MétaCan
Menu
Back to cohort
Record W4298733999 · doi:10.48550/arxiv.1605.09332

Parametric Exponential Linear Unit for Deep Convolutional Neural\n Networks

2016· preprint· W4298733999 on OpenAlexaff
Ludovic Trottier, Philippe Giguère, Brahim Chaib-draa

Bibliographic record

VenuearXiv (Cornell University) · 2016
Typepreprint
Language
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsUniversité Laval
Fundersnot available
KeywordsMNIST databaseParametric statisticsConvolutional neural networkComputer scienceArtificial intelligenceSet (abstract data type)Deep learningPattern recognition (psychology)Flexibility (engineering)Artificial neural networkDeep neural networksRealization (probability)Residual neural networkExponential functionMathematics

Abstract

fetched live from OpenAlex

Object recognition is an important task for improving the ability of visual\nsystems to perform complex scene understanding. Recently, the Exponential\nLinear Unit (ELU) has been proposed as a key component for managing bias shift\nin Convolutional Neural Networks (CNNs), but defines a parameter that must be\nset by hand. In this paper, we propose learning a parameterization of ELU in\norder to learn the proper activation shape at each layer in the CNNs. Our\nresults on the MNIST, CIFAR-10/100 and ImageNet datasets using the NiN,\nOverfeat, All-CNN and ResNet networks indicate that our proposed Parametric ELU\n(PELU) has better performances than the non-parametric ELU. We have observed as\nmuch as a 7.28% relative error improvement on ImageNet with the NiN network,\nwith only 0.0003% parameter increase. Our visual examination of the non-linear\nbehaviors adopted by Vgg using PELU shows that the network took advantage of\nthe added flexibility by learning different activations at different layers.\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)0.000
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 score0.964
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.003
Science and technology studies0.0010.001
Scholarly communication0.0000.001
Open science0.0040.003
Research integrity0.0010.001
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 head0.099
GPT teacher head0.222
Teacher spread0.124 · 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

Citations1
Published2016
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdvanced Neural Network ApplicationsFrench-language works237,207