ViT texture representations align with each other and with human psychophysics better than VGG-19 representations, suggesting architecture drives texture coding more than training objective.
Neocognitron: A self-organizing neural network model for a mecha- nism of pattern recognition unaffected by shift in position.Biological Cybernetics, 36(4): 193–202
8 Pith papers cite this work, alongside 58 external citations. Polarity classification is still indexing.
8
Pith papers citing it
58
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
years
2026 8roles
background 2polarities
background 2representative citing papers
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
A contrastive-learning score periodogram detects shallow 100-150 day transits in Kepler light curves, recovering all 60 known validation signals and outperforming BLS/TLS on low-SNR injections.
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
Holomorphic neural networks enforce exact satisfaction of harmonic PDEs for 3D Laplace and elasticity problems using Whittaker representations and boundary-only training.
A pathway-constrained autoencoder extended to multi-omics integration improves breast cancer stratification and provides interpretable pathway activity scores.
Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.
Joint sparse coding and temporal dynamics in mPFC and computational networks reduce cross-context interference and enhance separability, enabling better retention in lifelong learning without extra heuristics.
citing papers explorer
-
Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
ViT texture representations align with each other and with human psychophysics better than VGG-19 representations, suggesting architecture drives texture coding more than training objective.
-
Unmasking LAION-5B: Age, Gender, Race, and Emotion Biases in Large-Scale Image Datasets
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
-
DELOS: Detecting Shallow Transits in Kepler Photometry Using a Contrastive-Learning Framework
A contrastive-learning score periodogram detects shallow 100-150 day transits in Kepler light curves, recovering all 60 known validation signals and outperforming BLS/TLS on low-SNR injections.
-
Zero-shot World Models Are Developmentally Efficient Learners
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
-
A holomorphic neural network framework for 3D boundary value problems governed by harmonic potentials
Holomorphic neural networks enforce exact satisfaction of harmonic PDEs for 3D Laplace and elasticity problems using Whittaker representations and boundary-only training.
-
Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer
A pathway-constrained autoencoder extended to multi-omics integration improves breast cancer stratification and provides interpretable pathway activity scores.
-
Dual-Stream EEG Decoding for 3D Visual Perception
Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.
-
Joint sparse coding and temporal dynamics support context reconfiguration
Joint sparse coding and temporal dynamics in mPFC and computational networks reduce cross-context interference and enhance separability, enabling better retention in lifelong learning without extra heuristics.