default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDRoman Neruda
Person information
SPARQL queries 
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j9]Juan Carlos Figueroa-García
, Roman Neruda, Germán Jairo Hernández-Pérez:
On cosine fuzzy sets and uncertainty quantification. Eng. Appl. Artif. Intell. 138: 109241 (2024)- [c123]Gabriela Kadlecová, Jovita Lukasik, Martin Pilát, Petra Vidnerová, Mahmoud Safari, Roman Neruda, Frank Hutter:
Surprisingly Strong Performance Prediction with Neural Graph Features. ICML 2024 - [i3]Gabriela Kadlecová, Jovita Lukasik, Martin Pilát, Petra Vidnerová, Mahmoud Safari, Roman Neruda, Frank Hutter:
Surprisingly Strong Performance Prediction with Neural Graph Features. CoRR abs/2404.16551 (2024) - 2023
- [j8]Juan Carlos Figueroa-García, Roman Neruda, Germán Jairo Hernández-Pérez:
A genetic algorithm for multivariate missing data imputation. Inf. Sci. 619: 947-967 (2023) - [c122]Juan Carlos Figueroa García, Roman Neruda, Carlos Franco:
On Truncating Fuzzy Numbers with α-Levels. NAFIPS 2023: 258-267 - 2022
- [c121]Gabriela Suchopárová, Petra Vidnerová, Roman Neruda, Martin Smíd:
Using a Deep Neural Network in a Relative Risk Model to Estimate Vaccination Protection for COVID-19. EANN 2022: 310-320 - [c120]Juan Carlos Figueroa García, Roman Neruda, Yurilev Chalco-Cano:
An Experimental Study on Fuzzy Markov Chains Under Mn Generalized Mean Relation. NAFIPS 2022: 63-72 - [p3]Juan Carlos Figueroa-García, Carlos Franco, Roman Neruda:
An Optimization Model for Location-Allocation of Health Services Under Uncertainty. Computational Intelligence Methodologies Applied to Sustainable Development Goals 2022: 97-108 - 2021
- [c119]Alvaro David Orjuela-Cañón, Juan Carlos Figueroa-García, Roman Neruda:
Automated Machine Learning Strategies to Damage Identification of Neurofibromatosis Mutations. ICMLA 2021: 1341-1344 - [c118]Petra Vidnerová, Roman Neruda, Gabriela Suchopárová, Ludek Berec, Tomás Diviák, Ales Kubena, René Levínský, Josef Slerka, Martin Smíd, Jan Trnka, Vít Tucek, Karel Vrbenský, Milan Zajícek:
Simulation of Non-pharmaceutical Interventions in an Agent based Epidemic Model. ITAT 2021: 263-268 - 2020
- [j7]Petra Vidnerová, Roman Neruda:
Vulnerability of classifiers to evolutionary generated adversarial examples. Neural Networks 127: 168-181 (2020) - [c117]Juan Carlos Figueroa-García, Roman Neruda, Yurilev Chalco-Cano, Heriberto Román-Flores:
On the relationship between the centroid and the footprint of uncertainty of Interval Type-2 fuzzy numbers. FUZZ-IEEE 2020: 1-7 - [c116]Petra Vidnerová, Stepán Procházka, Roman Neruda:
Multiobjective Evolution for Convolutional Neural Network Architecture Search. ICAISC (1) 2020: 261-270 - [c115]Petra Vidnerová, Roman Neruda:
Multi-objective Evolution for Deep Neural Network Architecture Search. ICONIP (3) 2020: 270-281 - [c114]Stepán Procházka, Roman Neruda:
Black-box Evolutionary Search for Adversarial Examples against Deep Image Classifiers in Non-Targeted Attacks. IJCNN 2020: 1-8 - [c113]Gabriela Suchopárová, Roman Neruda:
Genens: An AutoML System for Ensemble Optimization Based on Developmental Genetic Programming. SSCI 2020: 631-638
2010 – 2019
- 2019
- [c112]Klára Pesková, Roman Neruda:
Hyperparameters Search Methods for Machine Learning Linear Workflows. ICMLA 2019: 1205-1210 - [c111]Juan Carlos Figueroa-García, Alvaro David Orjuela-Cañón, Roman Neruda:
On the boundaries of the centroid of a class of fuzzy numbers. LA-CCI 2019: 1-5 - 2018
- [c110]Petra Vidnerová, Roman Neruda:
Deep Networks with RBF Layers to Prevent Adversarial Examples. ICAISC (1) 2018: 257-266 - [c109]Petra Vidnerová, Roman Neruda:
Asynchronous Evolution of Convolutional Networks. ITAT 2018: 80-85 - [c108]Lucie Rehakova, Roman Neruda:
Utilization of Genetic Programming to Solve a Simple Task Network Planning Problem. SMC 2018: 3660-3666 - 2017
- [j6]Tomás Kren, Martin Pilát, Roman Neruda:
Automatic Creation of Machine Learning Workflows with Strongly Typed Genetic Programming. Int. J. Artif. Intell. Tools 26(5): 1760020:1-1760020:24 (2017) - [c107]Petra Vidnerová, Roman Neruda:
Evolving KERAS Architectures for Sensor Data Analysis. FedCSIS 2017: 109-112 - [c106]Martin Pilát, Roman Neruda:
Parallel evolutionary algorithm with interleaving generations. GECCO 2017: 865-872 - [c105]Martin Slapák, Roman Neruda:
Matching subtrees in genetic programming crossover operator. ICNC-FSKD 2017: 208-213 - [c104]Josef Moudrík, Tomás Kren, Roman Neruda:
Algorithm Discovery with Monte-Carlo Search: Controlling the Size. ICTAI 2017: 390-395 - [c103]Petra Vidnerová, Roman Neruda:
Evolution Strategies for Deep Neural Network Models Design. ITAT 2017: 159-166 - [c102]Tomás Kren, Josef Moudrík, Roman Neruda:
Combining top-down and bottom-up approaches for automated discovery of typed programs. SSCI 2017: 1-8 - [c101]Tomás Kren, Martin Pilát, Roman Neruda:
Multi-objective evolution of machine learning workflows. SSCI 2017: 1-8 - [c100]Roman Neruda, Martin Pilát, Josef Moudrík:
Unsupervised and Supervised Activity Analysis of Drone Sensor Data. WEA 2017: 3-11 - [e3]Carlos Martín-Vide, Roman Neruda, Miguel A. Vega-Rodríguez:
Theory and Practice of Natural Computing - 6th International Conference, TPNC 2017, Prague, Czech Republic, December 18-20, 2017, Proceedings. Lecture Notes in Computer Science 10687, Springer 2017, ISBN 978-3-319-71068-6 [contents] - 2016
- [c99]Petra Vidnerová, Roman Neruda:
Sensor Data Air Pollution Prediction by Kernel Models. CCGrid 2016: 666-673 - [c98]Martin Pilát, Roman Neruda:
General tuning of weights in MOEA/D. CEC 2016: 965-972 - [c97]Martin Pilát, Tomás Kren, Roman Neruda:
Asynchronous Evolution of Data Mining Workflow Schemes by Strongly Typed Genetic Programming. ICTAI 2016: 577-584 - [c96]Petra Vidnerová, Roman Neruda:
Vulnerability of Machine Learning Models to Adversarial Examples. ITAT 2016: 187-194 - [c95]Petra Vidnerová, Roman Neruda:
Evolutionary generation of adversarial examples for deep and shallow machine learning models. MISNC 2016: 43 - [c94]Martin Pilát, Roman Neruda:
Feature Extraction for Surrogate Models in Genetic Programming. PPSN 2016: 335-344 - [c93]Josef Moudrík, Roman Neruda:
Determining Player Skill in the Game of Go with Deep Neural Networks. TPNC 2016: 188-195 - [c92]Roman Neruda:
Search Techniques for Automated Proposal of Data Mining Schemes. WEA 2016: 84-90 - 2015
- [c91]Jakub Smíd, Martin Pilát, Klára Pesková, Roman Neruda:
Co-evolutionary genetic programming for dataset similarity induction. CEC 2015: 1160-1166 - [c90]Josef Moudrík, Petr Baudis, Roman Neruda:
Evaluating Go game records for prediction of player attributes. CIG 2015: 162-168 - [c89]Martin Pilát, Roman Neruda:
Incorporating User Preferences in MOEA/D through the Coevolution of Weights. GECCO 2015: 727-734 - [c88]Petra Vidnerová, Roman Neruda:
Product Multi-kernels for Sensor Data Analysis. ICAISC (1) 2015: 123-133 - [c87]Martin Pilát, Roman Neruda:
Hypervolume-Based Surrogate Model for MO-CMA-ES. ICTAI 2015: 604-611 - [c86]Tomás Kren, Martin Pilát, Klára Pesková, Roman Neruda:
Generating Workflow Graphs Using Typed Genetic Programming. MetaSel@PKDD/ECML 2015: 108-109 - [c85]Tomás Kren, Roman Neruda:
A Dynamic Programming Approach to Individual Initialization in Genetic Programming. SMC 2015: 1752-1757 - [c84]Toma Ken, Martin Pilát, Roman Neruda:
Evolving Workflow Graphs Using Typed Genetic Programming. SSCI 2015: 1407-1414 - [c83]Jakub Smíd, Martin Pilát, Klára Pesková, Roman Neruda:
Multi-Objective Genetic Programming for Dataset Similarity Induction. SSCI 2015: 1576-1582 - [c82]Josef Moudrík, Roman Neruda:
Evolving Non-Linear Stacking Ensembles for Prediction of Go Player Attributes. SSCI 2015: 1673-1680 - [i2]Josef Moudrík, Petr Baudis, Roman Neruda:
Evaluating Go Game Records for Prediction of Player Attributes. CoRR abs/1512.08969 (2015) - [i1]Josef Moudrík, Roman Neruda:
Evolving Non-linear Stacking Ensembles for Prediction of Go Player Attributes. CoRR abs/1512.09254 (2015) - 2014
- [c81]Ondrej Kazík, Roman Neruda:
Data Mining Process Optimization in Computational Multi-agent Systems. ADMI 2014: 93-103 - [c80]Tomás Kren, Roman Neruda:
Generating lambda term individuals in typed genetic programming using forgetful A∗. IEEE Congress on Evolutionary Computation 2014: 1847-1854 - [c79]Martin Pilát, Roman Neruda:
The effect of different local search algorithms on the performance of multi-objective optimizers. IEEE Congress on Evolutionary Computation 2014: 2172-2179 - [c78]Jakub Smíd, Roman Neruda:
Comparing datasets by attribute alignment. CIDM 2014: 56-62 - [c77]Klára Pesková, Jakub Smíd, Martin Pilát, Ondrej Kazík, Roman Neruda:
Hybrid Multi-Agent System for Metalearning in Data Mining. MetaSel@ECAI 2014: 53-54 - [c76]Martin Pilát, Roman Neruda:
Hypervolume-based local search in multi-objective evolutionary optimization. GECCO 2014: 637-644 - [c75]Tomás Kren, Roman Neruda:
Utilization of reductions and abstraction elimination in typed genetic programming. GECCO 2014: 943-950 - [c74]Martin Slapák, Roman Neruda:
Multiobjective Genetic Programming of Agent Decision Strategies. IBICA 2014: 173-182 - 2013
- [j5]Martin Pilát, Roman Neruda:
Aggregate meta-models for evolutionary multiobjective and many-objective optimization. Neurocomputing 116: 392-402 (2013) - [c73]Jan Kohout, Roman Neruda:
Two-Phase Genetic Algorithm for Social Network Graphs Clustering. AINA Workshops 2013: 197-202 - [c72]Martin Pilát, Roman Neruda:
Surrogate model selection for evolutionary multiobjective optimization. IEEE Congress on Evolutionary Computation 2013: 1860-1867 - [c71]Martin Pilát, Roman Neruda:
Multiobjectivization for classifier parameter tuning. GECCO (Companion) 2013: 97-98 - [c70]Jakub Smíd, Roman Neruda:
Using Genetic Programming to Estimate Performance of Computational Intelligence Models. ICANNGA 2013: 169-178 - [c69]Martin Pilát, Roman Neruda:
Multi-objectivization and Surrogate Modelling for Neural Network Hyper-parameters Tuning. ICIC (3) 2013: 61-66 - [c68]Ondrej Kazík, Klára Pesková, Jakub Smíd, Roman Neruda:
Clustering Based Classification in Data Mining Method Recommendation. ICMLA (2) 2013: 356-361 - 2012
- [c67]Ondrej Kazík, Roman Neruda:
Role-Based Management and Matchmaking in Data-Mining Multi-Agent Systems. ADMI 2012: 22-35 - [c66]Stepán Balcar, Martin Pilát, Roman Neruda:
An evolutionary algorithm for 2D semi-guillotinable circular saw cutting. IEEE Congress on Evolutionary Computation 2012: 1-5 - [c65]Martin Pilát, Roman Neruda:
An Evolutionary Strategy for Surrogate-Based Multiobjective Optimization. IEEE Congress on Evolutionary Computation 2012: 1-7 - [c64]Martin Pilát, Roman Neruda:
A surrogate multiobjective evolutionary strategy with local search and pre-selection. GECCO (Companion) 2012: 633-634 - [c63]Ondrej Kazík, Klára Pesková, Martin Pilát, Roman Neruda:
A Novel Meta Learning System and Its Application to Optimization of Computing Agents' Results. IAT 2012: 170-174 - [c62]Roman Neruda, Martin Slapák:
Evolving Decision Strategies for Computational Intelligence Agents. ICIC (2) 2012: 213-220 - [c61]Ondrej Kazík, Klára Pesková, Martin Pilát, Roman Neruda:
Combining Parameter Space Search and Meta-learning for Data-Dependent Computational Agent Recommendation. ICMLA (2) 2012: 36-41 - [c60]Martin Pilát, Roman Neruda:
Meta-learning and Model Selection in Multi-objective Evolutionary Algorithms. ICMLA (1) 2012: 433-438 - [c59]Martin Pilát, Roman Neruda:
A Surrogate Based Multiobjective Evolution Strategy with Different Models for Local Search and Pre-selection. ICTAI 2012: 215-222 - [c58]Jan Kohout, Roman Neruda:
Exploration and Exploitation Operators for Genetic Graph Clustering Algorithm. ISMIS 2012: 87-92 - [p2]Ondrej Kazík, Roman Neruda:
Management of MAS by Means of Automated Reasoning in the Role Model. Software Agents, Agent Systems and Their Applications 2012: 309-322 - 2011
- [c57]Martin Pilát, Roman Neruda:
ASM-MOMA: Multiobjective memetic algorithm with aggregate surrogate model. IEEE Congress on Evolutionary Computation 2011: 1202-1208 - [c56]Martin Pilát, Roman Neruda:
LAMM-MMA: multiobjective memetic algorithm with local aggregate meta-model. GECCO (Companion) 2011: 79-80 - [c55]Martin Pilát, Roman Neruda:
Improving many-objective optimizers with aggregate meta-models. HIS 2011: 555-560 - [c54]Ondrej Kazík, Klára Pesková, Martin Pilát, Roman Neruda:
Meta Learning in Multi-agent Systems for Data Mining. IAT 2011: 433-434 - [c53]Petra Vidnerová, Roman Neruda:
Evolving Sum and Composite Kernel Functions for Regularization Networks. ICANNGA (1) 2011: 180-189 - [c52]Martin Pilát, Roman Neruda:
Local Meta-models for ASM-MOMA. ICIC (3) 2011: 79-84 - [c51]Martin Pilát, Roman Neruda:
Local Meta-models for ASM-MOMA. ICIC (1) 2011: 147-152 - [c50]Ondrej Kazík, Roman Neruda:
Role Model of Search in Agents' Parameter-Space. ICMLA (2) 2011: 31-34 - [c49]Ondrej Kazík, Klára Pesková, Martin Pilát, Roman Neruda:
Implementation of Parameter Space Search for Meta Learning in a Data-Mining Multi-agent System. ICMLA (2) 2011: 366-369 - [c48]Stanislav Slusny, Roman Neruda:
Local Search Heuristics for Robotic Routing Planner. ISNN (3) 2011: 31-40 - [c47]Petra Vidnerová, Roman Neruda:
Evolutionary Learning of Regularization Networks with Multi-kernel Units. ISNN (1) 2011: 538-546 - [c46]Roman Neruda, Ondrej Kazík:
Modeling data mining processes in computational multi-agent systems. MEDES 2011: 61-67 - [c45]Petra Vidnerová, Roman Neruda:
Evolutionary learning of regularization networks with product kernel units. SMC 2011: 638-643 - 2010
- [j4]Vera Kurková, Roman Neruda, Jan Koutník:
Editorial. Neural Networks 23(4): 465 (2010) - [j3]Stanislav Slusny, Roman Neruda, Petra Vidnerová:
Comparison of behavior-based and planning techniques on the small robot maze exploration problem. Neural Networks 23(4): 560-567 (2010) - [c44]Martin Pilát, Roman Neruda:
Combining multiobjective and single-objective genetic algorithms in heterogeneous island model. IEEE Congress on Evolutionary Computation 2010: 1-8 - [c43]Roman Neruda, Petra Vidnerová:
Genetic Algorithm with Species for Regularization Network Metalearning. IAIT 2010: 192-201 - [c42]Petra Vidnerová, Roman Neruda:
Hybrid Learning of Regularization Neural Networks. ICAISC (2) 2010: 124-131 - [c41]Stanislav Slusny, Michal Zerola, Roman Neruda:
Real Time Robot Path Planning and Cleaning. ICIC (2) 2010: 442-449 - [c40]Roman Neruda, Petra Vidnerová:
Memetic Evolutionary Learning for Local Unit Networks. ISNN (1) 2010: 534-541 - [c39]Roman Neruda, Ondrej Kazík:
Role-based design of computational intelligence multi-agent system. MEDES 2010: 95-101
2000 – 2009
- 2009
- [j2]Roman Vaculín, Roman Neruda, Katia P. Sycara:
The process mediation framework for semantic web services. Int. J. Agent Oriented Softw. Eng. 3(1): 27-58 (2009) - [c38]Roman Neruda:
Description, Composition, and Decision Support for Multiagent Computational Systems. ICTAI 2009: 300-307 - [c37]Stanislav Slusny, Roman Neruda, Petra Vidnerová:
Localization With a Low-cost Robot. ITAT 2009: 77-80 - [p1]Roman Neruda:
Towards Data-Driven Hybrid Composition of Data Mining Multi-agent Systems. Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing 2009: 271-281 - 2008
- [c36]Roman Vaculín, Roman Neruda, Katia P. Sycara:
Towards Extending Service Discovery with Automated Composition Capabilities. ECOWS 2008: 3-12 - [c35]Roman Neruda, Stanislav Slusny, Petra Vidnerová:
Evolutionary Learning and Behavior Analysis of the Autonomous Robot Neuro-Controller. GEM 2008: 222-228 - [c34]Roman Neruda:
Hybrid Search Methods for Automatic Discovery of Computational Agent Schemes. Web Intelligence/IAT Workshops 2008: 579-582 - [c33]Roman Neruda, Václav Snásel, Jan Platos, Pavel Krömer, Dusan Húsek, Alexander A. Frolov:
Implementing Boolean Matrix Factorization. ICANN (1) 2008: 543-552 - [c32]Stanislav Slusny, Roman Neruda, Petra Vidnerová:
Comparison of RBF Network Learning and Reinforcement Learning on the Maze Exploration Problem. ICANN (1) 2008: 720-729 - [c31]Petra Vidnerová, Stanislav Slusny, Roman Neruda:
Evolutionary trained radial basis function networks for robot control. ICARCV 2008: 833-838 - [c30]Stanislav Slusny, Roman Neruda, Petra Vidnerová:
Rule-Based Analysis of Behaviour Learned by Evolutionary and Reinforcement Algorithms. ICIC (2) 2008: 284-291 - [c29]Roman Vaculín, Huajun Chen, Roman Neruda, Katia P. Sycara:
Modeling and Discovery of Data Providing Services. ICWS 2008: 54-61 - [c28]Petra Vidnerová, Roman Neruda:
Testing Error Estimates for Regularization and Radial Function Networks. ISNN (1) 2008: 549-554 - [c27]Stanislav Slusny, Roman Neruda, Petra Vidnerová:
Learning algorithms for small mobile robots: case study on maze exploration. ITAT 2008 - [c26]Roman Neruda:
Ontology-based and Evolutionary Search for Computational Agents Schemes. SEKE 2008: 569-572 - [c25]Roman Vaculín, Roman Neruda, Katia P. Sycara:
An Agent for Asymmetric Process Mediation in Open Environments. SOCASE 2008: 104-117 - [e2]Vera Kurková, Roman Neruda, Jan Koutník:
Artificial Neural Networks - ICANN 2008 , 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part I. Lecture Notes in Computer Science 5163, Springer 2008, ISBN 978-3-540-87535-2 [contents] - [e1]Vera Kurková, Roman Neruda, Jan Koutník:
Artificial Neural Networks - ICANN 2008, 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part II. Lecture Notes in Computer Science 5164, Springer 2008, ISBN 978-3-540-87558-1 [contents] - 2007
- [c24]Roman Neruda:
Evolving neural network which control a robotic agent. IEEE Congress on Evolutionary Computation 2007: 1517-1522 - [c23]Roman Neruda:
Hybrid evolutionary algorithm for multilayer perceptron networkswith competitive performance. IEEE Congress on Evolutionary Computation 2007: 1620-1627 - [c22]Roman Neruda, Stanislav Slusny:
Variants of Memetic And Hybrid Learning of Perceptron Networks. DEXA Workshops 2007: 158-162 - 2006
- [c21]Suhail S. J. Owais, Pavel Krömer, Václav Snásel, Dusan Húsek, Roman Neruda:
Implementing GP on Optimizing both Boolean and Extended Boolean Queries in IR and Fuzzy IR systems with Respect to the Users Profiles. IEEE Congress on Evolutionary Computation 2006: 1499-1505 - [c20]Roman Neruda:
Cooperation of Computational Intelligence Agents. CTS 2006: 256-263 - [c19]Andrei Kursin, Dusan Húsek, Roman Neruda:
Faster Learning with Overlapping Neural Assemblies. ICANN (1) 2006: 226-233 - [c18]Roman Neruda:
Emerging Hybrid Computational Models. ICIC (2) 2006: 379-389 - [c17]Roman Neruda, Gerd Beuster:
Description and Generation of Computational Agents. KSEM 2006: 318-329 - 2005
- [j1]Roman Neruda, Petra Kudová:
Learning methods for radial basis function networks. Future Gener. Comput. Syst. 21(7): 1131-1142 (2005) - [c16]Roman Neruda, Pavel Krusina:
Estimating and Measuring Performance of Computational Agents. IAT 2005: 615-618 - 2004
- [c15]Petra Kudová, Roman Neruda:
Kernel Based Learning Methods: Regularization Networks and RBF Networks. Deterministic and Statistical Methods in Machine Learning 2004: 124-136 - [c14]Roman Neruda, Pavel Krusina, Petra Kudová, Pavel Rydvan, Gerd Beuster:
Bang 3: A Computational Multi-Agent System. IAT 2004: 563-564 - 2003
- [c13]Gerd Beuster, Pavel Krusina, Roman Neruda, Pavel Rydvan:
Towards building computational agent schemes. ICANNGA 2003: 210-215 - [c12]Roman Neruda:
Building Hybrid Soft Computing Agents. Neural Networks and Computational Intelligence 2003: 7-12 - 2002
- [c11]Roman Neruda, Arnost Stedrý, Jitka Drkosová:
Variants of Learning Algorithm Based on Kolmogorov Theorem. International Conference on Computational Science (3) 2002: 536-543 - [c10]Roman Neruda, Petra Kudová:
Hybrid Learning of RBF Networks. International Conference on Computational Science (3) 2002: 594-603 - 2001
- [c9]Roman Neruda, Pavel Krusina, Zuzana Petrová:
More Autonomous Hybrid Models in Bang. International Conference on Computational Science (2) 2001: 935-942 - [c8]Roman Neruda, Arnost Stedrý, Jitka Drkosová:
Implementation of Kolmogorov Learning Algorithm for Feedforward Neural Networks. International Conference on Computational Science (2) 2001: 986-995 - [c7]Roman Neruda:
Agents that Make Hybrid AI Models. ISAS-SCI (1) 2001: 24-29 - 2000
- [c6]Roman Neruda:
Genetic Algorithms and Neural Networks: Making Use of Parameter Space Symmetries. IJCNN (1) 2000: 293-298
1990 – 1999
- 1999
- [c5]Roman Neruda:
Utilizing unique parametrization property in approximate genetic learning of feed-forward networks. IJCNN 1999: 4186-4191 - 1997
- [c4]Roman Neruda:
Canonical Genetic Learning of RBF Networks Is Faster. ICANNGA 1997: 350-353 - [c3]Roman Neruda:
Yet Another Genetic Algorithm for Feed-Forward Neural Networks. ICTAI 1997: 375- - [c2]David Strupl, Roman Neruda:
Parallelizing Self-Organizing Maps. SOFSEM 1997: 563-570 - 1995
- [c1]Roman Neruda:
Functional Equivalence and Genetic Learning of RBF Networks. ICANNGA 1995: 53-56
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-23 21:23 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
