Pokročilé metody nature-inspired optimalizačních algoritmů a HPC implementace pro řešení reálných aplikací

English title

Advanced Methods of Nature-Inspired Optimisation and HPC Implementation for the Real-Life Applications

Type

grant

Keywords

Nature-inspired optimization, evolutionary algorithm; computational intelligence, key enabling technologies; international cooperation

Abstract

The scientific aim of the project is to design advanced evolutionary algorithms (EA) that are applicable in the up to date complex engineering optimizing and designing problems. Another objective is to adapt such algorithms for different user-defined platforms, e.g. for powerful GPU (Graphic Processing Unit) or, on the other hand, for low-power embedded systems. The project is divided into three solution phases called Work Packages (WP1-3). Within the first phase, new and hybrid evolutionary algorithms will be designed and evaluated. The implementations of HPC (High Performance Computing) and embedded systems will be realized in the second phase, where the pre-defined efficiency (computational performance, scalability, energy efficiency) will be emphasized. Within the third phase, the practical applications, referred to as the case studies consequently, will be elaborated. This final phase will prove the efficiency of the proposed algorithms and practical applicability w.r.t. the predefined real tasks. The integration objective of the project is to evolve the existing international co-operation and establish new collaboration of the research teams within BUT working on evolutionary algorithms with leading scientific institutions abroad. The aim is to present common publications containing new scientific results.

Team members

Matoušek Radomil, doc. Ing., Ph.D. (ÚAI FSI VUT) , research leader
Sekanina Lukáš, prof. Ing., Ph.D. (UPSY FIT VUT) , team leader
Bidlo Michal, doc. Ing., Ph.D. (UPSY FIT VUT)
Vašíček Zdeněk, doc. Ing., Ph.D. (UPSY FIT VUT)

Publications

2020

ANSARI Mohammad S., MRÁZEK Vojtěch, COCKBURN Bruce F., SEKANINA Lukáš, VAŠÍČEK Zdeněk and HAN Jie. Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 28, no. 2, 2020, pp. 317-328. ISSN 1063-8210. Detail

2019

BIDLO Michal and KORGO Jakub. Ant Colony Optimisation for Performing Computational Task in Cellular Automata. Mendel, vol. 25, no. 1, 2019, pp. 147-156. ISSN 1803-3814. Detail
KONČAL Ondřej and SEKANINA Lukáš. Cartesian Genetic Programming as an Optimizer of Programs Evolved with Geometric Semantic Genetic Programming. In: Genetic Programming 22nd European Conference, EuroGP 2019. Cham: Springer International Publishing, 2019, pp. 98-113. ISBN 978-3-030-16669-4. Detail
BIDLO Michal. Comparison of Evolutionary Development of Cellular Automata Using Various Representations. Mendel, vol. 2019, no. 1, pp. 95-102. ISSN 1803-3814. Detail
BIDLO Michal. Evolution of Cellular Automata Development Using Various Representations. In: GECCO '19 Proceedings of the Genetic and Evolutionary Computation Conference Companion. Praha: Association for Computing Machinery, 2019, pp. 107-108. ISBN 978-1-4503-6748-6. Detail
KOCNOVÁ Jitka and VAŠÍČEK Zdeněk. Impact of subcircuit selection on the efficiency of CGP-based optimization of gate-level circuits. In: GECCO '19 Proceedings of the Genetic and Evolutionary Computation Conference Companion. New York: Association for Computing Machinery, 2019, pp. 377-378. ISBN 978-1-4503-6748-6. Detail
BADÁŇ Filip and SEKANINA Lukáš. Optimizing Convolutional Neural Networks for Embedded Systems By Means of Neuroevolution. In: Theory and Practice of Natural Computing. LNCS 11934. Cham: Springer International Publishing, 2019, pp. 109-121. ISBN 978-3-030-34499-3. Detail
KOCNOVÁ Jitka and VAŠÍČEK Zdeněk. Towards a Scalable EA-based Optimization of Digital Circuits. In: Genetic Programming 22nd European Conference, EuroGP 2019. Cham: Springer International Publishing, 2019, pp. 81-97. ISBN 978-3-030-16669-4. Detail

2018

MRÁZEK Vojtěch, VAŠÍČEK Zdeněk and SEKANINA Lukáš. Design of Quality-Configurable Approximate Multipliers Suitable for Dynamic Environment. In: Proceedings of the 2018 NASA/ESA Conference on Adaptive Hardware and Systems. Edinburgh: Institute of Electrical and Electronics Engineers, 2018, pp. 264-271. ISBN 978-1-5386-7753-7. Detail
SEKANINA Lukáš, MRÁZEK Vojtěch and VAŠÍČEK Zdeněk. Design Space Exploration for Approximate Implementations of Arithmetic Data Path Primitives. In: 25th IEEE International Conference on Electronics Circuits and Systems (ICECS). Bordeaux: IEEE Circuits and Systems Society, 2018, pp. 377-380. ISBN 978-1-5386-9562-3. Detail
GROCHOL David and SEKANINA Lukáš. Fast Reconfigurable Hash Functions for Network Flow Hashing in FPGAs. In: Proceedings of the 2018 NASA/ESA Conference on Adaptive Hardware and Systems. Edinburgh: Institute of Electrical and Electronics Engineers, 2018, pp. 257-263. ISBN 978-1-5386-7753-7. Detail