Publication
For HyperBFs AGOP is a greedy approximation to gradient descent. (2024).
CBMM-Memo-148.pdf (1.06 MB)
Formation of Representations in Neural Networks. (2024).
CBMM-Memo-150.pdf (4.03 MB)
Fast iterative regularization by reusing dataAbstract. Journal of Inverse and Ill-posed Problems (2023). doi:10.1515/jiip-2023-0009
Feature learning in deep classifiers through Intermediate Neural Collapse. (2023).
Feature_Learning_memo.pdf (2.16 MB)
For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability. Analysis and Applications 21, 193 - 215 (2023).
Face neurons encode nonsemantic features. Proceedings of the National Academy of Sciences 119, (2022).
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks. International Conference on Learning Representations (ICLR) (2022). at <https://openreview.net/forum?id=yeP_zx9vqNm>
A fast link between face perception and memory in the temporal pole. Science eabi6671 (2021). doi:10.1126/science.abi6671
Fast Recurrent Processing via Ventrolateral Prefrontal Cortex Is Needed by the Primate Ventral Stream for Robust Core Visual Object Recognition. Neuron 109, 164 - 176.e5 (2021).
Flexible modulation of sequence generation in the entorhinal-hippocampal system. Nature Neuroscience (2021). doi:10.1038/s41593-021-00831-7
Frivolous Units: Wider Networks Are Not Really That Wide. AAAI 2021 (2021). at <https://dblp.org/rec/conf/aaai/CasperBDGSVK21.html>
1912.04783.pdf (6.69 MB)
From Associative Memories to Powerful Machines. (2021).
v1.0 (1.01 MB)
v1.3Section added August 6 on self attention (3.9 MB)
From Marr’s Vision to the Problem of Human Intelligence. (2021).
CBMM-Memo-118.pdf (362.19 KB)
Fast Recurrent Processing via Ventrolateral Prefrontal Cortex Is Needed by the Primate Ventral Stream for Robust Core Visual Object Recognition. Neuron (2020). doi:10.1016/j.neuron.2020.09.035
PIIS0896627320307595.pdf (3.92 MB)
The fine structure of surprise in intuitive physics: when, why, and how much?. Proceedings of the 42th Annual Meeting of the Cognitive Science Society - Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020, virtual, July 29 - August 1, 2020 () (2020). at <https://cogsci.mindmodeling.org/2020/papers/0761/index.html>
For interpolating kernel machines, the minimum norm ERM solution is the most stable. (2020).
CBMM_Memo_108.pdf (1015.14 KB)
Better bound (without inequalities!) (1.03 MB)
Function approximation by deep networks. Communications on Pure & Applied Analysis 19, 4085 - 4095 (2020).
1534-0392_2020_8_4085.pdf (514.57 KB)
Facial Expression Scoring and Assessment of Facial Movement Kinematics in Non-Human Primates. The Rockefeller University 2019 Summer Science Research Program (SSRP) (2019).
Deep Learning: Algorithms and Applications (SPRINGER-VERLAG, 2019).
Finding Friend and Foe in Multi-Agent Games. Neural Information Processing Systems (NeurIPS 2019) (2019).
Max KW paper.pdf (928.96 KB)
A fast, invariant representation for human action in the visual system. Journal of Neurophysiology (2018). doi:https://doi.org/10.1152/jn.00642.2017
Finding any Waldo with zero-shot invariant and efficient visual search. Nature Communications 9, (2018).
From Map Reading to Geometric Intuitions. Developmental Psychology (2018). doi:http://dx.doi.org/10.1037/dev0000509
]