MétaCan
Menu
Back to cohort
Record W2891926718 · doi:10.48550/arxiv.1709.02043

The Mating Rituals of Deep Neural Networks: Learning Compact Feature\n Representations through Sexual Evolutionary Synthesis

2017· preprint· en· W2891926718 on OpenAlexaff
Paul Fieguth, Wong Alexander

Bibliographic record

VenuearXiv (Cornell University) · 2017
Typepreprint
Languageen
FieldComputer Science
TopicGenerative Adversarial Networks and Image Synthesis
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsMNIST databaseArtificial intelligenceModern evolutionary synthesisComputer scienceArtificial neural networkEvolutionary algorithmFeature (linguistics)MatingEvolutionary programmingMachine learningBiologyEvolutionary biologyEcology

Abstract

fetched live from OpenAlex

Evolutionary deep intelligence was recently proposed as a method for\nachieving highly efficient deep neural network architectures over successive\ngenerations. Drawing inspiration from nature, we propose the incorporation of\nsexual evolutionary synthesis. Rather than the current asexual synthesis of\nnetworks, we aim to produce more compact feature representations by\nsynthesizing more diverse and generalizable offspring networks in subsequent\ngenerations via the combination of two parent networks. Experimental results\nwere obtained using the MNIST and CIFAR-10 datasets, and showed improved\narchitectural efficiency and comparable testing accuracy relative to the\nbaseline asexual evolutionary neural networks. In particular, the network\nsynthesized via sexual evolutionary synthesis for MNIST had approximately\ndouble the architectural efficiency (cluster efficiency of 34.29X and synaptic\nefficiency of 258.37X) in comparison to the network synthesized via asexual\nevolutionary synthesis, with both networks achieving a testing accuracy of\n~97%.\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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
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 score0.982
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0020.000
Scholarly communication0.0000.001
Open science0.0030.002
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 head0.065
GPT teacher head0.226
Teacher spread0.161 · 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
Published2017
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicGenerative Adversarial Networks and Image SynthesisFrench-language works237,207