Similar Classifiers and VC Error Bounds

We improve error bounds based on VC analysis for classes with sets of similar classifiers. We apply the new error bounds to separating planes and artificial neural networks.

[1]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[2]  Nils J. Nilsson,et al.  Learning Machines: Foundations of Trainable Pattern-Classifying Systems , 1965 .

[3]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[4]  David G. Stork,et al.  Pattern Classiication and Scene Analysis 2nd Ed. Part 1: Pattern Classiication , 1999 .

[5]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[6]  Zehra Cataltepe,et al.  A new error bound for the classifier chosen by early stopping , 1997, 1997 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, PACRIM. 10 Years Networking the Pacific Rim, 1987-1997.

[7]  Yaser S. Abu-Mostafa,et al.  The Vapnik-Chervonenkis Dimension: Information versus Complexity in Learning , 1989, Neural Computation.

[8]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[9]  J. Orbach.  Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms. , 1962 .

[10]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

[11]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[12]  Eduardo D. Sontag,et al.  Neural Networks with Quadratic VC Dimension , 1995, J. Comput. Syst. Sci..