Vera Kurková

Neural Networks, August, 2023

2021

Translation-Invariant Kernels for Multivariable Approximation.

[BibT_eX]

[DOI]

David Coufal

IEEE Trans. Neural Networks Learn. Syst., 2021

Correlations of random classifiers on large data sets.

[BibT_eX]

[DOI]

Soft Comput., 2021

2020

Brain-inspired computing and machine learning.

[BibT_eX]

[DOI]

Lazaros S. Iliadis

Barbara Hammer

Neural Comput. Appl., 2020

Approximative compactness of linear combinations of characteristic functions.

[BibT_eX]

[DOI]

J. Approx. Theory, 2020

2019

Classification by Sparse Neural Networks.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2019

Limitations of shallow networks representing finite mappings.

[BibT_eX]

[DOI]

Neural Comput. Appl., 2019

Probabilistic Bounds for Binary Classification of Large Data Sets.

[BibT_eX]

[DOI]

Proceedings of the Recent Advances in Big Data and Deep Learning, 2019

Limitations of Shallow Networks.

[BibT_eX]

[DOI]

Proceedings of the Recent Trends in Learning From Data, 2019

Probabilistic Bounds for Approximation by Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2019: Theoretical Neural Computation, 2019

2018

Constructive lower bounds on model complexity of shallow perceptron networks.

[BibT_eX]

[DOI]

Neural Comput. Appl., 2018

Probabilistic Bounds on Complexity of Networks Computing Binary Classification Tasks.

[BibT_eX]

[DOI]

Proceedings of the 18th Conference Information Technologies, 2018

Sparsity and Complexity of Networks Computing Highly-Varying Functions.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2018, 2018

2017

Probabilistic lower bounds for approximation by shallow perceptron networks.

[BibT_eX]

[DOI]

Neural Networks, 2017

Bounds on Sparsity of One-Hidden-Layer Perceptron Networks.

[BibT_eX]

[DOI]

Proceedings of the 17th Conference on Information Technologies, 2017

Sparsity of Shallow Networks Representing Finite Mappings.

[BibT_eX]

[DOI]

Proceedings of the Engineering Applications of Neural Networks, 2017

2016

Model complexities of shallow networks representing highly varying functions.

[BibT_eX]

[DOI]

Neurocomputing, 2016

Multivariable Approximation by Convolutional Kernel Networks.

[BibT_eX]

[DOI]

Proceedings of the 16th ITAT Conference Information Technologies, 2016

Lower Bounds on Complexity of Shallow Perceptron Networks.

[BibT_eX]

[DOI]

Proceedings of the Engineering Applications of Neural Networks, 2016

2015

Limitations of One-Hidden-Layer Perceptron Networks.

[BibT_eX]

[DOI]

Proceedings of the Proceedings ITAT 2015: Information Technologies, 2015

Complexity of Shallow Networks Representing Finite Mappings.

[BibT_eX]

[DOI]

Proceedings of the Artificial Intelligence and Soft Computing, 2015

2014

Comparing fixed and variable-width Gaussian networks.

[BibT_eX]

[DOI]

Neural Networks, 2014

Complexity of Shallow Networks Representing Functions with Large Variations.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2014, 2014

Representations of Highly-Varying Functions by One-Hidden-Layer Networks.

[BibT_eX]

[DOI]

Proceedings of the Artificial Intelligence and Soft Computing, 2014

2013

Approximating Multivariable Functions by Feedforward Neural Nets.

[BibT_eX]

[DOI]

Proceedings of the Handbook on Neural Information Processing, 2013

Can Two Hidden Layers Make a Difference?

[BibT_eX]

[DOI]

Proceedings of the Adaptive and Natural Computing Algorithms, 2013

2012

Model Complexity of Neural Networks in High-Dimensional Approximation.

[BibT_eX]

[DOI]

Proceedings of the Recent Advances in Intelligent Engineering Systems, 2012

Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2012

Complexity estimates based on integral transforms induced by computational units.

[BibT_eX]

[DOI]

Neural Networks, 2012

Guest editorial: Adaptive and natural computing algorithms.

[BibT_eX]

[DOI]

Neurocomputing, 2012

Accuracy of approximations of solutions to Fredholm equations by kernel methods.

[BibT_eX]

[DOI]

Appl. Math. Comput., 2012

Surrogate solutions of Fredholm equations by feedforward networks.

[BibT_eX]

[DOI]

Proceedings of the Conference on Theory and Practice of Information Technologies, 2012

Surrogate Modelling of Solutions of Integral Equations by Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Artificial Intelligence Applications and Innovations, 2012

Some Comparisons of Networks with Radial and Kernel Units.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2012, 2012

2011

Can dictionary-based computational models outperform the best linear ones?

[BibT_eX]

[DOI]

Neural Networks, 2011

Some comparisons of complexity in dictionary-based and linear computational models.

[BibT_eX]

[DOI]

Neural Networks, 2011

Kernel Networks with Fixed and Variable Widths.

[BibT_eX]

[DOI]

Proceedings of the Adaptive and Natural Computing Algorithms, 2011

Bounds for Approximate Solutions of Fredholm Integral Equations Using Kernel Networks.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2011, 2011

2010

Editorial.

[BibT_eX]

[DOI]

Roman Neruda

Jan Koutník

Neural Networks, 2010

Learning from Data as an Optimization and Inverse Problem.

[BibT_eX]

[DOI]

Proceedings of the Computational Intelligence, 2010

Inverse Problems in Learning from Data.

[BibT_eX]

Proceedings of the ICFC-ICNC 2010, 2010

Some Comparisons of Model Complexity in Linear and Neural-Network Approximation.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks - ICANN 2010, 2010

2009

Estimates of Model Complexity in Neural-Network Learning.

[BibT_eX]

[DOI]

Proceedings of the Innovations in Neural Information Paradigms and Applications, 2009

An Integral Upper Bound for Neural Network Approximation.

[BibT_eX]

[DOI]

Neural Comput., 2009

Complexity of Gaussian-radial-basis networks approximating smooth functions.

[BibT_eX]

[DOI]

J. Complex., 2009

On Tractability of Neural-Network Approximation.

[BibT_eX]

[DOI]

Proceedings of the Adaptive and Natural Computing Algorithms, 9th International Conference, 2009

Model Complexity of Neural Networks and Integral Transforms.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks, 2009

2008

Geometric Upper Bounds on Rates of Variable-Basis Approximation.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2008

Minimization of Error Functionals over Perceptron Networks.

[BibT_eX]

[DOI]

Neural Comput., 2008

Approximate Minimization of the Regularized Expected Error over Kernel Models.

[BibT_eX]

[DOI]

Math. Oper. Res., 2008

Geometric Rates of Approximation by Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the SOFSEM 2008: Theory and Practice of Computer Science, 2008

Estimates of Network Complexity and Integral Representations.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks, 2008

2007

Generalization in Learning from Examples.

[BibT_eX]

[DOI]

Proceedings of the Challenges for Computational Intelligence, 2007

A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves.

[BibT_eX]

[DOI]

J. Approx. Theory, 2007

Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets.

[BibT_eX]

[DOI]

Discret. Appl. Math., 2007

Estimates of Data Complexity in Neural-Network Learning.

[BibT_eX]

[DOI]

Proceedings of the SOFSEM 2007: Theory and Practice of Computer Science, 2007

Estimates of Approximation Rates by Gaussian Radial-Basis Functions.

[BibT_eX]

[DOI]

Proceedings of the Adaptive and Natural Computing Algorithms, 8th International Conference, 2007

2005

Error Estimates for Approximate Optimization by the Extended Ritz Method.

[BibT_eX]

[DOI]

SIAM J. Optim., 2005

Rates of Minimization of Error Functionals over Boolean Variable-Basis Functions.

[BibT_eX]

[DOI]

J. Math. Model. Algorithms, 2005

Learning with generalization capability by kernel methods of bounded complexity.

[BibT_eX]

[DOI]

J. Complex., 2005

Neural Network Learning as an Inverse Problem.

[BibT_eX]

[DOI]

Log. J. IGPL, 2005

2004

Minimization of Error Functionals over Variable-Basis Functions.

[BibT_eX]

[DOI]

SIAM J. Optim., 2004

2003

Best approximation by linear combinations of characteristic functions of half-spaces.

[BibT_eX]

[DOI]

J. Approx. Theory, 2003

Neural network learning as approximate optimization.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Nets and Genetic Algorithms, 2003

2002

Comparison of worst case errors in linear and neural network approximation.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2002

2001

Bounds on rates of variable-basis and neural-network approximation.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2001

Continuity of Approximation by Neural Networks in Lp Spaces.

[BibT_eX]

[DOI]

Ann. Oper. Res., 2001

Tight Bounds on Rates of Neural-Network Approximation.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks, 2001

2000

Best approximation by Heaviside perceptron networks.

[BibT_eX]

[DOI]

Neural Networks, 2000

Comparison of Rates of Linear and Neural Network Approximation.

[BibT_eX]

[DOI]

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000

1999

Approximation by neural networks is not continuous.

[BibT_eX]

[DOI]

Neurocomputing, 1999

1998

Representations and rates of approximation of real-valued Boolean functions by neural networks.

[BibT_eX]

[DOI]

Petr Savický

Neural Networks, 1998

Approximation of Functions by Neural Networks.

[BibT_eX]

Proceedings of the International ICSC / IFAC Symposium on Neural Computation (NC 1998), 1998

1997

Estimates of the Number of Hidden Units and Variation with Respect to Half-Spaces.

[BibT_eX]

[DOI]

Vladik Kreinovich

Neural Networks, 1997

Upper Bounds on the Approximation Rates of Real-valued Boolean Functions by Neural Networks.

[BibT_eX]

[DOI]

Petr Savický

Proceedings of the International Conference on Artificial Neural Nets and Genetic Algorithms, 1997

1996

A geometric method to obtain error-correcting classification by neural networks with fewer hidden units.

[BibT_eX]

[DOI]

Proceedings of International Conference on Neural Networks (ICNN'96), 1996

Rates of approximation of real-valued boolean functions by neural networks.

[BibT_eX]

[DOI]

Proceedings of the 4th European Symposium on Artificial Neural Networks, 1996

1995

Approximation of functions by perceptron networks with bounded number of hidden units.

[BibT_eX]

[DOI]

Neural Networks, 1995

Approximation of functions by Gaussian RBF networks with bouded number of hidden units.

[BibT_eX]

[DOI]

Proceedings of the 3rd European Symposium on Artificial Neural Networks, 1995

1994

Uniqueness of network parametrization and faster learning.

[BibT_eX]

[DOI]

Vladik Kreinovich

Ongard Sirisaengtaksin

Neural Parallel Sci. Comput., 1994

Functionally Equivalent Feedforward Neural Networks.

[BibT_eX]

[DOI]

Neural Comput., 1994

Approximation of continuous functions by RBF and KBF networks.

[BibT_eX]

[DOI]

Proceedings of the 2nd European Symposium on Artificial Neural Networks, 1994

1992

Kolmogorov's theorem and multilayer neural networks.

[BibT_eX]

[DOI]

Neural Networks, 1992

Universal Approximation Using Feedforward Neural Networks with Gaussian Bar Units.

[BibT_eX]

Proceedings of the 10th European Conference on Artificial Intelligence, 1992

1991

Kolmogorov's Theorem Is Relevant.

[BibT_eX]

[DOI]