High-performing neural network models of visual cortex benefit from high latent dimensionality.

High-performing neural network models of visual cortex benefit from high latent dimensionality.

Geometric descriptions of deep neural networks (DNNs) have the potential to uncover core representational principles of computational models in neuroscience. Here we examined the geometry of DNN models of visual cortex by quantifying the latent dimensionality of their natural image representations....

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Eric Elmoznino, Michael F Bonner
Format:	Article
Sprog:	English
Udgivet:	Public Library of Science (PLoS) 2024-01-01
Serier:	PLoS Computational Biology
Online adgang:	https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011792&type=printable

Lignende værker

High-level visual prediction errors in early visual cortex
af: David Richter, et al.
Udgivet: (2024-11-01)

High-level visual prediction errors in early visual cortex.
af: David Richter, et al.
Udgivet: (2024-11-01)

Performance-optimized hierarchical models predict neural responses in higher visual cortex
af: Yamins, Daniel L. K., et al.
Udgivet: (2015)

Organization of high-level visual cortex in human infants
af: Keil, Boris, et al.
Udgivet: (2017)

An emerging view of neural geometry in motor cortex supports high-performance decoding
af: Sean M Perkins, et al.
Udgivet: (2025-02-01)

Liouville Integrability in a Four-Dimensional Model of the Visual Cortex
af: Ivan Galyaev, et al.
Udgivet: (2021-12-01)

High baseline activity in inferior temporal cortex improves neural and behavioral discriminability during visual categorization
af: Emadi, Nazli, et al.
Udgivet: (2014)

Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
af: Liao, Qianli, et al.
Udgivet: (2016)

Chip-Based High-Dimensional Optical Neural Network
af: Wang, Xinyu, et al.
Udgivet: (2022)

On nonlinearity in neural encoding models applied to the primary visual cortex.
af: Vidaurre, D, et al.
Udgivet: (2011)

Neural Pathways Conveying Novisual Information to the Visual Cortex
af: Wen Qin, et al.
Udgivet: (2013-01-01)

Neural correlates of perisaccadic visual mislocalization in extrastriate cortex
af: Geyu Weng, et al.
Udgivet: (2024-07-01)

Neural Regression, Representational Similarity, Model Zoology Neural Taskonomy at Scale in Rodent Visual Cortex
af: Conwell, Colin, et al.
Udgivet: (2022)

The maturation of infant and toddler visual cortex neural activity and associations with fine motor performance
af: Katharina Otten, et al.
Udgivet: (2025-01-01)

Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
af: Cadieu, Charles, et al.
Udgivet: (2014)

New Estimators of the Bayes Factor for Models with High-Dimensional Parameter and/or Latent Variable Spaces
af: Anna Pajor
Udgivet: (2021-03-01)

Complex-valued neural networks : utilizing high-dimensional parameters /
af: Nitta, Tohru, 1960-
Udgivet: (c200)

High-Resolution Neural Network for Driver Visual Attention Prediction
af: Byeongkeun Kang, et al.
Udgivet: (2020-04-01)

The Functional Network of the Visual Cortex Is Altered in Migraine
af: Jie Huang, et al.
Udgivet: (2021-11-01)

Node Detection Using High-Dimensional Fuzzy Parcellation Applied to the Insular Cortex
af: Ugo Vercelli, et al.
Udgivet: (2016-01-01)

Latent Diffusion Models to Enhance the Performance of Visual Defect Segmentation Networks in Steel Surface Inspection
af: Jon Leiñena, et al.
Udgivet: (2024-09-01)

Enhancing LS-PIE’s Optimal Latent Dimensional Identification: Latent Expansion and Latent Condensation
af: Jesse Stevens, et al.
Udgivet: (2024-08-01)

Multi-classification for high-dimensional data using probabilistic neural networks
af: Jingyi Li, et al.
Udgivet: (2022-06-01)

Deterministic projection by growing cell structure networks for visualization of high-dimensionality datasets.
af: Wong, J, et al.
Udgivet: (2005)

The neural origin for asymmetric coding of surface color in the primate visual cortex
af: Yujie Wu, et al.
Udgivet: (2024-01-01)

The relationship between depth perception and neural activity in primary visual cortex
af: Cumming, BG, et al.
Udgivet: (1997)

Symphony in the latent space: provably integrating high-dimensional techniques with non-linear machine learning models
af: Wu, Q, et al.
Udgivet: (2023)

Interocular suppression in the primary visual cortex: a possible neural basis of binocular rivalry
af: Sengpiel, F, et al.
Udgivet: (1995)

Hyperacuity and the visual cortex.
af: Parker, A, et al.
Udgivet: (1987)

High-Frequency, Long-Range Coupling Between Prefrontal and Visual Cortex During Attention
af: Gregoriou, Georgia G., et al.
Udgivet: (2014)

Benchmarking Artificial Neural Network Architectures for High-Performance Spiking Neural Networks
af: Riadul Islam, et al.
Udgivet: (2024-02-01)

Ventromedial prefrontal cortex encodes a latent estimate of cumulative reward.
af: Juechems, K, et al.
Udgivet: (2017)

Nonparametric Estimation for High-Dimensional Space Models Based on a Deep Neural Network
af: Hongxia Wang, et al.
Udgivet: (2023-09-01)

Feature selection for high-dimensional neural network potentials with the adaptive group lasso
af: Johannes Sandberg, et al.
Udgivet: (2024-01-01)

Topics in Sparsity and Compression: From High dimensional statistics to Overparametrized Neural Networks
af: Benbaki, Riade
Udgivet: (2023)

Local prediction-learning in high-dimensional spaces enables neural networks to plan
af: Christoph Stöckl, et al.
Udgivet: (2024-03-01)

Solve High-Dimensional Reflected Partial Differential Equations by Neural Network Method
af: Xiaowen Shi, et al.
Udgivet: (2023-06-01)

Convolutional neural networks develop major organizational principles of early visual cortex when enhanced with retinal sampling
af: Danny da Costa, et al.
Udgivet: (2024-04-01)

A Bayesian Gaussian Process-Based Latent Discriminative Generative Decoder (LDGD) Model for High-Dimensional Data
af: Navid Ziaei, et al.
Udgivet: (2024-01-01)

High performance artificial visual perception and recognition with a plasmon-enhanced 2D material neural network
af: Tian Zhang, et al.
Udgivet: (2024-03-01)