Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.

<p>Fig 8 presents the mean absolute error (MAE) in millimeters as a function of kernel size (in pixels) for two model configurations. The red line, marked with circles, corresponds to the ‘Full Model’, while the blue line, marked with ‘X’ symbols, represents the ‘Reduced Depth’ version. The gr...

Full description

Saved in:
Bibliographic Details
Main Author: Liu Liu (512237) (author)
Other Authors: Zhifei Xu (540854) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852020365473087488
author Liu Liu (512237)
author2 Zhifei Xu (540854)
author2_role author
author_facet Liu Liu (512237)
Zhifei Xu (540854)
author_role author
dc.creator.none.fl_str_mv Liu Liu (512237)
Zhifei Xu (540854)
dc.date.none.fl_str_mv 2025-05-15T17:22:17Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0320777.g008
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Comparison_of_Mean_Absolute_Error_MAE_in_Millimeters_as_a_Function_of_Kernel_Size_/29079942
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Neuroscience
Science Policy
Mental Health
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
agent &# 8217
neural plasticity mechanisms
atari game settings
various performance metrics
standard atari games
neuronal spike timings
methodology leverages mrl
including learning speed
game generalization
dependent plasticity
xlink ">
results show
research explores
learning efficiency
hybrid mrl
deep q
changing conditions
ai agents
dc.title.none.fl_str_mv Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Fig 8 presents the mean absolute error (MAE) in millimeters as a function of kernel size (in pixels) for two model configurations. The red line, marked with circles, corresponds to the ‘Full Model’, while the blue line, marked with ‘X’ symbols, represents the ‘Reduced Depth’ version. The graph tracks the performance of both models across kernel sizes ranging from 100 to 300 pixels. The Full Model generally maintains a lower MAE, suggesting higher accuracy than the Reduced Depth model. Both models show a decrease in MAE as the kernel size increases up to approximately 200 pixels. After this point, the Reduced Depth model’s MAE increases significantly, while the Full Model’s performance stabilizes before slightly increasing again.</p>
eu_rights_str_mv openAccess
id Manara_e2b48906bc7dfdb853dc3f8cd24426cc
identifier_str_mv 10.1371/journal.pone.0320777.g008
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29079942
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.Liu Liu (512237)Zhifei Xu (540854)NeuroscienceScience PolicyMental HealthBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedagent &# 8217neural plasticity mechanismsatari game settingsvarious performance metricsstandard atari gamesneuronal spike timingsmethodology leverages mrlincluding learning speedgame generalizationdependent plasticityxlink ">results showresearch exploreslearning efficiencyhybrid mrldeep qchanging conditionsai agents<p>Fig 8 presents the mean absolute error (MAE) in millimeters as a function of kernel size (in pixels) for two model configurations. The red line, marked with circles, corresponds to the ‘Full Model’, while the blue line, marked with ‘X’ symbols, represents the ‘Reduced Depth’ version. The graph tracks the performance of both models across kernel sizes ranging from 100 to 300 pixels. The Full Model generally maintains a lower MAE, suggesting higher accuracy than the Reduced Depth model. Both models show a decrease in MAE as the kernel size increases up to approximately 200 pixels. After this point, the Reduced Depth model’s MAE increases significantly, while the Full Model’s performance stabilizes before slightly increasing again.</p>2025-05-15T17:22:17ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0320777.g008https://figshare.com/articles/figure/Comparison_of_Mean_Absolute_Error_MAE_in_Millimeters_as_a_Function_of_Kernel_Size_/29079942CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/290799422025-05-15T17:22:17Z
spellingShingle Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
Liu Liu (512237)
Neuroscience
Science Policy
Mental Health
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
agent &# 8217
neural plasticity mechanisms
atari game settings
various performance metrics
standard atari games
neuronal spike timings
methodology leverages mrl
including learning speed
game generalization
dependent plasticity
xlink ">
results show
research explores
learning efficiency
hybrid mrl
deep q
changing conditions
ai agents
status_str publishedVersion
title Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
title_full Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
title_fullStr Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
title_full_unstemmed Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
title_short Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
title_sort Comparison of Mean Absolute Error (MAE) in Millimeters as a Function of Kernel Size.
topic Neuroscience
Science Policy
Mental Health
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
agent &# 8217
neural plasticity mechanisms
atari game settings
various performance metrics
standard atari games
neuronal spike timings
methodology leverages mrl
including learning speed
game generalization
dependent plasticity
xlink ">
results show
research explores
learning efficiency
hybrid mrl
deep q
changing conditions
ai agents