MétaCan
Menu
Back to cohort
Record W4311681113 · doi:10.22215/etd/2022-15289

Optimization of Convolutional Neural Networks for Constrained Devices through Binarization

2022· dissertation· en· W4311681113 on OpenAlexaff
Kaveh Rouhandeh

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer scienceConvolutional neural networkQuantization (signal processing)Artificial intelligenceConvolution (computer science)Artificial neural networkBinary numberFeature extractionDeep learningPattern recognition (psychology)Constrained optimization problemFeature (linguistics)AlgorithmOptimization problemMathematics

Abstract

fetched live from OpenAlex

CNNs are the most common branch of Deep Neural Networks (DNNs), and they are structures with a strong capability for feature extraction. By using CNNs, a nonlinear model is trained to map an input space to a corresponding output space. These highperformance CNNs come with a high computational cost and the need for huge memory storage due to the chains of many Convolutional Layers (usually more than 50 layers). To address these issues, a variety of algorithms have been proposed in recent years. In this research, we present a solution that is a combination of several different approaches. and based on matrix optimization, parameters binary quantization, and data parallelism programming techniques. We show that our method significantly outperforms the current conventional PyTorch convolution operation with less memory usage and better computational budget when tested in different scenarios.

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: Methods · Consensus signal: Methods
Teacher disagreement score0.365
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
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 head0.019
GPT teacher head0.293
Teacher spread0.273 · 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
GenreMethods

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
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Neural Network ApplicationsFrench-language works237,207