MétaCan
Menu
Back to cohort
Record W2775632911 · doi:10.15353/vsnl.v3i1.175

Estimating Optimal Depth of VGG Net with Tree-Structured Parzen Estimators

2017· article· en· W2775632911 on OpenAlexaffvenue
Sunghwan Yoo, Masoom A. Haider, Farzad Khalvati

Bibliographic record

VenueJournal of Computational Vision and Imaging Systems · 2017
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsSunnybrook HospitalUniversity of Toronto
Fundersnot available
KeywordsEstimatorComputer scienceComputationConvolutional neural networkGridTree (set theory)ArchitectureArtificial intelligencePattern recognition (psychology)AlgorithmMathematicsStatistics

Abstract

fetched live from OpenAlex

Deep convolutional neural networks (CNNs) have shown astonishingperformances in variety of fields. However, different architecturesof the networks are required for different datasets, and findingright architecture for given data has been a topic of great interest incomputer vision communities. One of the most important factors ofthe CNNs architecture is the depth of the networks, which plays asignificant role in avoiding over-fitting. Grid Search is widely usedfor estimating the depth, but it requires huge computation time. Motivatedby this, a method for finding an optimal architecture depth isintroduced, which is based on a hyper-parameter optimizer calledTree-Structured Parzen Estimators (TPE). In this work, we showthat the TPE is capable of estimating the CNNs architecture depthwith an accuracy of 83.33% with CIFAR-10 dataset and 60.00%with CIFAR-100 dataset while it reduces the computation time bymore 70% compared to the Grid Search.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.008
Threshold uncertainty score0.017

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.005
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.003
Open science0.0010.001
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.298
Teacher spread0.286 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2017
Admission routes2
Has abstractyes

Explore more

Same venueJournal of Computational Vision and Imaging SystemsSame topicAdvanced Neural Network ApplicationsFrench-language works237,207