Исправљач (неуронске мреже) (Serbian Wikipedia)
Analysis of information sources in references of the Wikipedia article "Исправљач (неуронске мреже)" in Serbian language version.
refsWebsite
Global rank
Serbian rank
18th place
28th place
1st place
1st place
low place
low place
low place
low place
551st place
962nd place
179th place
200th place
120th place
187th place
arxiv.org
- Ramachandran, Prajit; Barret, Zoph (16. 10. 2017). „Searching for Activation Functions”. arXiv:1710.05941
[cs.NE]. - Kadmon, Jonathan; Sompolinsky, Haim (2015-11-19). „Transition to Chaos in Random Neuronal Networks”. Physical Review X. 5 (4): 041030. Bibcode:2015PhRvX...5d1030K. arXiv:1508.06486 . doi:10.1103/PhysRevX.5.041030.
- Engelken, Rainer; Wolf, Fred (2020-06-03). „Lyapunov spectra of chaotic recurrent neural networks”. arXiv:2006.02427 [nlin.CD].
- He, Kaiming; Zhang, Xiangyu. „Delving Deep into Rectifiers: Surpassing Human-Level Performance on Image Net Classification”. arXiv:1502.01852 [cs.CV].
- He, Kaiming; Zhang, Xiangyu. „Delving Deep into Rectifiers: Surpassing Human-Level Performance on Image Net Classification”. arXiv:1502.01852 [cs.CV].He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing; Sun, Jian (2015). "Delving Deep into Rectifiers: Surpassing Human-Level Performance on Image Net Classification". arXiv:1502.01852 [cs.CV].
- Hendrycks, Dan; Gimpel, Kevin. „Gaussian Error Linear Units (GELUs)”. arXiv:1606.08415 [cs.LG].
- Diganta Misra (23. 8. 2019), Mish: A Self Regularized Non-Monotonic Activation Function (PDF), arXiv:1908.08681v1 , Приступљено 26. 3. 2022
- Hendrycks, Dan; Gimpel, Kevin. „Gaussian Error Linear Units (GELUs)”. arXiv:1606.08415 [cs.LG].Hendrycks, Dan; Gimpel, Kevin (2016). "Gaussian Error Linear Units (GELUs)". arXiv:1606.08415 [cs.LG].
- Clevert, Djork-Arné; Unterthiner, Thomas. „Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)”. arXiv:1511.07289 [cs.LG].
- Diganta Misra (23. 8. 2019), Mish: A Self Regularized Non-Monotonic Activation Function (PDF), arXiv:1908.08681v1 , Приступљено 26. 3. 2022Diganta Misra (23 Aug 2019), Mish: A Self Regularized Non-Monotonic Activation Function (PDF), arXiv:1908.08681v1, retrieved 26 March 2022
bmvc2020-conference.com
- Diganta Misra (23. 8. 2019), Mish: A Self Regularized Non-Monotonic Activation Function (PDF), arXiv:1908.08681v1 , Приступљено 26. 3. 2022
- Diganta Misra (23. 8. 2019), Mish: A Self Regularized Non-Monotonic Activation Function (PDF), arXiv:1908.08681v1 , Приступљено 26. 3. 2022Diganta Misra (23 Aug 2019), Mish: A Self Regularized Non-Monotonic Activation Function (PDF), arXiv:1908.08681v1, retrieved 26 March 2022
doi.org
- Fukushima, K. (1969). „Visual feature extraction by a multilayered network of analog threshold elements”. IEEE Transactions on Systems Science and Cybernetics. 5 (4): 322—333. doi:10.1109/TSSC.1969.300225.
- Fukushima, K.; Miyake, S. (1982). „Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition.”. In Competition and Cooperation in Neural Nets. Lecture Notes in Biomathematics. Springer. 45: 267—285. ISBN 978-3-540-11574-8. doi:10.1007/978-3-642-46466-9_18.
- Hahnloser, R.; Sarpeshkar, R.; Mahowald, M. A.; Douglas, R. J.; Seung, H. S. (2000). „Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit”. Nature. 405 (6789): 947—951. Bibcode:2000Natur.405..947H. PMID 10879535. doi:10.1038/35016072.
- Hansel, D.; van Vreeswijk, C. (2002). „How noise contributes to contrast invariance of orientation tuning in cat visual cortex”. J. Neurosci. 22 (12): 5118—5128. PMC 6757721 . PMID 12077207. doi:10.1523/JNEUROSCI.22-12-05118.2002.
- Kadmon, Jonathan; Sompolinsky, Haim (2015-11-19). „Transition to Chaos in Random Neuronal Networks”. Physical Review X. 5 (4): 041030. Bibcode:2015PhRvX...5d1030K. arXiv:1508.06486 . doi:10.1103/PhysRevX.5.041030.
- Behnke, Sven (2003). Hierarchical Neural Networks for Image Interpretation. Lecture Notes in Computer Science. 2766. Springer. ISBN 978-3-540-40722-5. doi:10.1007/b11963.
harvard.edu
adsabs.harvard.edu
- Hahnloser, R.; Sarpeshkar, R.; Mahowald, M. A.; Douglas, R. J.; Seung, H. S. (2000). „Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit”. Nature. 405 (6789): 947—951. Bibcode:2000Natur.405..947H. PMID 10879535. doi:10.1038/35016072.
- Kadmon, Jonathan; Sompolinsky, Haim (2015-11-19). „Transition to Chaos in Random Neuronal Networks”. Physical Review X. 5 (4): 041030. Bibcode:2015PhRvX...5d1030K. arXiv:1508.06486 . doi:10.1103/PhysRevX.5.041030.
intel.com
software.intel.com
- „Smooth Rectifier Linear Unit (SmoothReLU) Forward Layer”. Developer Guide for Intel Data Analytics Acceleration Library (на језику: енглески). 2017. Архивирано из оригинала 05. 12. 2021. г. Приступљено 2018-12-04.
jmlr.org
- . Архивирано из оригинала
|archive-url=захтева|url=(помоћ)|archive-url=захтева|archive-date=(помоћ). г. Недостаје или је празан параметар|title=(помоћ)Xavier Glorot, Antoine Bordes and Yoshua Bengio (2011). Deep sparse rectifier neural networks Архивирано на сајту Wayback Machine (13. децембар 2016) (PDF). AISTATS.Rectifier and softplus activation functions. The second one is a smooth version of the first.
{{cite conference}}: CS1 maint: uses authors parameter (link)
lecun.com
yann.lecun.com
- „Efficient BackProp” (PDF). Neural Networks: Tricks of the Trade. Springer. 1998.
machinelearningmastery.com
- Brownlee, Jason (8. 1. 2019). „A Gentle Introduction to the Rectified Linear Unit (ReLU)”. Machine Learning Mastery. Приступљено 8. 4. 2021.
medium.com
- Liu, Danqing (30. 11. 2017). „A Practical Guide to ReLU”. Medium (на језику: енглески). Приступљено 8. 4. 2021.
nih.gov
ncbi.nlm.nih.gov
- Hahnloser, R.; Sarpeshkar, R.; Mahowald, M. A.; Douglas, R. J.; Seung, H. S. (2000). „Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit”. Nature. 405 (6789): 947—951. Bibcode:2000Natur.405..947H. PMID 10879535. doi:10.1038/35016072.
- Hansel, D.; van Vreeswijk, C. (2002). „How noise contributes to contrast invariance of orientation tuning in cat visual cortex”. J. Neurosci. 22 (12): 5118—5128. PMC 6757721 . PMID 12077207. doi:10.1523/JNEUROSCI.22-12-05118.2002.
nips.cc
papers.nips.cc
- Dugas, Charles; Bengio, Yoshua; Bélisle, François; Nadeau, Claude; Garcia, René (2000-01-01). „Incorporating second-order functional knowledge for better option pricing” (PDF). Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS'00). MIT Press: 451—457. „Since the sigmoid h has a positive first derivative, its primitive, which we call softplus, is convex.”
researchgate.net
- Behnke, Sven (2003). Hierarchical Neural Networks for Image Interpretation. Lecture Notes in Computer Science. 2766. Springer. ISBN 978-3-540-40722-5. doi:10.1007/b11963.
stanford.edu
ai.stanford.edu
- Andrew L. Maas, Awni Y. Hannun, Andrew Y. Ng (2014). Rectifier Nonlinearities Improve Neural Network Acoustic Models.
wandb.ai
- Shaw, Sweta (2020-05-10). „Activation Functions Compared with Experiments”. W&B (на језику: енглески). Приступљено 2022-07-11.
web.archive.org
- . Архивирано из оригинала
|archive-url=захтева|url=(помоћ)|archive-url=захтева|archive-date=(помоћ). г. Недостаје или је празан параметар|title=(помоћ)Xavier Glorot, Antoine Bordes and Yoshua Bengio (2011). Deep sparse rectifier neural networks Архивирано на сајту Wayback Machine (13. децембар 2016) (PDF). AISTATS.Rectifier and softplus activation functions. The second one is a smooth version of the first.
{{cite conference}}: CS1 maint: uses authors parameter (link) - „Smooth Rectifier Linear Unit (SmoothReLU) Forward Layer”. Developer Guide for Intel Data Analytics Acceleration Library (на језику: енглески). 2017. Архивирано из оригинала 05. 12. 2021. г. Приступљено 2018-12-04.