Search results
- 1.0586300 - ÚI 2025 RIV GB eng J - Journal Article
Šíma, Jiří - Cabessa, Jérémie - Vidnerová, Petra
On energy complexity of fully-connected layers.
Neural Networks. Roč. 178, October 2024 (2024), č. článku 106419. ISSN 0893-6080. E-ISSN 1879-2782
R&D Projects: GA ČR(CZ) GA22-02067S
Institutional support: RVO:67985807
Keywords : Deep neural networks * Convolutional neural networks * Fully-connected layer * Energy complexity * Energy consumption * Dataflow
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 7.8, year: 2022
Method of publishing: Limited access
https://doi.org/10.1016/j.neunet.2024.106419
Permanent Link: https://hdl.handle.net/11104/0353852 - 2.0584980 - ÚI 2025 US J - Journal Article
Šíma, Jiří - Vidnerová, Petra - Mrázek, V.
Energy Complexity of Convolutional Neural Networks.
Neural Computation. Online March 2024 (2024). ISSN 0899-7667. E-ISSN 1530-888X
Impact factor: 2.9, year: 2022
https://doi.org/10.1162/neco_a_01676
Permanent Link: https://hdl.handle.net/11104/0352763 - 3.0536423 - ÚI 2023 RIV NL eng J - Journal Article
Šíma, Jiří
Stronger Separation of Analog Neuron Hierarchy by Deterministic Context-Free Languages.
Neurocomputing. Roč. 493, July 2022 (2022), s. 605-612. ISSN 0925-2312. E-ISSN 1872-8286
R&D Projects: GA ČR(CZ) GA19-05704S
Institutional support: RVO:67985807
Keywords : Recurrent neural network * Analog neuron hierarchy * Deterministic context-free language * Chomsky hierarchy
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 6, year: 2022
Method of publishing: Limited access
http://dx.doi.org/10.1016/j.neucom.2021.12.107
Permanent Link: http://hdl.handle.net/11104/0314194 - 4.0507515 - ÚI 2021 RIV GB eng J - Journal Article
Šíma, Jiří
Analog Neuron Hierarchy.
Neural Networks. Roč. 128, August 2020 (2020), s. 199-215. ISSN 0893-6080. E-ISSN 1879-2782
R&D Projects: GA ČR(CZ) GA19-05704S
Institutional support: RVO:67985807
Keywords : recurrent neural network * analog neuron hierarchy * deterministic context-free language * Turing machine * Chomsky hierarchy
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 8.050, year: 2020
Method of publishing: Limited access
http://dx.doi.org/10.1016/j.neunet.2020.05.006
Permanent Link: http://hdl.handle.net/11104/0298502 - 5.0490203 - ÚI 2020 RIV GB eng J - Journal Article
Šíma, Jiří
Subrecursive Neural Networks.
Neural Networks. Roč. 116, August (2019), s. 208-223. ISSN 0893-6080. E-ISSN 1879-2782
R&D Projects: GA ČR(CZ) GA19-05704S
Institutional support: RVO:67985807
Keywords : recurrent neural network * Chomsky hierarchy * cut language * quasi-periodic number
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 5.535, year: 2019
Method of publishing: Limited access
http://dx.doi.org/10.1016/j.neunet.2019.04.019
Permanent Link: http://hdl.handle.net/11104/0284481File Download Size Commentary Version Access 0490203-sub.pdf 5 2 MB Author´s preprint open-access 0490203-aa.pdf 13 1 MB Publisher’s postprint require - 6.0482160 - ÚI 2019 RIV NL eng J - Journal Article
Šíma, Jiří - Savický, Petr
Quasi-Periodic beta-Expansions and Cut Languages.
Theoretical Computer Science. Roč. 720, 11 April (2018), s. 1-23. ISSN 0304-3975. E-ISSN 1879-2294
R&D Projects: GA ČR GBP202/12/G061
Institutional support: RVO:67985807
Keywords : beta-expansion * quasi-periodicity * Pisot number * cut language * Chomsky hierarchy
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 0.718, year: 2018
Permanent Link: http://hdl.handle.net/11104/0277554File Download Size Commentary Version Access 0482160.pdf 6 1.2 MB Author´s preprint open-access a0482160.pdf 8 686.3 KB Publisher’s postprint require - 7.0405292 - UIVT-O 330614 RIV US eng J - Journal Article
Šíma, Jiří - Sgall, Jiří
On the Non-Learnability of a Single Spiking Neuron.
[O nenaučitelnosti jednoho spiking neuronu.]
Neural Computation. Roč. 17, č. 12 (2005), s. 2635-2647. ISSN 0899-7667. E-ISSN 1530-888X
R&D Projects: GA ČR GA201/02/1456; GA AV ČR 1ET100300517; GA MŠMT LN00A056; GA MŠMT(CZ) 1M0545
Institutional research plan: CEZ:AV0Z10300504; CEZ:AV0Z10190503
Keywords : spiking neuron * consistency problem * NP-completness * PAC model * robust learning * representation problem
Subject RIV: BA - General Mathematics
Impact factor: 2.591, year: 2005
Permanent Link: http://hdl.handle.net/11104/0125473File Download Size Commentary Version Access 0405292.pdf 1 366.7 KB Author´s preprint open-access - 8.0404691 - UIVT-O 20030011 RIV NL eng J - Journal Article
Šíma, Jiří - Orponen, P.
Exponential Transients in Continuous-Time Liapunov Systems.
Theoretical Computer Science. Roč. 306, - (2003), s. 353-372. ISSN 0304-3975. E-ISSN 1879-2294
R&D Projects: GA AV ČR IAB2030007; GA ČR GA201/00/1489; GA ČR GA201/01/1192
Institutional research plan: AV0Z1030915
Keywords : dynamical systems * continuous time * Hopfield network * Liapunov function * convergence time
Subject RIV: BA - General Mathematics
Impact factor: 0.764, year: 2003
Permanent Link: http://hdl.handle.net/11104/0124930File Download Size Commentary Version Access 0404691.pdf 0 963 KB Author´s preprint open-access - 9.0404612 - UIVT-O 20030009 RIV US eng J - Journal Article
Šíma, Jiří - Orponen, P.
Continuous-Time Symmetric Hopfield Nets are Computationally Universal.
Neural Computation. Roč. 15, č. 3 (2003), s. 693-733. ISSN 0899-7667. E-ISSN 1530-888X
R&D Projects: GA AV ČR IAB2030007; GA ČR GA201/02/1456
Institutional research plan: AV0Z1030915
Keywords : continuous-time Hopfield network * Liapunov function * analog computation * computational power * Turing universality
Subject RIV: BA - General Mathematics
Impact factor: 2.747, year: 2003
Permanent Link: http://hdl.handle.net/11104/0124854File Download Size Commentary Version Access 0404612.pdf 10 743.2 KB Author´s preprint open-access - 10.0404583 - UIVT-O 20020147 RIV US eng J - Journal Article
Šíma, Jiří
Training a Single Sigmoidal Neuron is Hard.
Neural Computation. Roč. 14, č. 11 (2002), s. 2709-2729. ISSN 0899-7667. E-ISSN 1530-888X
R&D Projects: GA MŠMT LN00A056
Keywords : sigmoidal neuron * loading problem * NP-hardness
Subject RIV: BA - General Mathematics
Impact factor: 2.313, year: 2002
Permanent Link: http://hdl.handle.net/11104/0124828File Download Size Commentary Version Access 0404583.pdf 0 476.8 KB Author´s preprint open-access