Publication
Export 805 results:
How Deep Sparse Networks Avoid the Curse of Dimensionality: Efficiently Computable Functions are Compositionally Sparse. (2022).
v1.0 (984.15 KB)
v5.2 more fine tuning (1.14 MB)


On the Implicit Bias Towards Minimal Depth of Deep Neural Networks. arXiv (2022). at <https://arxiv.org/abs/2202.09028>
2202.09028.pdf (2 MB)

Incorporating Rich Social Interactions Into MDPs. (2022).
CBMM-Memo-133.pdf (1.68 MB)

Infants infer potential social partners by observing the interactions of their parent with unknown others. Proceedings of the National Academy of Sciences 119, (2022).
pnas.2121390119.pdf (1.43 MB)

Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4. BrainScore Workshop at COSYNE (2022). at <https://openreview.net/pdf?id=SOulrWP-Xb5>
Look twice: A generalist computational model predicts return fixations across tasks and species. PLOS Computational Biology 18, e1010654 (2022).
journal.pcbi_.1010654.pdf (4.51 MB)

Neural Collapse in Deep Homogeneous Classifiers and the role of Weight Decay. IEEE International Conference on Acoustics, Speech and Signal Processing (2022).
A neural population selective for song in human auditory cortex. Current Biology (2022). doi:10.1016/j.cub.2022.01.069
mmc2.pdf (9.52 MB)

Neurons detect cognitive boundaries to structure episodic memories in humans. Nature Neuroscience 25, 358 - 368 (2022).
One thing to fool them all: generating interpretable, universal, and physically-realizable adversarial features. arXiv (2022). doi:10.48550/arXiv.2110.03605
2110.03605.pdf (6.7 MB)

PCA as a defense against some adversaries. (2022).
CBMM-Memo-135.pdf (2.58 MB)

Reasoning about the antecedents of emotions: Bayesian causal inference over an intuitive theory of mind. Proceedings of the 44th Annual Conference of the Cognitive Science Society 44, 854-861 (2022).
Houlihan 2022 Proceedings of the 44th Annual Conference of the Cognitive Science Society.pdf (687.98 KB)

Representation Learning in Sensory Cortex: a theory. IEEE Access 1 - 1 (2022). doi:10.1109/ACCESS.2022.3208603
Representation_Learning_in_Sensory_Cortex_a_theory.pdf (1.17 MB)

Robust Feature-Level Adversaries are Interpretability Tools. NeurIPS (2022). at <https://openreview.net/forum?id=lQ--doSB2o>
8789_robust_feature_level_adversari.pdf (3.79 MB)

SGD Noise and Implicit Low-Rank Bias in Deep Neural Networks. (2022).
Implicit Rank Regularization.pdf (1.42 MB)

Stochastic consolidation of lifelong memoryAbstract. Scientific Reports 12, (2022).
s41598-022-16407-9.pdf (2.54 MB)

Synthesizing theories of human language with Bayesian program inductionAbstract. Nature Communications 13, (2022).
s41467-022-32012-w.pdf (2.19 MB)

System identification of neural systems: If we got it right, would we know?. (2022).
CBMM-Memo-136.pdf (1.75 MB)

Task-specific neural processes underlying conflict resolution during cognitive control. BioRxiv (2022). doi:10.1101/2022.01.16.476535
2022.01.16.476535v1.full_.pdf (22.96 MB)

Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations. (2022).
CBMM-Memo-119.pdf (31.08 MB)

Trajectory Prediction with Linguistic Representations. (2022).
CBMM-Memo-132.pdf (1.15 MB)

Transformer Module Networks for Systematic Generalization in Visual Question Answering. (2022).
CBMM-Memo-121.pdf (1.06 MB)

Understanding the Role of Recurrent Connections in Assembly Calculus. (2022).
CBMM-Memo-137.pdf (1.49 MB)

Using child‐friendly movie stimuli to study the development of face, place, and object regions from age 3 to 12 years. Human Brain Mapping (2022). doi:10.1002/hbm.25815
When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations. Nature Machine Intelligence 4, 146 - 153 (2022).