MétaCan
Menu
Back to cohort
Record W4300651176 · doi:10.48550/arxiv.1704.04133

Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR)\n Approach to Understanding Deep Neural Networks

2017· preprint· en· W4300651176 on OpenAlexaff
Devinder Kumar, Alexander Wong, Graham W. Taylor

Bibliographic record

VenuearXiv (Cornell University) · 2017
Typepreprint
Languageen
FieldPsychology
TopicMental Health Research Topics
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsAmbiguityComputer scienceDeep neural networksVisualizationClass (philosophy)Process (computing)Artificial intelligenceMachine learningArtificial neural networkDecision-making

Abstract

fetched live from OpenAlex

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an\napproach to visualize and understand the decisions made by deep neural networks\n(DNNs) given a specific input. CLEAR facilitates the visualization of attentive\nregions and levels of interest of DNNs during the decision-making process. It\nalso enables the visualization of the most dominant classes associated with\nthese attentive regions of interest. As such, CLEAR can mitigate some of the\nshortcomings of heatmap-based methods associated with decision ambiguity, and\nallows for better insights into the decision-making process of DNNs.\nQuantitative and qualitative experiments across three different datasets\ndemonstrate the efficacy of CLEAR for gaining a better understanding of the\ninner workings of DNNs during the decision-making process.\n

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)0.007
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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.007
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.001
Scholarly communication0.0020.004
Open science0.0010.002
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0060.001

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 head0.327
GPT teacher head0.322
Teacher spread0.005 · 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
GenreEmpirical

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

Citations1
Published2017
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicMental Health Research TopicsFrench-language works237,207