Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.

<p>Left: No regularization, Right: With activity regularization. Dotted line: p < 0.05. Solid line: p < 0.0001.</p>

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Dirk Gütlin (22566778) (author)
مؤلفون آخرون: Ryszard Auksztulewicz (4640515) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852015126898540544
author Dirk Gütlin (22566778)
author2 Ryszard Auksztulewicz (4640515)
author2_role author
author_facet Dirk Gütlin (22566778)
Ryszard Auksztulewicz (4640515)
author_role author
dc.creator.none.fl_str_mv Dirk Gütlin (22566778)
Ryszard Auksztulewicz (4640515)
dc.date.none.fl_str_mv 2025-11-05T18:26:33Z
dc.identifier.none.fl_str_mv 10.1371/journal.pcsy.0000076.g006
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Learning_Performance_evaluated_by_classification_accuracy_of_the_original_stimulus_classes_based_on_the_output_encoding_of_the_neural_network_models_/30544054
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biophysics
Neuroscience
Physiology
Science Policy
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
without evaluating whether
like effects across
like behaviors better
including mismatch responses
biological neural networks
compared two pc
advancing brain modelling
inspired training objectives
like responses
training algorithms
neural learning
work contributes
underlying mechanisms
semantic information
saving principles
results show
promising foundation
pc framework
neuroscientific theory
key signatures
inspired algorithms
important mechanism
gain control
findings indicate
dnn ).
contrastive approach
accurately reflect
dc.title.none.fl_str_mv Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Left: No regularization, Right: With activity regularization. Dotted line: p < 0.05. Solid line: p < 0.0001.</p>
eu_rights_str_mv openAccess
id Manara_bd55daa2ee6a666f1017c7bf4b53439b
identifier_str_mv 10.1371/journal.pcsy.0000076.g006
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30544054
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.Dirk Gütlin (22566778)Ryszard Auksztulewicz (4640515)BiophysicsNeurosciencePhysiologyScience PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedwithout evaluating whetherlike effects acrosslike behaviors betterincluding mismatch responsesbiological neural networkscompared two pcadvancing brain modellinginspired training objectiveslike responsestraining algorithmsneural learningwork contributesunderlying mechanismssemantic informationsaving principlesresults showpromising foundationpc frameworkneuroscientific theorykey signaturesinspired algorithmsimportant mechanismgain controlfindings indicatednn ).contrastive approachaccurately reflect<p>Left: No regularization, Right: With activity regularization. Dotted line: p < 0.05. Solid line: p < 0.0001.</p>2025-11-05T18:26:33ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pcsy.0000076.g006https://figshare.com/articles/figure/Learning_Performance_evaluated_by_classification_accuracy_of_the_original_stimulus_classes_based_on_the_output_encoding_of_the_neural_network_models_/30544054CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/305440542025-11-05T18:26:33Z
spellingShingle Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
Dirk Gütlin (22566778)
Biophysics
Neuroscience
Physiology
Science Policy
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
without evaluating whether
like effects across
like behaviors better
including mismatch responses
biological neural networks
compared two pc
advancing brain modelling
inspired training objectives
like responses
training algorithms
neural learning
work contributes
underlying mechanisms
semantic information
saving principles
results show
promising foundation
pc framework
neuroscientific theory
key signatures
inspired algorithms
important mechanism
gain control
findings indicate
dnn ).
contrastive approach
accurately reflect
status_str publishedVersion
title Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
title_full Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
title_fullStr Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
title_full_unstemmed Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
title_short Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
title_sort Learning Performance evaluated by classification accuracy of the original stimulus classes based on the output encoding of the neural network models.
topic Biophysics
Neuroscience
Physiology
Science Policy
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
without evaluating whether
like effects across
like behaviors better
including mismatch responses
biological neural networks
compared two pc
advancing brain modelling
inspired training objectives
like responses
training algorithms
neural learning
work contributes
underlying mechanisms
semantic information
saving principles
results show
promising foundation
pc framework
neuroscientific theory
key signatures
inspired algorithms
important mechanism
gain control
findings indicate
dnn ).
contrastive approach
accurately reflect