Visual Image Reconstructed Without Semantics from Human Brain Activity Using Linear Image Decoders and Nonlinear Noise Suppression

In recent years, substantial strides have been made in the field of visual image reconstruction, particularly in its capacity to generate high-quality visual representations from human brain activity while considering semantic information. This advancement not only enables the recreation of visual c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:bioRxiv
1. Verfasser: Li, Qiang
Format: Paper
Sprache:Englisch
Veröffentlicht: Cold Spring Harbor Cold Spring Harbor Laboratory Press 31.12.2024
Cold Spring Harbor Laboratory
Ausgabe:1.6
Schlagworte:
ISSN:2692-8205, 2692-8205
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In recent years, substantial strides have been made in the field of visual image reconstruction, particularly in its capacity to generate high-quality visual representations from human brain activity while considering semantic information. This advancement not only enables the recreation of visual content but also provides valuable insights into the intricate processes occurring within high-order functional brain regions, contributing to a deeper understanding of brain function. However, considering fusion semantics in reconstructing visual images from brain activity involves semantic-to-image guide reconstruction and may ignore underlying neural computational mechanisms, which does not represent true reconstruction from brain activity. In response to this limitation, our study introduces a novel approach that combines linear mapping with nonlinear noise suppression to reconstruct visual images perceived by subjects based on their brain activity patterns. The primary challenge associated with linear mapping lies in its susceptibility to noise interference. To address this issue, we leverage a flexible denoised deep convolutional neural network, which can suppress noise from linear mapping. Our investigation encompasses linear mapping as well as the training of shallow and deep autoencoder denoised neural networks, including a pre-trained, state-of-the-art denoised neural network. The outcome of our study reveals that combining linear image decoding with nonlinear noise reduction significantly enhances the quality of reconstructed images from human brain activity. This suggests that our methodology holds promise for decoding intricate perceptual experiences directly from brain activity patterns without semantic information. Moreover, the model has strong neural explanatory power because it shares structural and functional similarities with the visual brain.Competing Interest StatementThe authors have declared no competing interest.Footnotes* Updated the references and the text.
AbstractList In recent years, substantial strides have been made in the field of visual image reconstruction, particularly in its capacity to generate high-quality visual representations from human brain activity while considering semantic information. This advancement not only enables the recreation of visual content but also provides valuable insights into the intricate processes occurring within high-order functional brain regions, contributing to a deeper understanding of brain function. However, considering fusion semantics in reconstructing visual images from brain activity involves semantic-to-image guide reconstruction and may ignore underlying neural computational mechanisms, which does not represent true reconstruction from brain activity. In response to this limitation, our study introduces a novel approach that combines linear mapping with nonlinear noise suppression to reconstruct visual images perceived by subjects based on their brain activity patterns. The primary challenge associated with linear mapping lies in its susceptibility to noise interference. To address this issue, we leverage a flexible denoised deep convolutional neural network, which can suppress noise from linear mapping. Our investigation encompasses linear mapping as well as the training of shallow and deep autoencoder denoised neural networks, including a pre-trained, state-of-the-art denoised neural network. The outcome of our study reveals that combining linear image decoding with nonlinear noise reduction significantly enhances the quality of reconstructed images from human brain activity. This suggests that our methodology holds promise for decoding intricate perceptual experiences directly from brain activity patterns without semantic information. Moreover, the model has strong neural explanatory power because it shares structural and functional similarities with the visual brain.
In recent years, substantial strides have been made in the field of visual image reconstruction, particularly in its capacity to generate high-quality visual representations from human brain activity while considering semantic information. This advancement not only enables the recreation of visual content but also provides valuable insights into the intricate processes occurring within high-order functional brain regions, contributing to a deeper understanding of brain function. However, considering fusion semantics in reconstructing visual images from brain activity involves semantic-to-image guide reconstruction and may ignore underlying neural computational mechanisms, which does not represent true reconstruction from brain activity. In response to this limitation, our study introduces a novel approach that combines linear mapping with nonlinear noise suppression to reconstruct visual images perceived by subjects based on their brain activity patterns. The primary challenge associated with linear mapping lies in its susceptibility to noise interference. To address this issue, we leverage a flexible denoised deep convolutional neural network, which can suppress noise from linear mapping. Our investigation encompasses linear mapping as well as the training of shallow and deep autoencoder denoised neural networks, including a pre-trained, state-of-the-art denoised neural network. The outcome of our study reveals that combining linear image decoding with nonlinear noise reduction significantly enhances the quality of reconstructed images from human brain activity. This suggests that our methodology holds promise for decoding intricate perceptual experiences directly from brain activity patterns without semantic information. Moreover, the model has strong neural explanatory power because it shares structural and functional similarities with the visual brain.Competing Interest StatementThe authors have declared no competing interest.Footnotes* Updated the references and the text.
Author Li, Qiang
Author_xml – sequence: 1
  givenname: Qiang
  surname: Li
  fullname: Li, Qiang
BookMark eNpNUE1PAjEUbAwmIvIDvDXx4gVsu90tPSJ-QEIwEdHjprRvsQRabHeJXP3l1sDBy7w3700mk7lELecdIHRNSZ9SQu8YYVmfyH7CPJeUizPUZoVkvQEjeevffoG6Ma4JIUwWNBO8jX7ebWzUBk-2agX4FbR3sQ6NrsHgD1t_-qbGc9gqV1sdcRX8Fo-bRPF9UNbhoa7t3tYHvIjWrfDUOlDhZPaQzAyEiJUzeObd5viceRsBz5vdLkCM1rsrdF6pTYTuaXbQ4unxbTTuTV-eJ6PhtLekhIueGMiCZULkRkFRcC5FxXUGQIHLwogCNNdLkagy2lTUZEoQYvKcawNVOmQddHv0XVofvu2-3AW7VeFQ_tVXElkmPNaXpDdH6S74rwZiXa59E1xKVzLJBiK1Lkn2C2jpc1w
ContentType Paper
Copyright 2024. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (“the License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2024, Posted by Cold Spring Harbor Laboratory
Copyright_xml – notice: 2024. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (“the License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2024, Posted by Cold Spring Harbor Laboratory
DBID 8FE
8FH
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
GNUQQ
HCIFZ
LK8
M7P
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
FX.
DOI 10.1101/2023.09.23.559147
DatabaseName ProQuest SciTech Collection
ProQuest Natural Science Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
Natural Science Collection
ProQuest One Community College
ProQuest Central
ProQuest Central Student
SciTech Premium Collection
ProQuest Biological Science Collection
ProQuest Biological Science
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
bioRxiv
DatabaseTitle Publicly Available Content Database
ProQuest Central Student
ProQuest One Academic Middle East (New)
ProQuest Biological Science Collection
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Natural Science Collection
Biological Science Database
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
Natural Science Collection
ProQuest Central Korea
Biological Science Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: ProQuest Publicly Available Content
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 2692-8205
Edition 1.6
ExternalDocumentID 2023.09.23.559147v6
Genre Working Paper/Pre-Print
GroupedDBID 8FE
8FH
ABUWG
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
GNUQQ
HCIFZ
LK8
M7P
NQS
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PROAC
RHI
FX.
ID FETCH-LOGICAL-b1047-789623775dae664497f4c3ee1e496d76ec4cb7e1eadcdf1d3a700d554cdefdf13
IEDL.DBID BENPR
ISSN 2692-8205
IngestDate Thu Jan 02 20:48:46 EST 2025
Fri Jul 25 09:22:10 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Keywords Functional Similarities
Visual Image Reconstruction
Neural Explanatory
Linear Decoding
Deep Autoencoder Denoised Neural Networks
Brain Activity
Language English
License This pre-print is available under a Creative Commons License (Attribution-NonCommercial-NoDerivs 4.0 International), CC BY-NC-ND 4.0, as described at http://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-b1047-789623775dae664497f4c3ee1e496d76ec4cb7e1eadcdf1d3a700d554cdefdf13
Notes SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
Competing Interest Statement: The authors have declared no competing interest.
ORCID 0000-0002-5337-0676
OpenAccessLink https://www.proquest.com/docview/2928711090?pq-origsite=%requestingapplication%
PQID 2928711090
PQPubID 2050091
PageCount 11
ParticipantIDs biorxiv_primary_2023_09_23_559147
proquest_journals_2928711090
PublicationCentury 2000
PublicationDate 20241231
PublicationDateYYYYMMDD 2024-12-31
PublicationDate_xml – month: 12
  year: 2024
  text: 20241231
  day: 31
PublicationDecade 2020
PublicationPlace Cold Spring Harbor
PublicationPlace_xml – name: Cold Spring Harbor
PublicationTitle bioRxiv
PublicationYear 2024
Publisher Cold Spring Harbor Laboratory Press
Cold Spring Harbor Laboratory
Publisher_xml – name: Cold Spring Harbor Laboratory Press
– name: Cold Spring Harbor Laboratory
References Thirion (2023.09.23.559147v6.18) 2007; 33
Zhang, Zuo, Chen, Meng, Zhang (2023.09.23.559147v6.24) 2016
Li (2023.09.23.559147v6.57) 2022
Hurvich, Jameson (2023.09.23.559147v6.45) 1957; 64
Conway, Malik-Moraleda, Gibson (2023.09.23.559147v6.48) 2023
Li, Gomez-Villa, Bertalmío, Malo (2023.09.23.559147v6.31) 2022; 22
Raghavan, Thomson (2023.09.23.559147v6.21) 2019
Shen, Dwivedi, Majima, Horikawa, Kamitani (2023.09.23.559147v6.13) 2019; 13
Hochreiter, Schmidhuber (2023.09.23.559147v6.34) 1997; 9
Chang (2023.09.23.559147v6.37) 2019; 6
Kamitani, Tong (2023.09.23.559147v6.17) 2005; 8
Huang (2023.09.23.559147v6.36) 2024; 112
Mordvintsev, Olah, Tyka (2023.09.23.559147v6.40) 2015
Allen (2023.09.23.559147v6.53) 2021
Power (2023.09.23.559147v6.1) 2011; 72
Ren (2023.09.23.559147v6.15) 2021; 228
Miyawaki (2023.09.23.559147v6.6) 2009; 60
Goodfellow (2023.09.23.559147v6.33) 2014; 27
Bontempi (2023.09.23.559147v6.38) 2021
Li (2023.09.23.559147v6.23) 2023; 34
Yamins, Hong, Cadieu, DiCarlo (2023.09.23.559147v6.43) 2013; 26
Li, Steeg, Yu, Malo (2023.09.23.559147v6.54) 2022; 24
Schurgin (2023.09.23.559147v6.4) 2018; 80
Park, Friston (2023.09.23.559147v6.2) 2013; 342
Liu (2023.09.23.559147v6.8) 2016; 143
Fujiwara, Miyawaki, Kamitani (2023.09.23.559147v6.11) 2009; 22
Quan, Chen, Pang, Ji (2023.09.23.559147v6.29) 2020
Zhang, Zuo, Zhang (2023.09.23.559147v6.25) 2017
Stanley, Li, Dan (2023.09.23.559147v6.30) 1999; 19
Naselaris, Prenger, Kay, Oliver, Gallant (2023.09.23.559147v6.19) 2009; 63
Abdelhack, Kamitani (2023.09.23.559147v6.49) 2018; 5
Li, Calhoun, Iraji (2023.09.23.559147v6.3) 2024; 822
Kay, Naselaris, Prenger, Gallant (2023.09.23.559147v6.20) 2008; 452
Nishimoto (2023.09.23.559147v6.16) 2011; 21
Buchsbaum, Gottschalk (2023.09.23.559147v6.46) 1983; 220
Soh, Cho (2023.09.23.559147v6.52) 2021
Naselaris, Kay, Nishimoto, Gallant (2023.09.23.559147v6.5) 2011; 56
Krizhevsky, Sutskever, Hinton (2023.09.23.559147v6.39) 2012; 25
Schmidhuber (2023.09.23.559147v6.50) 2014; 61
Li (2023.09.23.559147v6.9) 2022; 146
VanRullen, Reddy (2023.09.23.559147v6.14) 2019; 2
Chang, Cunningham, Glover (2023.09.23.559147v6.7) 2008; 44
Chen, Lin, Wang, Yang, Cheng (2023.09.23.559147v6.27) 2021; 30
Ozcelik, VanRullen (2023.09.23.559147v6.32) 2023; 13
Ulyanov, Vedaldi, Lempitsky (2023.09.23.559147v6.28) 2020; 128
Li, Ver Steeg, Malo (2023.09.23.559147v6.55) 2023; 571
Li (2023.09.23.559147v6.56) 2021
Hering (2023.09.23.559147v6.47) 1878
Guo, Yan, Zhang, Zuo, Zhang (2023.09.23.559147v6.26) 2019
Li, Fergus, Perona, Zekrifa (2023.09.23.559147v6.51) 2013; 106
Szegedy (2023.09.23.559147v6.41) 2015
Li, Calhoun, Pham, Iraji (2023.09.23.559147v6.10) 2024; 34
Shen, Horikawa, Majima, Kamitani (2023.09.23.559147v6.12) 2019; 15
Yamins, DiCarlo (2023.09.23.559147v6.42) 2016; 19
Hartmann, Lazar, Nessler, Triesch (2023.09.23.559147v6.22) 2015; 11
Cadieu (2023.09.23.559147v6.44) 2014; 10
Maass (2023.09.23.559147v6.35) 1997; 10
References_xml – volume: 220
  start-page: 113
  year: 1983
  end-page: 89
  ident: 2023.09.23.559147v6.46
  article-title: Trichromacy, opponent colours coding and optimum colour information transmission in the retina
  publication-title: Proceedings of the Royal Society of London. Series B. Biological Sciences
– start-page: 109
  year: 2022
  end-page: 116
  ident: 2023.09.23.559147v6.57
  article-title: Investigate Bidirectional Functional Brain Networks Using Directed Information
  publication-title: in 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
– volume: 143
  year: 2016
  ident: 2023.09.23.559147v6.8
  article-title: Noise contributions to the fMRI signal: An Overview
  publication-title: NeuroImage
– volume: 10
  start-page: 1659
  year: 1997
  end-page: 1671
  ident: 2023.09.23.559147v6.35
  article-title: Networks of spiking neurons: The third generation of neural network models
  publication-title: Neural Networks
– volume: 27
  year: 2014
  ident: 2023.09.23.559147v6.33
  publication-title: in Advances in Neural Information Processing Systems
– year: 2017
  ident: 2023.09.23.559147v6.25
  article-title: FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
  publication-title: IEEE Transactions on Image Processing PP
– volume: 30
  start-page: 2313
  year: 2021
  end-page: 2324
  ident: 2023.09.23.559147v6.27
  article-title: Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation
  publication-title: IEEE Transactions on Image Processing
– volume: 56
  start-page: 400
  year: 2011
  end-page: 10
  ident: 2023.09.23.559147v6.5
  article-title: Encoding and decoding in fMRI
  publication-title: NeuroImage
– volume: 72
  start-page: 665
  year: 2011
  end-page: 678
  ident: 2023.09.23.559147v6.1
  article-title: Functional Network Organization of the Human Brain
  publication-title: Neuron
– year: 2021
  ident: 2023.09.23.559147v6.52
  article-title: Deep Universal Blind Image Denoising
  publication-title: in (25th International Conference on Pattern Recognition, Underline Science I
– year: 2015
  ident: 2023.09.23.559147v6.40
  publication-title: Inceptionism: Going Deeper into Neural Networks
– volume: 44
  start-page: 857
  year: 2008
  end-page: 69
  ident: 2023.09.23.559147v6.7
  article-title: Influence of heart rate on the BOLD signal: The cardiac response function
  publication-title: NeuroImage
– volume: 34
  year: 2023
  ident: 2023.09.23.559147v6.23
  article-title: Saliency prediction based on multi-channel models of visual processing
  publication-title: Machine Vision and Applications
– volume: 15
  start-page: e1006633
  year: 2019
  ident: 2023.09.23.559147v6.12
  article-title: Deep image reconstruction from human brain activity
  publication-title: PLOS Computational Biology
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: 2023.09.23.559147v6.34
  article-title: Long short-term memory
  publication-title: Neural computation
– volume: 13
  year: 2023
  ident: 2023.09.23.559147v6.32
  article-title: Natural scene reconstruction from fMRI signals using generative latent diffusion
  publication-title: Scientific Reports
– volume: 822
  start-page: 137624
  year: 2024
  ident: 2023.09.23.559147v6.3
  article-title: Revealing complex functional topology brain network correspondences between humans and marmosets
  publication-title: Neuroscience Letters
– volume: 26
  year: 2013
  ident: 2023.09.23.559147v6.43
  publication-title: in Advances in Neural Information Processing Systems
– volume: 228
  start-page: 117602
  year: 2021
  ident: 2023.09.23.559147v6.15
  article-title: Reconstructing seen image from brain activity by visually-guided cognitive representation and adversarial learning
  publication-title: NeuroImage
– year: 2016
  ident: 2023.09.23.559147v6.24
  article-title: Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
  publication-title: IEEE Transactions on Image Processing PP
– volume: 22
  year: 2009
  ident: 2023.09.23.559147v6.11
  publication-title: in Advances in Neural Information Processing Systems
– start-page: 1712
  year: 2019
  end-page: 1722
  ident: 2023.09.23.559147v6.26
  article-title: Toward Convolutional Blind Denoising of Real Photographs
  publication-title: in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
– volume: 33
  start-page: 1104
  year: 2007
  end-page: 16
  ident: 2023.09.23.559147v6.18
  article-title: Inverse retinotopy: Inferring the visual content of images from brain activation patterns
  publication-title: NeuroImage
– volume: 60
  start-page: 915
  year: 2009
  end-page: 29
  ident: 2023.09.23.559147v6.6
  article-title: Visual Image Reconstruction from Human Brain Activity using a Combination of Multiscale Local Image Decoders
  publication-title: Neuron
– volume: 34
  year: 2024
  ident: 2023.09.23.559147v6.10
  article-title: Exploring nonlinear dynamics in brain functionality through phase portraits and fuzzy recurrence plots
  publication-title: Chaos: An Interdisciplinary Journal of Nonlinear Science
– volume: 64
  start-page: 384
  year: 1957
  end-page: 404
  ident: 2023.09.23.559147v6.45
  article-title: An opponent-process theory of color vision
  publication-title: Psychological review
– start-page: 1
  year: 2015
  end-page: 9
  ident: 2023.09.23.559147v6.41
  article-title: Going deeper with convolutions
  publication-title: in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
– year: 2021
  ident: 2023.09.23.559147v6.38
  publication-title: “Statistical foundations of machine learning”
– volume: 21
  start-page: 1641
  year: 2011
  end-page: 6
  ident: 2023.09.23.559147v6.16
  article-title: Reconstructing Visual Experiences from Brain Activity Evoked by Natural Movies
  publication-title: Current biology : CB
– volume: 11
  start-page: e1004640
  year: 2015
  ident: 2023.09.23.559147v6.22
  article-title: Where’s the Noise? Key Features of Spontaneous Activity and Neural Variability Arise through Learning in a Deterministic Network
  publication-title: PLoS computational biology
– volume: 5
  year: 2018
  ident: 2023.09.23.559147v6.49
  article-title: Sharpening of Hierarchical Visual Feature Representations of Blurred Images
  publication-title: eneuro
– volume: 10
  start-page: 1
  year: 2014
  end-page: 18
  ident: 2023.09.23.559147v6.44
  article-title: Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
  publication-title: PLOS Computational Biology
– volume: 80
  year: 2018
  ident: 2023.09.23.559147v6.4
  article-title: Visual memory, the long and the short of it: A review of visual working memory and long-term memory
  publication-title: Attention, Perception, Psychophysics
– year: 1878
  ident: 2023.09.23.559147v6.47
  publication-title: Zur Lehre vom Lichtsinne: sechs Mittheilungen an die Kaiser. Akad. der Wissenschaften in Wien
– start-page: 1887
  year: 2020
  end-page: 1895
  ident: 2023.09.23.559147v6.29
  article-title: Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image
  publication-title: in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
– volume: 61
  start-page: 85
  year: 2014
  end-page: 117
  ident: 2023.09.23.559147v6.50
  article-title: Deep learning in neural networks: An overview
  publication-title: Neural networks : the official journal of the International Neural Network Society
– volume: 19
  start-page: 8036
  year: 1999
  end-page: 42
  ident: 2023.09.23.559147v6.30
  article-title: Reconstruction of Natural Scenes from Ensemble Responses in the Lateral Geniculate Nucleus
  publication-title: The Journal of neuroscience : the official journal of the Society for Neuroscience
– volume: 112
  start-page: 102573
  year: 2024
  ident: 2023.09.23.559147v6.36
  article-title: From Sight to Insight: A Multi-task Approach with the Visual Language Decoding Model
  publication-title: Information Fusion
– volume: 6
  year: 2019
  ident: 2023.09.23.559147v6.37
  article-title: BOLD5000, a public fMRI dataset while viewing 5000 visual images
  publication-title: Scientific Data
– year: 2023
  ident: 2023.09.23.559147v6.48
  article-title: Color appearance and the end of Hering’s Opponent-Colors Theory
  publication-title: Trends in Cognitive Sciences
– volume: 22
  start-page: 8
  year: 2022
  end-page: 8
  ident: 2023.09.23.559147v6.31
  article-title: Contrast sensitivity functions in autoencoders
  publication-title: Journal of Vision
– volume: 571
  start-page: 127143
  year: 2023
  ident: 2023.09.23.559147v6.55
  article-title: Functional connectivity via total correlation: Analytical results in visual areas
  publication-title: Neurocomputing
– start-page: 57
  year: 2021
  end-page: 66
  ident: 2023.09.23.559147v6.56
  publication-title: in Brain Informatics
– volume: 106
  start-page: 59
  year: 2013
  end-page: 70
  ident: 2023.09.23.559147v6.51
  article-title: Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
  publication-title: Computer Vision and Image Understanding
– volume: 146
  start-page: 85
  year: 2022
  end-page: 97
  ident: 2023.09.23.559147v6.9
  article-title: Functional connectivity inference from fMRI data using multivariate information measures
  publication-title: Neural Networks
– volume: 25
  year: 2012
  ident: 2023.09.23.559147v6.39
  publication-title: in Advances in Neural Information Processing Systems
– year: 2019
  ident: 2023.09.23.559147v6.21
  publication-title: Neural networks grown and self-organized by noise in NeurIPS
– volume: 2
  year: 2019
  ident: 2023.09.23.559147v6.14
  article-title: Reconstructing faces from fMRI patterns using deep generative neural networks
  publication-title: Communications Biology
– volume: 452
  start-page: 352
  year: 2008
  end-page: 5
  ident: 2023.09.23.559147v6.20
  article-title: Identifying natural images from human brain activity
  publication-title: Nature
– volume: 19
  start-page: 356
  year: 2016
  end-page: 365
  ident: 2023.09.23.559147v6.42
  article-title: Using goal-driven deep learning models to understand sensory cortex
  publication-title: Nat. Neurosci
– year: 2021
  ident: 2023.09.23.559147v6.53
  article-title: A massive 7T fMRI dataset to bridge cognitive and computational neuroscience
  publication-title: bioRxiv
– volume: 13
  start-page: 21
  year: 2019
  ident: 2023.09.23.559147v6.13
  article-title: End-to-End Deep Image Reconstruction From Human Brain Activity
  publication-title: Frontiers in Computational Neuroscience
– volume: 63
  start-page: 902
  year: 2009
  end-page: 15
  ident: 2023.09.23.559147v6.19
  article-title: Bayesian Reconstruction of Natural Images from Human Brain Activity
  publication-title: Neuron
– volume: 8
  start-page: 679
  year: 2005
  end-page: 85
  ident: 2023.09.23.559147v6.17
  article-title: Decoding the visual and subjective contents of the human brain
  publication-title: Nature neuroscience
– volume: 24
  start-page: 1725
  year: 2022
  ident: 2023.09.23.559147v6.54
  article-title: Functional Connectome of the Human Brain with Total Correlation
  publication-title: Entropy
– volume: 342
  start-page: 1238411
  year: 2013
  ident: 2023.09.23.559147v6.2
  article-title: Structural and functional brain networks: from connections to cognition
  publication-title: Science
– volume: 128
  year: 2020
  ident: 2023.09.23.559147v6.28
  article-title: Deep Image Prior
  publication-title: International Journal of Computer Vision
SSID ssj0002961374
Score 1.7445607
SecondaryResourceType preprint
Snippet In recent years, substantial strides have been made in the field of visual image reconstruction, particularly in its capacity to generate high-quality visual...
SourceID biorxiv
proquest
SourceType Open Access Repository
Aggregation Database
SubjectTerms Activity patterns
Brain
Computational neuroscience
Image processing
Neural networks
Neuroimaging
Neuroscience
Noise reduction
Semantics
Structure-function relationships
Title Visual Image Reconstructed Without Semantics from Human Brain Activity Using Linear Image Decoders and Nonlinear Noise Suppression
URI https://www.proquest.com/docview/2928711090
https://www.biorxiv.org/content/10.1101/2023.09.23.559147
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA7qKnjyjY9VIngtdvtItidxfaCgpfj2VNJkigVt1-0qevWXO9NGPQhevATSQCiTyWRmMvk-xnbA1yYIte9kgZs5gQg9B7186ejcy5XuZcI0zHM3ZzKO-3d3UWITbrUtq_yyiY2hNpWmHPmuF5FvT2WEe8Nnh1ij6HbVUmhMsg4hlaGedwZHcXLxnWXxIjyuGihmT0S49T03tFebqIoU-PuEcootOtY9oliZyYpq9Fa8_jLNzXlzPPffP51nnUQNYbTAJqBcZDMt4-T7Evu4KeoX9chPn9COcIo9LYIsGH5bjB-qlzG_hCcUd6FrTm9PeJPm5wOikuD7uiWb4E2lAcdAFjeKnewQ6Hn8qOaqNDxuEThwMK6KGjiRh7YVt-Uyuz4-ujo4cSwNg5M1OA6yH6GPJGVoFAh0nyKZB9oH6EEQCSMF6EBnErvKaJP3jK-k6xp0U7SBHD_4K2yqrEpYZVxJwLkyIcmr8BVkpq9EX2PIB57MRbjGtq3802ELtpHSGqVulGLbrtEa636JPbX7rU5_ZL7-9_AGm8UZLVRjl02hiGGTTevXcVGPtqz6bFEFaIK95PQ8uf8E0ejRNA
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT9wwEB7BUkRP0ELFlpcrlWPUrJPYmwOqeIoVS7QSz56CY0_USJAsm4WWa38Qv5Fxki0HJG4cuFhKLI1kz6d52OP5AL6jp40faM9JfDdxfBFwh6J86eiUp0p3EmEq5rnzvoyi7uVlOJiCx8lbGFtWObGJlaE2hbZn5D94aGN7W0b4c3jrWNYoe7s6odCoYXGED38oZSu3enuk303OD_ZPdw-dhlXASaq2BLIbksuXMjAKBUUDoUx97SF20A-FkQK1rxNJn8pok3aMp6TrGvK62mBKPzySOw0zPoHdbcHMoHc8-PX_VIeH5B6r1s9chGRquBs0V6kEfXvQ4NmuqjRSIN-xlC6zSVaM_mb3L1xB5d8O5t_bzizQjqghjj7BFOafYbZm1HxYhH_nWXmnrlnvhuwks7l10yEXDbvIxr-LuzE7wRuCU6ZLZt_WsOoag-1Yqgy2rWsyDVZVUjBK1GldjbA9tM__RyVTuWFR3WGEJqMiK5FZctS6ojhfgrM3WfYXaOVFjsvAlESSlQhpoyZPYWK6SnQ1pbTIZSqCNnxr9B0P62YiscVE7IYxjTUm2rA6UXPc2JMyftbx19enN2Du8PS4H_d70dEKfCTpTVvKVWjRduMafND346wcrTfQZXD11ph4AvnMLao
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Visual+Image+Reconstructed+Without+Semantics+from+Human+Brain+Activity+Using+Linear+Image+Decoders+and+Nonlinear+Noise+Suppression&rft.jtitle=bioRxiv&rft.au=Li%2C+Qiang&rft.date=2024-12-31&rft.pub=Cold+Spring+Harbor+Laboratory&rft.eissn=2692-8205&rft_id=info:doi/10.1101%2F2023.09.23.559147&rft.externalDocID=2023.09.23.559147v6
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2692-8205&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2692-8205&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2692-8205&client=summon