Folgen
Martin Schrimpf
Martin Schrimpf
MIT Research Scientist
Bestätigte E-Mail-Adresse bei mit.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Brain-Score: Which artificial neural network for object recognition is most brain-like?
M Schrimpf*, J Kubilius*, H Hong, NJ Majaj, R Rajalingham, EB Issa, ...
bioRxiv, 2018
267*2018
Recurrent computations for visual pattern completion
H Tang*, M Schrimpf*, W Lotter*, C Moerman, A Paredes, JO Caro, ...
Proceedings of the National Academy of Sciences (PNAS) 115 (35), 8835-8840, 2018
1402018
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
J Kubilius*, M Schrimpf*, K Kar, R Rajalingham, H Hong, N Majaj, E Issa, ...
Advances in Neural Information Processing Systems (NeurIPS), 12785-12796, 2019
1382019
The neural architecture of language: Integrative modeling converges on predictive processing
M Schrimpf, IA Blank, G Tuckute, C Kauf, EA Hosseini, NG Kanwisher, ...
Proceedings of the National Academy of Sciences (PNAS) 118 (45), 2021
137*2021
Unsupervised neural network models of the ventral visual stream
C Zhuang, S Yan, A Nayebi, M Schrimpf, MC Frank, JJ DiCarlo, ...
Proceedings of the National Academy of Sciences (PNAS) 118 (3), 2021
1212021
CORnet: Modeling the neural mechanisms of core object recognition
J Kubilius*, M Schrimpf*, A Nayebi, D Bear, DLK Yamins, JJ DiCarlo
bioRxiv, 2018
101*2018
Threedworld: A platform for interactive multi-modal physical simulation
C Gan, J Schwartz, S Alter, M Schrimpf, J Traer, J De Freitas, J Kubilius, ...
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2021
952021
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
J Dapello*, T Marques*, M Schrimpf, F Geiger, DD Cox, JJ DiCarlo
Neural Information Processing Systems (NeurIPS), 2020
822020
Integrative benchmarking to advance neurally mechanistic models of human intelligence
M Schrimpf, J Kubilius, MJ Lee, NAR Murty, R Ajemian, JJ DiCarlo
Neuron 108 (3), 413-423, 2020
762020
On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
N Cheney*, M Schrimpf*, G Kreiman
CBMM Memo, 2017
342017
A Flexible Approach to Automated RNN Architecture Generation
M Schrimpf*, S Merity*, J Bradbury, R Socher
International Conference on Learning Representations (ICLR), 2017
152017
Frivolous Units: Wider Networks Are Not Really That Wide
S Casper, X Boix, V D'Amario, L Guo, M Schrimpf, K Vinken, G Kreiman
Proceedings of the AAAI Conference on Artificial Intelligence, 6921-6929, 2021
14*2021
Multi-scale hierarchical neural network models that bridge from single neurons in the primate primary visual cortex to object recognition behavior
T Marques, M Schrimpf, JJ DiCarlo
bioRxiv, 2021
132021
Beyond linear regression: mapping models in cognitive neuroscience should align with research goals
AA Ivanova, M Schrimpf, S Anzellotti, N Zaslavsky, E Fedorenko, L Isik
bioRxiv, 2021
8*2021
Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results
L Arend, Y Han, M Schrimpf, P Bashivan, K Kar, T Poggio, JJ DiCarlo, ...
Center for Brains, Minds and Machines (CBMM), 2018
82018
Should i use tensorflow
M Schrimpf
arXiv preprint arXiv:1611.08903, 2016
72016
Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream
F Geiger*, M Schrimpf*, T Marques, J DiCarlo
International Conference on Learning Representations (ICLR), 2022
62022
Continual Learning with Self-Organizing Maps
P Bashivan, M Schrimpf, R Ajemian, I Rish, M Riemer, Y Tu
Neural Information Processing Systems (NeurIPS) Continual Learning Workshop, 2018
62018
To find better neural network models of human vision, find better neural network models of primate vision
KM Jozwik, M Schrimpf, N Kanwisher, JJ DiCarlo
BioRxiv, 688390, 2019
52019
Large-scale hyperparameter search for predicting human brain responses in the Algonauts challenge
KM Jozwik, M Lee, T Marques, M Schrimpf, P Bashivan
bioRxiv, 689844, 2019
42019
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20