6533b7d7fe1ef96bd126840d
RESEARCH PRODUCT
The regression Tsetlin machine: a novel approach to interpretable nonlinear regression
Ole-christoffer GranmoMorten GoodwinLei JiaoXuan ZhangK. Darshana Abeyrathnasubject
021110 strategic defence & security studiesTheoretical computer scienceEmpirical comparisonComputer scienceGeneral Mathematics0211 other engineering and technologiesGeneral EngineeringGeneral Physics and AstronomyBinary number02 engineering and technologyThresholdingRegressionPropositional formula0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingBitwise operationTheme (computing)Nonlinear regressionVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550description
Relying simply on bitwise operators, the recently introduced Tsetlin machine (TM) has provided competitive pattern classification accuracy in several benchmarks, including text understanding. In this paper, we introduce the regression Tsetlin machine (RTM), a new class of TMs designed for continuous input and output, targeting nonlinear regression problems. In all brevity, we convert continuous input into a binary representation based on thresholding, and transform the propositional formula formed by the TM into an aggregated continuous output. Our empirical comparison of the RTM with state-of-the-art regression techniques reveals either superior or on par performance on five datasets. This article is part of the theme issue ‘Harmonizing energy-autonomous computing and intelligence’.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2019-12-24 |