The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
From MaRDI portal
Publication:4400270
DOI10.1109/18.661502zbMath0901.68177OpenAlexW2099579348MaRDI QIDQ4400270
Publication date: 2 August 1998
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://eprints.qut.edu.au/43927/1/43927.pdf
Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)
Related Items
Bounding the generalization error of convex combinations of classifiers: Balancing the dimensionality and the margins., Generalization error of combined classifiers., Deep learning: a statistical viewpoint, Tikhonov, Ivanov and Morozov regularization for support vector machine learning, ON DETERMINISTIC FINITE STATE MACHINES IN RANDOM ENVIRONMENTS, Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets, Robust Formulations for Training Multilayer Perceptrons, Terminated Ramp--Support Vector machines: A nonparametric data dependent kernel, Benign overfitting in linear regression, Ten More Years of Error Rate Research, One-class classification with extreme learning machine, \(L_{p}\)-norm Sauer-Shelah lemma for margin multi-category classifiers, On the generalization error of fixed combinations of classifiers, The learning rate of \(l_2\)-coefficient regularized classification with strong loss, Approximation by multivariate Bernstein-Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels, Extreme learning machine for a new hybrid morphological/linear perceptron, Relation between weight size and degree of over-fitting in neural network regression, Approximation bounds for norm constrained neural networks with applications to regression and GANs, Two fast and accurate heuristic RBF learning rules for data classification, Statistical guarantees for regularized neural networks, Sequence classification via large margin hidden Markov models, Quantitative convergence analysis of kernel based large-margin unified machines, Tests and classification methods in adaptive designs with applications, Robust cutpoints in the logical analysis of numerical data, Minimax rates for conditional density estimation via empirical entropy, Statistical performance of support vector machines, Robustness and generalization, Learning half-spaces on general infinite spaces equipped with a distance function, Unnamed Item, Minimizing loss probability bounds for portfolio selection, Learning bounds via sample width for classifiers on finite metric spaces, On the role of norm constraints in portfolio selection, Learning with Convex Loss and Indefinite Kernels, Unified approach to coefficient-based regularized regression, A simpler approach to coefficient regularized support vector machines regression, A hybrid classifier based on boxes and nearest neighbors, Generalization performance of least-square regularized regression algorithm with Markov chain samples, Estimation of the misclassification error for multicategory support vector machine classification, A tight upper bound on the generalization error of feedforward neural networks, Optimal rate of the regularized regression learning algorithm, Sparse Deep Neural Networks Using L1,∞-Weight Normalization, Sample Complexity of Classifiers Taking Values in ℝQ, Application to Multi-Class SVMs, Unnamed Item, Unnamed Item, A probabilistic learning algorithm for robust modeling using neural networks with random weights, Classification with polynomial kernels and \(l^1\)-coefficient regularization, Optimal convergence rate of the universal estimation error, Optimal control of complex systems based on improved dual heuristic dynamic programming algorithm, Learning rates for regularized classifiers using multivariate polynomial kernels, Analysis of a two-layer neural network via displacement convexity, Aspects of discrete mathematics and probability in the theory of machine learning, Logistic classification with varying gaussians, Learning rates for multi-kernel linear programming classifiers, Robust extreme learning machine for modeling with unknown noise, The consistency of multicategory support vector machines, The weight-decay technique in learning from data: an optimization point of view, Analysis of a multi-category classifier, SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming, Classification-based objective functions, Probabilities of discrepancy between minima of cross-validation, Vapnik bounds and true risks, Large margin cost-sensitive learning of conditional random fields, Least Square Regression with lp-Coefficient Regularization, A selective overview of deep learning, Approximating and learning by Lipschitz kernel on the sphere, Comments on: Support vector machines maximizing geometric margins for multi-class classification, Efficient extreme learning machine via very sparse random projection, Multi-category classifiers and sample width, Comment, Boosting the margin: a new explanation for the effectiveness of voting methods, Regularisation of neural networks by enforcing Lipschitz continuity, GENERALIZATION BOUNDS OF REGULARIZATION ALGORITHMS DERIVED SIMULTANEOUSLY THROUGH HYPOTHESIS SPACE COMPLEXITY, ALGORITHMIC STABILITY AND DATA QUALITY, Analysis of support vector machines regression, The complexity of model classes, and smoothing noisy data, Maximal width learning of binary functions, Nonparametric regression with modified ReLU networks, Evolutionary extreme learning machine, Unnamed Item, Optimal rate for support vector machine regression with Markov chain samples, Measurement error models: from nonparametric methods to deep neural networks, Kernel learning at the first level of inference, Overparameterised adaptive controllers can reduce non-singular costs., Complexities of convex combinations and bounding the generalization error in classification, Backward elimination model construction for regression and classification using leave-one-out criteria, A re-weighting strategy for improving margins
