The Concept of Forward-Forward Learning Applied to a Multi Output Perceptron

K. Fredrik Karlsson
4/6/2023
cs.LGcs.NE

No official code found. Best implementation: KFKarlsson/FFPerceptron (7 stars, MIT, last commit 2023-04-11).

Abstract

The concept of a recently proposed Forward-Forward learning algorithm for fully connected artificial neural networks is applied to a single multi output perceptron for classification. The parameters of the system are trained with respect to increased (decreased) "goodness" for correctly (incorrectly) labelled input samples. Basic numerical tests demonstrate that the trained perceptron effectively deals with data sets that have non-linear decision boundaries. Moreover, the overall performance is comparable to more complex neural networks with hidden layers. The benefit of the approach presented here is that it only involves a single matrix multiplication.

View on arXivView PDF

Code Implementations(1)

KFKarlsson/FFPerceptronCommunity100%
MIT
71Python, Jupyter NotebookApr 4, 20233 years agoMIT

Similar Papers

One-class systems seamlessly fit in the forward-forward algorithm

84% match2023

Forward Learning of Graph Neural Networks

83% match1 repo222024

Novel Saliency Analysis for the Forward Forward Algorithm

83% match2024

Extending the Forward Forward Algorithm

83% match1 repo352023

On Advancements of the Forward-Forward Algorithm

83% match2025

Forward-Cooperation-Backward (FCB) learning in a Multi-Encoding Uni-Decoding neural network architecture

83% match2025

Cite this paper

@article{karlsson2023concept,
  title  = {The Concept of Forward-Forward Learning Applied to a Multi Output Perceptron},
  author = {K. Fredrik Karlsson},
  year   = {2023},
  eprint = {2304.03189},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.03189v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.03189.svg)](https://codeofpaper.com/paper/2304.03189)

Discussion