Petra Vidnerová
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Petra Vidnerová has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Roman Neruda
Institute of Computer Science, Czech Academy of Sciences, Prague, Czech Republic
9 shared publications - Jan Kalina
The Czech Academy of Sciences, Institute of Computer Science
7 shared publications - Jiří Šíma
Institute of Computer Science of the Czech Academy of Sciences
5 shared publications - Vojtech Mrazek
Brno University of Technology
2 shared publications - Gabriela Suchopárová
Czech Academy of Sciences
1 shared publication Jan Kalina
The Czech Academy of Sciences, Institute of Computer Science
1 shared publication
Latest Publications
- 22 November 2025
- Published by Springer Nature
- p. 460-475
Cross-Entropy Loss of Approximated Deep Neural Networks
- 22 November 2025
- Published by Springer Nature
- p. 460-475
Cross-Entropy Loss of Approximated Deep Neural Networks
- 30 September 2025
- Published by Springer Nature
- p. 398-416
Weight-Rounding Error in Deep Neural Networks
- 30 September 2025
- Published by Springer Nature
- p. 398-416
Weight-Rounding Error in Deep Neural Networks
- 17 September 2024
- Published by Springer Nature
- p. 30-40
On the Bayesian Interpretation of Robust Regression Neural Networks
- 17 September 2024
- Published by Springer Nature
- p. 30-40
On the Bayesian Interpretation of Robust Regression Neural Networks
- 19 July 2024
- Published by MIT Press in Neural Computation
- Vol. 36 (8) , 1601-1625
Energy Complexity of Convolutional Neural Networks
The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices. Recently, a number of methods have been proposed for providing energy-optimal mappings of CNNs onto diverse hardware accelerators. Their estimated energy consumption is related to specific implementation details and hardware parameters, which does not allow for machine-independent exploration of CNN energy measures. In this letter, we introduce a simplified theoretical energy complexity model for CNNs, based on only a two-level memory hierarchy that captures asymptotically all important sources of energy consumption for different CNN hardware implementations. In this model, we derive a simple energy lower bound and calculate the energy complexity of evaluating a CNN layer for two common data flows, providing corresponding upper bounds. According to statistical tests, the theoretical energy upper and lower bounds we present fit asymptotically very well with the real energy consumption of CNN implementations on the Simba and Eyeriss hardware platforms, estimated by the Timeloop/Accelergy program, which validates the proposed energy complexity model for CNNs.
- 19 July 2024
- Published by MIT Press in Neural Computation
- Vol. 36 (8) , 1601-1625
Energy Complexity of Convolutional Neural Networks
The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices. Recently, a number of methods have been proposed for providing energy-optimal mappings of CNNs onto diverse hardware accelerators. Their estimated energy consumption is related to specific implementation details and hardware parameters, which does not allow for machine-independent exploration of CNN energy measures. In this letter, we introduce a simplified theoretical energy complexity model for CNNs, based on only a two-level memory hierarchy that captures asymptotically all important sources of energy consumption for different CNN hardware implementations. In this model, we derive a simple energy lower bound and calculate the energy complexity of evaluating a CNN layer for two common data flows, providing corresponding upper bounds. According to statistical tests, the theoretical energy upper and lower bounds we present fit asymptotically very well with the real energy consumption of CNN implementations on the Simba and Eyeriss hardware platforms, estimated by the Timeloop/Accelergy program, which validates the proposed energy complexity model for CNNs.
- 31 May 2024
- Published by Elsevier in Neural Networks
- Vol. 178, 106419
On energy complexity of fully-connected layers
- 31 May 2024
- Published by Elsevier in Neural Networks
- Vol. 178, 106419
On energy complexity of fully-connected layers
- 23 September 2023
- Published by Springer Nature
- p. 200-212
Properties of the Weighted and Robust Implicitly Weighted Correlation Coefficients
- 23 September 2023
- Published by Springer Nature
- p. 200-212
Properties of the Weighted and Robust Implicitly Weighted Correlation Coefficients
- 22 September 2023
- Published by Springer Nature
- p. 186-198
Energy Complexity Model for Convolutional Neural Networks
- 22 September 2023
- Published by Springer Nature
- p. 186-198
Energy Complexity Model for Convolutional Neural Networks
- 24 August 2023
- Published by Springer Nature
- p. 2355-2376
Modern Approaches to Statistical Estimation of Measurements in the Location Model and Regression
- 24 August 2023
- Published by Springer Nature
- p. 2355-2376
Modern Approaches to Statistical Estimation of Measurements in the Location Model and Regression
- 24 January 2023
- Published by Springer Nature
- p. 144-153
Multi-objective Bayesian Optimization for Neural Architecture Search
- 24 January 2023
- Published by Springer Nature
- p. 144-153
Multi-objective Bayesian Optimization for Neural Architecture Search
- 10 June 2022
- Published by Springer Nature
- p. 310-320
Using a Deep Neural Network in a Relative Risk Model to Estimate Vaccination Protection for COVID-19
- 10 June 2022
- Published by Springer Nature
- p. 310-320
Using a Deep Neural Network in a Relative Risk Model to Estimate Vaccination Protection for COVID-19