MétaCan
Menu
Back to cohort

Decision Tree-based Adaptive Approximate Accelerators for Enhanced Quality

2020· article· en· W3111850714 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

Venue2020 IEEE International Systems Conference (SysCon) · 2020
Typearticle
Languageen
FieldEngineering
TopicLow-power high-performance VLSI design
Canadian institutionsConcordia University
Fundersnot available
KeywordsComputer scienceOverhead (engineering)Set (abstract data type)Tree (set theory)ComputationDecision treeQuality (philosophy)Computer engineeringAlgorithmData mining

Abstract

fetched live from OpenAlex

Hardware accelerators are used for parallel computation with the tendency to accept inexact results. Such accelerators are used extensively in big-data processing applications, and thus can be designed approximately for reduced power consumption, area and processing time. However, since for some inputs the output errors may reach unacceptable levels, the main challenge is to ensure the quality of the approximated results. Towards this goal, in this paper, we propose a fine-grained input-dependent decision tree-based adaptive approximate design to meet the output quality constraints set by the user. For illustration purposes, we use a library of 16-bit approximate array multipliers with 20 different settings. The proposed methodology has been evaluated for audio and image processing applications. The simulation result, demonstrate the effectiveness of the proposed methodology, utilizing a lightweight decision tree-based design selector where the proposed adaptive design achieves the userspecified target output quality with a relatively low overhead.

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 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: none
Teacher disagreement score0.805
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
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 head0.070
GPT teacher head0.290
Teacher spread0.221 · 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