Many problems in education, finance, and engineering design require that decisions be made under uncertainty. In these fields, Machine Learning is often used to search for patterns and information from data. To find patterns in Fuzzy Data, Fuzzy Machine Learning techniques can be used. In this paper, we focus on solving and manipulating Fuzzy Nonlinear problems in the Linear Fuzzy Real (LFR) number system using the Gradient Descent. The Gradient Descent is the most often used learning algorithm in Machine Learning. Thus, we propose the LFR Gradient Descent method for solving nonlinear equations in the LFR number system.
Paper
Full text
Fuzzy gradient descent for the linear fuzzy real number system
Semantic Scholar · Mathematics · 2019
Abstract
Many problems in education, finance, and engineering design require that decisions be made under uncertainty. In these fields, Machine Learning is often used to search for patterns and information from data. To find patterns in Fuzzy Data, Fuzzy Machine Learning techniques can be used. In this paper, we focus on solving and manipulating Fuzzy Nonlinear problems in the Linear Fuzzy Real (LFR) number system using the Gradient Descent. The Gradient Descent is the most often used learning algorithm in Machine Learning. Thus, we propose the LFR Gradient Descent method for solving nonlinear equations in the LFR number system.