Publications
Export 16 results:
Filters: Author is DiCarlo, James J [Clear All Filters]
Adversarially trained neural representations may already be as robust as corresponding biological neural representations. arXiv. 2022. doi:https://doi.org/10.48550/arXiv.2206.11228.
(1.99 MB)

Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream. In: International Conference on Learning Representations 2022 Spotlight. International Conference on Learning Representations 2022 Spotlight.; 2022. doi:10.1101/2020.06.08.140111.
(1.45 MB)
. 
Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs. Shared Visual Representations in Human & Machine Intelligence - NeurIPS Workshop. 2021. Available at: https://arxiv.org/abs/2110.10645.
(1000.31 KB)
. 
The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI. arXiv. 2021. doi:arXiv:2103.14025.
(6.79 MB)

Unsupervised changes in core object recognition behavior are predicted by neural plasticity in inferior temporal cortex. eLife. 2021;10. doi:10.7554/eLife.60830.
. Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations. Neural Information Processing Systems (NeurIPS; spotlight). 2020. doi:10.1101/2020.06.16.154542.
(2.48 MB)
. 
Comparing novel object learning in humans, models, and monkeys. Journal of Vision. 2019;19(10):114b. doi:10.1167/19.10.114b.
. Using Brain-Score to Evaluate and Build Neural Networks for Brain-Like Object Recognition. In: Computational and Systems Neuroscience (COSYNE). Computational and Systems Neuroscience (COSYNE). Denver, CO; 2019.
Neural dynamics at successive stages of the ventral visual stream are consistent with hierarchical error signals. eLife. 2018;7. doi:10.7554/eLife.42870.
. Eight open questions in the computational modeling of higher sensory cortex. Current Opinion in Neurobiology. 2016;37:114 - 120. doi:10.1016/j.conb.2016.02.001.
. Explicit information for category-orthogonal object properties increases along the ventral stream. Nature Neuroscience. 2016;19(4):613 - 622. doi:10.1038/nn.4247.
. Using goal-driven deep learning models to understand sensory cortex. Nature Neuroscience. 2016;19(3):356 - 365. doi:10.1038/nn.4244.
. Why is Real-World Visual Object Recognition Hard?. . PLoS Computational Biology. 2008;4:e27. doi:10.1371/journal.pcbi.0040027.
(1.93 MB)
. 
Learning and neural plasticity in visual object recognition. Current Opinion in Neurobiology. 2006;16(2):152 - 158. doi:10.1016/j.conb.2006.03.012.
(181.23 KB)
. 
'Breaking' position-invariant object recognition. Nature Neuroscience. 2005;8(9):1145 - 1147. doi:10.1038/nn1519.
(175.59 KB)
(49.96 KB)
(87.63 KB)
. 


Receptive field structure in cortical area 3b of the alert monkey. Behavioural Brain Research. 2002;135(1-2):167 - 178. doi:10.1016/S0166-4328(02)00162-6.
(382.63 KB)
. 