Forward-Forward Algorithm for Hyperspectral Image Classification: A Preliminary Study

TL;DR

This paper explores the use of the forward-forward algorithm as an alternative to back-propagation for hyperspectral image classification, highlighting its potential benefits and preliminary effectiveness.

Contribution

It introduces the application of the forward-forward algorithm to hyperspectral image classification, offering a preliminary comparison with traditional back-propagation methods.

Findings

FFA shows promising results compared to back-propagation

Potential for reduced computational complexity

Preliminary evidence of effectiveness in hyperspectral tasks

Abstract

The back-propagation algorithm has long been the de-facto standard in optimizing weights and biases in neural networks, particularly in cutting-edge deep learning models. Its widespread adoption in fields like natural language processing, computer vision, and remote sensing has revolutionized automation in various tasks. The popularity of back-propagation stems from its ability to achieve outstanding performance in tasks such as classification, detection, and segmentation. Nevertheless, back-propagation is not without its limitations, encompassing sensitivity to initial conditions, vanishing gradients, overfitting, and computational complexity. The recent introduction of a forward-forward algorithm (FFA), which computes local goodness functions to optimize network parameters, alleviates the dependence on substantial computational resources and the constant need for architectural scaling. This study investigates the application of FFA for hyperspectral image classification. Experimental results and comparative analysis are provided with the use of the traditional back-propagation algorithm. Preliminary results show the potential behind FFA and its promises.