MétaCan
Menu
Back to cohort
Record W4285787112 · doi:10.48550/arxiv.1909.02562

TFCheck : A TensorFlow Library for Detecting Training Issues in Neural\n Network Programs

2019· preprint· en· W4285787112 on OpenAlexaff
Houssem Ben Braiek, Foutse Khomh

Bibliographic record

VenuearXiv (Cornell University) · 2019
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsPolytechnique Montréal
Fundersnot available
KeywordsComputer scienceImplementationMachine learningCode (set theory)Artificial intelligenceProcess (computing)Training setArtificial neural networkTraining (meteorology)Focus (optics)Software engineeringProgramming languageSet (abstract data type)

Abstract

fetched live from OpenAlex

The increasing inclusion of Machine Learning (ML) models in safety critical\nsystems like autonomous cars have led to the development of multiple\nmodel-based ML testing techniques. One common denominator of these testing\ntechniques is their assumption that training programs are adequate and\nbug-free. These techniques only focus on assessing the performance of the\nconstructed model using manually labeled data or automatically generated data.\nHowever, their assumptions about the training program are not always true as\ntraining programs can contain inconsistencies and bugs. In this paper, we\nexamine training issues in ML programs and propose a catalog of verification\nroutines that can be used to detect the identified issues, automatically. We\nimplemented the routines in a Tensorflow-based library named TFCheck. Using\nTFCheck, practitioners can detect the aforementioned issues automatically. To\nassess the effectiveness of TFCheck, we conducted a case study with real-world,\nmutants, and synthetic training programs. Results show that TFCheck can\nsuccessfully detect training issues in ML code implementations.\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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.742
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0030.003
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.092
GPT teacher head0.220
Teacher spread0.128 · 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 teacher head, not a consensus.

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

Citations0
Published2019
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdversarial Robustness in Machine LearningFrench-language works237,207