 523–530, 1993

1993

Earlier work this paper cites.

H. Sompolinsky, “Theoretical issues in learning from examples,” in NEC Research Symposium , 1993, pp. 217–237

1993

Earlier work this paper cites.

M. Biehl and A. Mietzner, “Statistical mechanics of unsupervised learning,” Europhys. Lett. , vol. 24, no. 5, p. 421, 1993

1993

Earlier work this paper cites.

C. Cortes et al. , “Learning curves: Asymptotic values and rate of convergence,” in NeurIPS , 1994, pp. 327–334

1994

Earlier work this paper cites.

E. Perez and L. A. Rendell, “Using multidimensional projection to find relations,” in ML Proc. Elsevier, 1995, pp. 447–455

1995

Earlier work this paper cites.

D. Schuurmans, “Characterizing rational versus exponential learning curves,” in EuroCOLT . Springer, 1995, pp. 272–286

1995

Earlier work this paper cites.

K. Ritter et al. , “Multivariate integration and approximation for random fields satisfying sacks-ylvisaker conditions,” Ann. Appl. Prob. , vol. 5, no. 2, pp. 518–540, 1995

1995

Earlier work this paper cites.

M. Opper, “Statistical Mechanics of Learning : Generalization,” The Handbook of Brain Theory and Neural Networks , p. 20, 1995

1995

Earlier work this paper cites.

H. Seung, “Annealed theories of learning,” CTP-PRSRI Joint Workshop on Theoretical Physics. Singapore, World Scientific , 1995

1995

Earlier work this paper cites.

R. P. W. Duin, “Small sample size generalization,” in SCIA . Springer, 1995, pp. 1–8

1995

Earlier work this paper cites.

M. Skurichina and R. P. Duin, “Stabilizing classifiers for very small sample sizes,” in ICPR , vol. 2. IEEE, 1996, pp. 891–896

1996

Earlier work this paper cites.

R. Kohavi, “Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid.” in Kdd , vol. 96, 1996, pp. 202–207

1996

Earlier work this paper cites.

G. H. John and P. Langley, “Static versus dynamic sampling for data mining.” in KDD , vol. 96, 1996, pp. 367–370

1996

Earlier work this paper cites.

L. Devroye et al. , A Probabilistic Theory of Pattern Recognition . New York, NY, USA: Springer, 1996, vol. 31

1996

Cited alongside, same era.

D. Haussler et al. , “Rigorous learning curve bounds from statistical mechanics [longer version],” Mach. Learn. , vol. 25, no. 2-3, pp. 195–236, 1996

1996

Cited alongside, same era.

L. Plaskota, Noisy information and computational complexity . Cambridge University Press, 1996, vol. 95, no. 55

1996

Cited alongside, same era.

K. Ritter, “Almost optimal differentiation using noisy data,” J. of Approx. Theory , vol. 86, no. 3, pp. 293–309, 1996

1996

Cited alongside, same era.

R. P. Duin et al. , “Experiments with a featureless approach to pattern recognition,” Pattern Recognit. Lett. , vol. 18, no. 11-13, pp. 1159–1166, 1997

1997

Cited alongside, same era.

P. D. Grünwald and W. Kotłowski, “Bounds on individual risk for log-loss predictors,” JMLR , vol. 19, pp. 813–816, 2011

2011

Later among the works it cites.

R. O. Duda et al. , Pattern classification . John Wiley & Sons, 2012

2012

Later among the works it cites.

K. P. Murphy, Machine learning: a probabilistic perspective . MIT Press, 2012

2012

Later among the works it cites.

R. L. Figueroa et al. , “Predicting sample size required for classification performance,” BMC Med.Inform.Decis , vol. 12, no. 1, p. 8, 2012

2012

Later among the works it cites.

N. Bertoldi et al. , “Evaluating the learning curve of domain adaptive statistical machine translation systems,” in Workshop on Statistical Machine Translation , 2012, pp. 433–441

2012

Later among the works it cites.