DEEP LEARNING FOR NONLINEAR REGRESSION

Abstract

Artificial intelligence based on deep learning has shown to be useful in a wide range of applications and research areas because, in contrast to traditional machine learning algorithms, it can produce extremely high-level data representations from amounts of raw data. As a result, it has proven to be an excellent solution to a broad range of linear issues, and it seems to be highly for the non-linear ones The aim of this work is to propose a methodology to be followed in the design of deep learning model for non-linear regression, then developing a CNN model that can deal with this scenario. Thereafter, apply it to solve real world issues such as predicting lifetime and mechanical performance degradation of multilayer greenhouse polyethylene films. we created a hybrid deep learning model capable of handling the challenge in order to complete this assignment. Both the training and validation phases of the DL model were successful, demonstrating the feasibility of using 1D CNN for nonlinear regression