# Extending the Forward Forward Algorithm

arXiv: https://arxiv.org/abs/2307.04205 · HTML: https://mlsanity.com/paper/2307.04205/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 9 Jul 2023.

## Builds on (most cited first, 7 of 7)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [Gradients without Backpropagation](https://mlsanity.com/paper/2202.08587/) (2022)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [Meta Learning Backpropagation And Improving It](https://mlsanity.com/paper/2012.14905/) (2020)
- [The Predictive Forward-Forward Algorithm](https://mlsanity.com/paper/2301.01452/) (2023)

## Built on by (most cited first, 6 of 6)

- [Training Convolutional Neural Networks with the Forward-Forward algorithm](https://mlsanity.com/paper/2312.14924/) (2023)
- [Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm](https://mlsanity.com/paper/2502.20411/) (2025)
- [Resource-efficient Medical Image Analysis with Self-adapting Forward-Forward Networks](https://mlsanity.com/paper/2406.14038/) (2024)
- [On the Improvement of Generalization and Stability of Forward-Only Learning via Neural Polarization](https://mlsanity.com/paper/2408.09210/) (2024)
- [Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant](https://mlsanity.com/paper/2605.06240/) (2026)
- [Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm](https://mlsanity.com/paper/2609.06042/) (2026)

## Abstract (arXiv)

The Forward Forward algorithm, proposed by Geoffrey Hinton in November 2022, is a novel method for training neural networks as an alternative to backpropagation. In this project, we replicate Hinton's experiments on the MNIST dataset, and subsequently extend the scope of the method with two significant contributions. First, we establish a baseline performance for the Forward Forward network on the IMDb movie reviews dataset. As far as we know, our results on this sentiment analysis task marks the first instance of the algorithm's extension beyond computer vision. Second, we introduce a novel pyramidal optimization strategy for the loss threshold - a hyperparameter specific to the Forward Forward method. Our pyramidal approach shows that a good thresholding strategy causes a difference of up to 8% in test error. Lastly, we perform visualizations of the trained parameters and derived several significant insights, such as a notably larger (10-20x) mean and variance in the weights acquired by the Forward Forward network. Repository: https://github.com/Ads-cmu/ForwardForward