A Novel Symbolic Type Neural Network Model- Application to River Flow Forecasting

TL;DR

This paper introduces a symbolic neural network model called SFN, designed for river flow forecasting, demonstrating superior accuracy and sparsity compared to existing models.

Contribution

The paper presents a novel symbolic neural tree network that allows feature and functional selection with flexible structure for system modeling.

Findings

SFN outperforms traditional models in river flow forecasting

The model achieves higher fitness and sparsity

Demonstrates effectiveness of symbolic functions in neural networks

Abstract

In this paper we introduce a new symbolic type neural tree network called symbolic function network (SFN) that is based on using elementary functions to model systems in a symbolic form. The proposed formulation permits feature selection, functional selection, and flexible structure. We applied this model on the River Flow forecasting problem. The results found to be superior in both fitness and sparsity.