Employing Layerwised Unsupervised Learning to Lessen Data and Loss Requirements in Forward-Forward Algorithms

TL;DR

This paper introduces an unsupervised version of the Forward-Forward algorithm, reducing data and loss requirements, and enhancing its practicality for diverse datasets and distributed environments.

Contribution

It proposes an unsupervised Forward-Forward algorithm that allows training with standard loss functions and inputs, broadening its applicability.

Findings

Enables stable learning across various datasets.

Facilitates training in distributed environments like federated learning.

Reduces dependency on special input and loss functions.

Abstract

Recent deep learning models such as ChatGPT utilizing the back-propagation algorithm have exhibited remarkable performance. However, the disparity between the biological brain processes and the back-propagation algorithm has been noted. The Forward-Forward algorithm, which trains deep learning models solely through the forward pass, has emerged to address this. Although the Forward-Forward algorithm cannot replace back-propagation due to limitations such as having to use special input and loss functions, it has the potential to be useful in special situations where back-propagation is difficult to use. To work around this limitation and verify usability, we propose an Unsupervised Forward-Forward algorithm. Using an unsupervised learning model enables training with usual loss functions and inputs without restriction. Through this approach, we lead to stable learning and enable versatile utilization across various datasets and tasks. From a usability perspective, given the characteristics of the Forward-Forward algorithm and the advantages of the proposed method, we anticipate its practical application even in scenarios such as federated learning, where deep learning layers need to be trained separately in physically distributed environments.