MétaCan
Menu
Back to cohort

Learning to Stabilize Extreme Neural Machines with Metaplasticity

2022· article· en· W4312228327 on OpenAlexaff
Megan Boucher-Routhier, Artem Pilzak, Annie Théberge Charbonneau, Jean‐Philippe Thivierge

Bibliographic record

Venue2022 International Joint Conference on Neural Networks (IJCNN) · 2022
Typearticle
Languageen
FieldComputer Science
TopicNeural Networks and Reservoir Computing
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsRecurrent neural networkComputer scienceArtificial intelligenceAmbiguityArtificial neural networkMetaplasticityMachine learningTask (project management)RecallSynaptic plasticityEngineeringPsychologyCognitive psychology

Abstract

fetched live from OpenAlex

Training recurrent reservoir networks to solve complex tasks is a difficult problem due to extensive training times and the ambiguity of adjusting synaptic weights located deep within the architecture of the network. Recently, a novel model termed Extreme Neural Machine (ENM) has been proposed to perform one-shot learning in recurrent networks. A drawback of this approach, however, is that synaptic weights may become destabilized after training due to the random activation of recurrent units. In this paper, we propose a solution to this problem by incorporating metaplasticity in the learning rule of ENMs. With this novel approach, networks learned complex functions that can be recalled after a delay period. Using realworld data, networks were trained to produce sound waveforms obtained from spoken English words. Results show that metaplasticity improved task recall in recurrent neural networks.

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), Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.471
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 studies0.0010.000
Scholarly communication0.0010.000
Open science0.0020.002
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0010.000

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 head0.038
GPT teacher head0.246
Teacher spread0.209 · 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
Published2022
Admission routes1
Has abstractyes

Explore more

Same venue2022 International Joint Conference on Neural Networks (IJCNN)Same topicNeural Networks and Reservoir ComputingFrench-language works237,207