MétaCan
Menu
Back to cohort
Record W2530530944 · doi:10.11159/cdsr16.123

Automated Model Tuning Using A Genetic Algorithm

2016· article· en· W2530530944 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueProceedings of the International Conference of Control, Dynamic systems, and Robotics · 2016
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Multi-Objective Optimization Algorithms
Canadian institutionsCarleton University
FundersNatural Sciences and Engineering Research Council of CanadaMitacsOntario Centres of Excellence
KeywordsComputer scienceGenetic algorithmAlgorithmMachine learning

Abstract

fetched live from OpenAlex

A simple but reliable model tuning method was developed in order to tune a flight model for a high-fidelity type-specific small aircraft simulator. A genetic algorithm (GA) was used as a parameter estimation method. GAs are robust parallel heuristic search methods that often use least squares curve fitting methods to solve complex problems. They belong to the class of evolutionary computing algorithms that mimic natural processes, in this case evolution, to predict behaviour and solve optimization problems. A population of possible solution sets is selected at random and the known math model is then used to determine the behaviour of each of these possible solutions. The behaviour of each is then compared to the desired behaviour of the model, i.e., the reference data set, and the error is calculated. Those with the highest error are culled from the population while those with the lowest error are deemed to be "parents". These parent solution sets are then paired together, to create "children" by finding a weighted average of the parents. To ensure the solution space is fully explored, "mutations" are also created by replacing a single part of select solution sets with a randomly-generated value. Two mutation mechanisms were used in the algorithm described in this paper to ensure that the solution space was explored fully while avoiding convergence on a local, rather than global, minimum. The second generation solution set is 50% comprised of parents, 25% comprised of children, and 25% comprised of mutations. The process repeats until the convergence criteria is met. This algorithm was successfully tested with multiple dynamic systems, including simulated flight test data created using X-Plane, a flight simulator software. The algorithm proved to be a capable and adaptive parameter estimation method applicable to a wide variety of dynamic models, including flight models.

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.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation 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: none
Teacher disagreement score0.655
Threshold uncertainty score0.438

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
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 head0.023
GPT teacher head0.264
Teacher spread0.241 · 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