MétaCan
Menu
Back to cohort

A Novel way of Training a Neural Network with Reinforcement learning and without Back Propagation

2020· article· en· W3091080409 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.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicOptimization and Search Problems
Canadian institutionsQueen's UniversityRoyal Military College of Canada
Fundersnot available
KeywordsReinforcement learningComputer scienceArtificial neural networkWorryGradient descentBackpropagationArtificial intelligenceLearning automataCore (optical fiber)Action (physics)Automaton

Abstract

fetched live from OpenAlex

This paper introduces, explores and shows a new way to optimize the weights of a neural network. This new technique does not use back propagation or relies on gradient descent. The core idea is to combine both Game Theory and Reinforcement Learning to train a Neural network. We structure a game of learning automata agents, specifically Continuous Action Learning Automata (CALA) agents, that iteratively converges to a global minimum. Each CALA agent is associated with a weight in a neural network, and when the game converges to a global minimum, we can say that the neural network has been trained. By using a game of CALA agents we can deal with input that has been corrupted by noise, do not have to worry about the vanishing gradient problem or worry about over fitting and is structured better for parallel computing.

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 score0.797
Threshold uncertainty score0.180

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 communication0.0000.000
Open science0.0000.000
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 head0.048
GPT teacher head0.255
Teacher spread0.207 · 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

Quick stats

Citations7
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicOptimization and Search ProblemsFrench-language works237,207