Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Johannes Mehrer"'
Publikováno v:
Nature Communications, Vol 11, Iss 1, Pp 1-12 (2020)
Do artificial neural networks, like brains, exhibit individual differences? Using tools from systems neuroscience, this study reveals substantial variability in network-internal representations, calling into question the neuroscientific practice of u
Externí odkaz:
https://doaj.org/article/2dc8aab8551349db9390fdc10d566c86
Publikováno v:
PLoS Computational Biology, Vol 16, Iss 10, p e1008215 (2020)
Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computat
Externí odkaz:
https://doaj.org/article/fe1c5085e4954f2eb774b4de06c5e5dc
Autor:
Katherine R. Storrs, Johannes Mehrer, Nikolaus Kriegeskorte, Tim C. Kietzmann, Alexander Walther
Publikováno v:
Journal of Cognitive Neuroscience, 33, 10, pp. 2044-2064
Journal of Cognitive Neuroscience, 33, 2044-2064
Journal of Cognitive Neuroscience, 33, 2044-2064
Contains fulltext : 237374.pdf (Publisher’s version ) (Open Access) Deep neural networks (DNNs) trained on object recognition provide the best current models of high-level visual cortex. What remains unclear is how strongly experimental choices, su
Publikováno v:
Proceedings of the National Academy of Sciences USA, 118, 8
Proceedings of the National Academy of Sciences of the United States of America
Proceedings of the National Academy of Sciences USA, 118
Proceedings of the National Academy of Sciences of the United States of America
Proceedings of the National Academy of Sciences USA, 118
Significance Inspired by core principles of information processing in the brain, deep neural networks (DNNs) have demonstrated remarkable success in computer vision applications. At the same time, networks trained on the task of object classification
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c22058d631c629e623ab5a8f7b7fa1b1
https://hdl.handle.net/https://repository.ubn.ru.nl/handle/2066/231147
https://hdl.handle.net/https://repository.ubn.ru.nl/handle/2066/231147
Autor:
Johannes Mehrer, Katherine R. Storrs, Nikolaus Kriegeskorte, Tim C. Kietzmann, Alexander Walther
Deep neural networks (DNNs) trained on object recognition provide the best current models of high-level visual areas in the brain. What remains unclear is how strongly network design choices, such as architecture, task training, and subsequent fittin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fed8560d14bd1a9a69a0f7011352c11f
Publikováno v:
Plos Computational Biology, 16, 10
PLoS Computational Biology
PLoS Computational Biology, Vol 16, Iss 10, p e1008215 (2020)
Plos Computational Biology, 16
PLoS Computational Biology
PLoS Computational Biology, Vol 16, Iss 10, p e1008215 (2020)
Plos Computational Biology, 16
Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c227145782f7d4b20d04d6b4a6414d75
https://hdl.handle.net/2066/225297
https://hdl.handle.net/2066/225297
Publikováno v:
2018 Conference on Cognitive Computational Neuroscience.
Publikováno v:
2018 Conference on Cognitive Computational Neuroscience.