Institute of Computer Science of the CAS, v. v. i.

0518921 - ÚI 2020 CZ eng A - Abstract
Coufal, David
Generative Adversial Networks. A 2019 Review.
Proceedings of the 22nd Czech-Japan Seminar on Data Analysis and Decision Making (CJS’19). Praha: MatfyzPress, 2019 - (Inuiguchi, M.; Jiroušek, R.; Kratochvíl, V.). s. 25-27. ISBN 978-80-7378-400-3.
[CJS 2019. Czech-Japan Seminar on Data Analysis and Decision Making /22./. 25.09.2019-28.09.2019, Nový Světnov]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
http://cjs.utia.cas.cz/proceedings.pdf
Permanent link: http://hdl.handle.net/11104/0303927

Inst. Repository

0494463 - ÚI 2019 RIV CH eng C - Proceedings Paper (International conf.)
Coufal, David
Superkernels for RBF Networks Initialization (Short Paper).
Artificial Neural Networks and Machine Learning – ICANN 2018. Proceedings, Part II. Cham: Springer, 2018 - (Kůrková, V.; Manolopoulos, Y.; Hammer, B.; Iliadis, L.; Maglogiannis, I.), s. 621-623. Lecture Notes in Computer Science, 11140. ISBN 978-3-030-01420-9.
[ICANN 2018. International Conference on Artificial Neural Networks /27./. Rhodes (GR), 04.10.2018-07.10.2018]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Regression task * Nonparametric estimation * Superkernel
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
https://link.springer.com/content/pdf/bbm%3A978-3-030-01421-6%2F1.pdf
Permanent link: http://hdl.handle.net/11104/0287651

0519375 - ÚI 2021 US eng C - Proceedings Paper (International conf.)
Figueroa–García, J. C. - Orjuela–Caňon, A. D. - Neruda, Roman
On the boundaries of the centroid of a class of fuzzy numbers.
2019 IEEE Latin American Conference on Computational Intelligence. IEEE, 2020, s. 183-187.
[LA-CCI 2019: IEEE Latin American Conference on Computational Intelligence /6./. Guayaquil (EC), 11.11.2019-15.11.2019]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Fuzzy numbers * Chebyshev integral inequality * centroid
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0304368

0509648 - ÚI 2020 RIV CZ eng C - Proceedings Paper (International conf.)
Kalina, Jan - Vidnerová, Petra
Implicitly weighted robust estimation of quantiles in linear regression.
Conference Proceedings. 37th International Conference on Mathematical Methods in Economics 2019. České Budějovice: University of South Bohemia in České Budějovice, Faculty of Economics, 2019 - (Houda, M.; Remeš, R.), s. 25-30. ISBN 978-80-7394-760-6.
[MME 2019: International Conference on Mathematical Methods in Economics /37./. České Budějovice (CZ), 11.09.2019-13.09.2019]
R&D Projects: GA ČR(CZ) GA19-05704S; GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: regression quantiles * robust regression * outliers * leverage points
Subject RIV: BB - Applied Statistics, Operational Research
Obor OECD: Statistics and probability
https://mme2019.ef.jcu.cz/files/conference_proceedings.pdf
Permanent link: http://hdl.handle.net/11104/0300322

0522365 - ÚI 2021 C - Proceedings Paper (International conf.)
Kalina, Jan - Vidnerová, Petra
Regression Neural Networks with a Highly Robust Loss Function.
Amistat 2019. Springer, 2020.
[AMISTAT 2019: Analytical Methods in Statistics. Liberec (CZ), 16.09.2019-19.09.2019]
R&D Projects: GA ČR(CZ) GA19-05704S; GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0306871

Inst. Repository

0506360 - ÚI 2020 RIV CH eng C - Proceedings Paper (International conf.)
Kalina, Jan - Vidnerová, Petra
Robust Training of Radial Basis Function Neural Networks.
Artificial Intelligence and Soft Computing. Proceedings, Part I. Cham: Springer, 2019 - (Rutkowski, L.; Scherer, R.; Korytkowski, M.; Pedrycz, W.; Tadeusiewicz, R.; Zurada, J.), s. 113-124. Lecture Notes in Computer Science, 11508. ISBN 978-3-030-20911-7. ISSN 0302-9743.
[ICAISC 2019: International Conference on Artificial Intelligence and Soft Computing /18./. Zakopane (PL), 16.06.2019-20.06.2019]
R&D Projects: GA ČR(CZ) GA19-05704S; GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Machine learning * Outliers * Robustness * Subset selection * Anomaly detection
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0297617

0500123 - ÚI 2019 CZ eng V - Research Report
Křen, Tomáš
Transforming hierarchical images to program expressions using deep networks.
Prague: ICS CAS, 2018. 12 s. Technical report, V-1263.
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: deep networks * automatic program synthesis * image processing
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0292265

Inst. Repository

0485611 - ÚI 2020 RIV US eng J - Journal Article
Kůrková, Věra - Sanguineti, M.
Classification by Sparse Neural Networks.
IEEE Transactions on Neural Networks and Learning Systems. Roč. 30, č. 9 (2019), s. 2746-2754. ISSN 2162-237X
R&D Projects: GA ČR GA15-18108S; GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Binary classification * Chernoff–Hoeffding bound * dictionaries of computational units * feedforward networks * measures of sparsity
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 11.683, year: 2018
http://dx.doi.org/10.1109/TNNLS.2018.2888517
Permanent link: http://hdl.handle.net/11104/0280566

0485562 - ÚI 2021 RIV CH eng M - Monograph chapter
Kůrková, Věra - Kainen, P.C.
Integral Transforms Induced by Heaviside Perceptrons.
Beyond Traditional Probabilistic Data Processing Techniques: Interval, Fuzzy, etc. Methods and Their Applications. Cham: Springer, 2020 - (Kosheleva, O.; Shary, S.; Xiang, G.; Zapatrin, R.), s. 631-649. Studies in Computational Intelligence, 835. ISBN 978-3-030-31040-0
R&D Projects: GA ČR GA15-18108S; GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0280525

SCOPUS
DOI

0485613 - ÚI 2020 RIV US eng J - Journal Article
Kůrková, Věra
Limitations of Shallow Networks Representing Finite Mappings.
Neural Computing & Applications. Roč. 31, č. 6 (2019), s. 1783-1792. ISSN 0941-0643
R&D Projects: GA ČR GA15-18108S; GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: shallow and deep networks * sparsity * variational norms * functions on large finite domains * finite dictionaries of computational units * pseudo-noise sequences * perceptron networks
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 4.664, year: 2018
http://dx.doi.org/10.1007/s00521-018-3680-1
Kůrková, Věra
Permanent link: http://hdl.handle.net/11104/0280569

0503127 - ÚI 2021 RIV CH eng C - Proceedings Paper (International conf.)
Kůrková, Věra - Sanguineti, M.
Probabilistic Bounds for Binary Classification of Large Data Sets.
Recent Advances in Big Data and Deep Learning. Cham: Springer, 2020 - (Oneto, L.; Navarin, N.; Sperduti, A.; Anguita, D.), s. 309-319. Proceedings of the International Neural Networks Society, 1. ISBN 978-3-030-16840-7. ISSN 2661-8141.
[INNSBDDL 2019: INNS Big Data and Deep Learning /4./. Sestri Levante (IT), 16.04.2019-18.04.2019]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Binary classification * Approximation by feedforward networks * Concentration of measure * Azuma-Hoeffding inequality
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Sanguineti, M.
Permanent link: http://hdl.handle.net/11104/0294978

0493926 - ÚI 2019 RIV DE eng C - Proceedings Paper (International conf.)
Kůrková, Věra - Sanguineti, M.
Probabilistic Bounds on Complexity of Networks Computing Binary Classification Tasks.
ITAT 2018: Information Technologies – Applications and Theory. Proceedings of the 18th conference ITAT 2018. Aachen: Technical University & CreateSpace Independent Publishing Platform, 2018 - (Krajči, S.), s. 86-91. CEUR Workshop Proceedings, V-2203. ISSN 1613-0073.
[ITAT 2018. Conference on Information Technologies – Applications and Theory /18./. Plejsy (SK), 21.09.2018-25.09.2018]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: feedforward networks * binary classification * measures of sparsity * probabilistic bounds * dictionaries of computational units
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://ceur-ws.org/Vol-2203/86.pdf
Permanent link: http://hdl.handle.net/11104/0287193

0523714 - ÚI 2021 IT eng A - Abstract
Kůrková, Věra - Sanguineti, M.
Probabilistic Tools for Optimization of Classifiers on Large Data Sets.
ODS 2019. Book of Abstracts. Genova: AIRO - Italian Operations Research Society, 2019. s. 75-75.
[ODS 2019: International Conference on Optimization and Decision Science /49./. 04.09.2019-07.09.2019, Genova]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Classification * Optimization of Computational Models * Concentration of Measures * Azuma-Hoeffding Inequality
Permanent link: http://hdl.handle.net/11104/0308024

Inst. Repository

0510711 - ÚI 2020 ES eng A - Abstract
Kůrková, Věra
Some Implications of Interval Approach to Dimension for Network Complexity.
ESCIM 2019. Book of Abstracts. Cádiu: University of Cádiz, 2019 - (Kóczy, L.; Medina, J.). s. 59-60. ISBN 978-84-09-14600-0.
[ESCIM 2019: European Symposium on Computational Intelligence and Mathematics /11./. 02.10.2019-05.10.2019, Toledo]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: quasiorthogonal dimension * sparsity of feedforward networks * high-dimensional geometry * concentration of measure * covering numbers
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0301114

0503896 - ÚI 2020 RIV NL eng J - Journal Article
Kůrková, Věra
Some insights from high-dimensional spheres: Comment on 'The unreasonable effectiveness of small neural ensembles in high-dimensional brain' by Alexander N. Gorban et al.
Physics of Life Reviews. Roč. 29, July 2019 (2019), s. 98-100. ISSN 1571-0645
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: neural networks * high-dimensional geometry * concentration of measure * commentary
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 11.045, year: 2018
Permanent link: http://hdl.handle.net/11104/0295662

0493825 - ÚI 2019 RIV CH eng C - Proceedings Paper (International conf.)
Kůrková, Věra
Sparsity and Complexity of Networks Computing Highly-Varying Functions.
Artificial Neural Networks and Machine Learning – ICANN 2018. Proceedings, Part III. Cham: Springer, 2018 - (Kůrková, V.; Manolopoulos, Y.; Hammer, B.; Iliadis, L.; Maglogiannis, I.), s. 534-543. Lecture Notes in Computer Science, 11141. ISBN 978-3-030-01423-0. ISSN 0302-9743.
[ICANN 2018. International Conference on Artificial Neural Networks /27./. Rhodes (GR), 04.10.2018-07.10.2018]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Shallow and deep networks * Model complexity * Sparsity * Highly-varying functions * Covering numbers * Dictionaries of computational units * Perceptrons
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
https://www.springer.com/us/book/9783030014230
Kůrková, Věra
Permanent link: http://hdl.handle.net/11104/0287121

0519370 - ÚI 2020 RIV US eng C - Proceedings Paper (International conf.)
Pešková, K. - Neruda, Roman
Hyperparameters search methods for machine learning linear workflows.
18th IEEE International Conference on Machine Learning and Applications ICMLA 2019. Proceedings. Piscataway: IEEE, 2019, s. 1205-1210. ISBN 978-1-7281-4550-1.
[ICMLA 2019: IEEE International Conference on Machine Learning and Applications /18./. Boca Raton (US), 16.12.2019-19.12.2019]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: hyperparameters optimization * machine learning workflows * data preprocessing
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0304362

0499984 - ÚI 2019 RIV US eng C - Proceedings Paper (International conf.)
Řeháková, L. - Neruda, Roman
Utilization of Genetic Programming to Solve a Simple Task Network Planning Problem.
Proceedings of the 2018 IEEE International Conference on Systems, Man, and Cybernetic. Los Alamitos: IEEE CS, 2018, s. 3660-3666. ISBN 978-1-5386-6650-0. ISSN 2577-1655.
[SMC 2018. International Conference on Systems, Man and Cybernetics. Miyazaki (JP), 07.10.2018-10.10.2018]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: Planning * Task analysis * Genetic programming * Standards * Software algorithms * Automobiles
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0292162

0494108 - ÚI 2019 RIV DE eng C - Proceedings Paper (International conf.)
Vidnerová, Petra - Neruda, Roman
Asynchronous Evolution of Convolutional Networks.
ITAT 2018: Information Technologies – Applications and Theory. Proceedings of the 18th conference ITAT 2018. Aachen: Technical University & CreateSpace Independent Publishing Platform, 2018 - (Krajči, S.), s. 80-85. CEUR Workshop Proceedings, V-2203. ISSN 1613-0073.
[ITAT 2018. Conference on Information Technologies – Applications and Theory /18./. Plejsy (SK), 21.09.2018-25.09.2018]
R&D Projects: GA ČR(CZ) GA18-23827S
GA MŠk(CZ) LM2015042
Institutional Support: RVO:67985807
Keywords: convolutional neural networks * evolutioanary algorithms * asynchronous evolution
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://ceur-ws.org/Vol-2203/80.pdf
Vidnerová, Petra
Permanent link: http://hdl.handle.net/11104/0287354

0490841 - ÚI 2019 RIV CH eng C - Proceedings Paper (International conf.)
Vidnerová, Petra - Neruda, Roman
Deep Networks with RBF Layers to Prevent Adversarial Examples.
Artificial Intelligence and Soft Computing. Cham: Springer, 2018 - (Rutkowski, L.; Scherer, R.; Korytkowski, M.; Pedrycz, W.; Tadeusiewicz, R.; Zurada, J.), s. 257-266. Lecture Notes in Artificial Intelligence, 10841. ISBN 978-3-319-91252-3. ISSN 0302-9743.
[ICAISC 2018. International Conference on Artificial Intelligence and Soft Computing /17./. Zakopane (PL), 03.06.2018-07.06.2018]
R&D Projects: GA ČR(CZ) GA18-23827S
GA MŠk(CZ) LM2015042
Institutional Support: RVO:67985807
Keywords: Adversarial examples * RBF networks * Deep neural networks * Convolutional networks
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0284980

Citation, Review▾

0505494 - ÚI 2020 RIV CZ eng L4 - Software
Vidnerová, Petra
RBF-Keras: an RBF Layer for Keras Library.
Interní kód: RBF-Keras ; 2019
Technical Parameters: Uživatel potřebuje nainstalovanou knihovnu Keras (http://keras.io) a poté je možné vytvářet modely neuronových sítí způsobem obvyklým v této knihovně včetně použití naší RBF vrstvy. Pro nastavení středů si lze vybrat s připravených inicializátorů (náhodný výběr z tréninkové množiny nebo použití KMeans shlukování), případně uživatel může použít vlastní inicializátor.
Ekonomické parametry: RBF-Keras obsahuje implementaci třídy RBFLayer, která je určena k implementaci RBF sítí a hlubokých sítí obsahujících RBF vrstvu v knihovně Keras. Jedná se o rozšíření knihovny Keras, která samotná RBF vrstvu neobsahuje. RBF-Keras usnadňuje realizaci experimentů s modely RBF sítí nebo hlubokých sítí s RBF vrstvou a umožňuje aplikaci těchto modelů.
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: neuronová síť typu RBF * hluboké neuronové sítě * RBF network * deep neural networks * Keras
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
https://github.com/PetraVidnerova/rbf_keras
Permanent link: http://hdl.handle.net/11104/0296977

Result - R&D

0505718 - ÚI (2019) DATA Vědecká data
Vidnerová, Petra
RBF-Keras: RBF vrstva pro knihovnu Keras.

RBF-Keras: RBF vrstva pro knihovnu Keras
[RBF-Keras: an RBF Layer for Keras Library]
Keywords: neuronová síť typu RBF * hluboké neuronové sítě * RBF network * deep neural networks * Keras
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Permanent link: http://hdl.handle.net/11104/0297129

0485639 - ÚI 2021 GB eng J - Journal Article
Vidnerová, Petra - Neruda, Roman
Vulnerability of classifiers to evolutionary generated adversarial examples.
Neural Networks. Accepted 16 April 2020 (2020). ISSN 0893-6080
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional Support: RVO:67985807
Keywords: supervised learning * neural networks * kernel methods * genetic algorithms * adversarial examples
Subject RIV: IN - Informatics, Computer Science
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 5.785, year: 2018
Permanent link: http://hdl.handle.net/11104/0280599

DOI