Robust trainability of single neurons

DOI10.1006/jcss.1995.1011zbMath0939.68771OpenAlexW2041615247MaRDI QIDQ1892210

Klaus-Uwe Höffgen, Kevin S. Van Horn, Hans Ulrich Simon

Publication date: 4 July 2000

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.1995.1011

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Apportioned margin approach for cost sensitive large margin classifiers, Some connections between learning and optimization, Neural networks with linear threshold activations: structure and algorithms, Regularizing conjunctive features for classification, Self-improved gaps almost everywhere for the agnostic approximation of monomials, Discriminative Reranking for Natural Language Parsing, Complexity in the case against accuracy estimation, On the difficulty of approximately maximizing agreements., Set-Valued Support Vector Machine with Bounded Error Rates, Sparse weighted voting classifier selection and its linear programming relaxations, Fast learning of relational kernels, Boosting Method for Local Learning in Statistical Pattern Recognition, Loading Deep Networks Is Hard: The Pyramidal Case, Polynomially bounded minimization problems which are hard to approximate, Classification Based on the Support Vector Machine, Regression Depth, and Discriminant Analysis, Computational limitations on training sigmoid neural networks, Measuring overlap in binary regression., Training a Single Sigmoidal Neuron Is Hard, Maximizing agreements with one-sided error with applications to heuristic learning, A local Vapnik-Chervonenkis complexity, Maximizing agreements with one-sided error with applications to heuristic learning, On the Nonlearnability of a Single Spiking Neuron, On the approximability of minimizing nonzero variables or unsatisfied relations in linear systems, On the complexity of learning for spiking neurons with temporal coding., On approximate learning by multi-layered feedforward circuits, Comparison between various regression depth methods and the support vector machine to approximate the minimum number of misclassifications, Hardness results for neural network approximation problems, Maximizing agreements and coagnostic learning