Solution of Definite Integrals using Functional Link Artificial Neural Networks

2019/04/21 by Satyasaran Changdar, Changdar, Satyasaran, Snehangshu Bhattacharjee +1
Physics and Astronomy · Mathematics · Computer Science · #Model Reduction and Neural Networks #Iterative Methods for Nonlinear Equations #Numerical Methods and Algorithms

paper · pdf · doi:10.48550/arxiv.1904.09656

Abstract

This paper discusses a new method to solve definite integrals using artificial neural networks. The objective is to build a neural network that would be a novel alternative to pre-established numerical methods and with the help of a learning algorithm, be able to solve definite integrals, by minimising a well constructed error function. The proposed algorithm, with respect to existing numerical methods, is effective and precise and well-suited for purposes which require integration of higher order polynomials. The observations have been recorded and illustrated in tabular and graphical form.

Citations

• The perceptron: A probabilistic model for information storage and organization in the brain.

Related

• Fixed Integral Neural Networks
• Neural Networks are Integrable
• Artificial neural networks for solving ordinary and partial differential equations
• Advanced Physics-Informed Neural Network with Residuals for Solving Complex Integral Equations
• Computing Anti-Derivatives using Deep Neural Networks