Constrained design strategies for improving normal approximations in nonlinear regression problems

2002 ◽  
Vol 104 (1) ◽  
pp. 175-196 ◽  
Author(s):  
Merlise Clyde ◽  
Kathryn Chaloner
Keyword(s):  
Nonlinear Regression ◽  
Design Strategies ◽  
Normal Approximations ◽  
Regression Problems

scholarly journals The regression Tsetlin machine: a novel approach to interpretable nonlinear regression

2019 ◽  
Vol 378 (2164) ◽  
pp. 20190165 ◽  
Author(s):  
K. Darshana Abeyrathna ◽  
Ole-Christoffer Granmo ◽  
Xuan Zhang ◽  
Lei Jiao ◽  
Morten Goodwin
Keyword(s):  
Nonlinear Regression ◽  
Binary Representation ◽  
Propositional Formula ◽  
New Class ◽  
Text Understanding ◽  
Novel Approach ◽  
Continuous Output ◽  
Regression Techniques ◽  
Regression Problems ◽  
Continuous Input

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’.

Sign in / Sign up

Export Citation Format

Share Document