MétaCan
Menu
Back to cohort
Record W2107999479 · doi:10.1109/icnn.1996.549206

The effects of reduced precision bit lengths on feedforward neural networks for speech recognition

2002· article· en· W2107999479 on OpenAlexaff
Selçuk Şen, William Robertson, William Phillips

Bibliographic record

VenueProceedings of International Conference on Neural Networks (ICNN'96) · 2002
Typearticle
Languageen
FieldComputer Science
TopicNeural Networks and Applications
Canadian institutionsTechnical University of Nova Scotia
Fundersnot available
KeywordsArtificial neural networkComputer scienceFeedforward neural networkFeed forwardFixed-point arithmeticSpeech recognitionFixed pointFloating pointSet (abstract data type)ArithmeticA priori and a posterioriTime delay neural networkPrecision and recallIndependence (probability theory)Point (geometry)AlgorithmArtificial intelligencePattern recognition (psychology)MathematicsStatistics

Abstract

fetched live from OpenAlex

An investigation of using fixed-point arithmetic on a neural networks is presented. A formula that estimates the standard deviation of the output differences of fixed-point and floating-point networks is developed. The formula provides a priori knowledge regarding the required number of bit precision that should be employed to achieve acceptable recognition rate on the feedforward recall phase. A time delay neural network (TDNN) with speaker independence is used to do unvoiced stop consonants recognition, namely P, T, K. The fixed-point arithmetic implementation offers comparable simulation results to that of a floating-point implementation. The recognition rate for the test set employing fixed-point arithmetic in both training and recall is between 75% and 90%. A single digit speaker independent problem is also investigated to prove the validity of formula further.

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: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.971
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 science0.0020.000
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 head0.037
GPT teacher head0.270
Teacher spread0.232 · 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

Citations4
Published2002
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of International Conference on Neural Networks (ICNN'96)Same topicNeural Networks and ApplicationsFrench-language works237,207