AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling

Kuruge Darshana Abeyrathna, Bimal Bhattarai, Morten Goodwin, Saeed Rahimi Gorji, Ole-Christoffer Granmo, Lei Jiao, Rupsa Saha, Rohan K. Yadav

ICML 2021 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems · 23 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use asynchronous clause threads with local voting tallies instead of synchronized sequential clause evaluationTsetlin Machine · classification datasets in Table 1accuracyNo clear effect
Use asynchronous clause threads with local voting tallies instead of indexed CPU learningTsetlin Machine · BBC Sportsspeedup: 38.9$\times$Improved
Use asynchronous clause threads with local voting tallies instead of indexed CPU learningTsetlin Machine · 20 Newsgroupspeedup: 49.3$\times$Improved
Use asynchronous clause threads with local voting tallies instead of indexed CPU learningTsetlin Machine · IMDBaccuracy: 88.42 $\scriptstyle\pm$ 2.05 -> 89.92 $\scriptstyle\pm$ 0.23Improved
Increase the number of clausesRegression Tsetlin Machine · Bike SharingMAEImproved
Use CUDA parallelization rather than indexed CPU implementationRegression Tsetlin Machine · Bike Sharingspeedup: 156.4$\times$Improved
Use CUDA parallelization rather than indexed CPU implementationRegression Tsetlin Machine · BlogFeedbackspeedup: 211.6$\times$Improved
Increase clause count from 20 to 2,560CUDA Tsetlin Machine · SEMEVALexecution time: 40%No clear effect
Use CUDA parallelization rather than indexed CPU implementationTsetlin Machine · JAVAaccuracy: 97.03 $\scriptstyle\pm$ 0.02 -> 97.53 $\scriptstyle\pm$ 0.02No clear effect
Use asynchronous clause threads with local voting talliesTsetlin Machine · Bike SharingMAE: 23.5$\scriptstyle\pm$0.04 -> 23.9$\scriptstyle\pm$0.08No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy