The Forward-Forward Algorithm: Some Preliminary Investigations

Abstract

The aim of this paper is to introduce a new learning procedure for neural networks and to demonstrate that it works well enough on a few small problems to be worth further investigation. The Forward-Forward algorithm replaces the forward and backward passes of backpropagation by two forward passes, one with positive (i.e. real) data and the other with negative data which could be generated by the network itself. Each layer has its own objective function which is simply to have high goodness for positive data and low goodness for negative data. The sum of the squared activities in a layer can be used as the goodness but there are many other possibilities, including minus the sum of the squared activities. If the positive and negative passes could be separated in time, the negative passes could be done offline, which would make the learning much simpler in the positive pass and allow video to be pipelined through the network without ever storing activities or stopping to propagate derivatives.

Cited by in corpus (7)

• Programmable metasurfaces for future photonic artificial intelligence
• Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
• Model-free Optical Processors using In Situ Reinforcement Learning with Proximal Policy Optimization
• Unlearning regularization for Boltzmann Machines
• Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks
• Scaling of hardware-compatible perturbative training algorithms
• Contrastive Forward-Forward: A Training Algorithm of Vision Transformer