# On Advancements of the Forward-Forward Algorithm

arXiv: https://arxiv.org/abs/2504.21662 · HTML: https://mlsanity.com/paper/2504.21662/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 10 of 10)

- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [LoCo: Local Contrastive Representation Learning](https://mlsanity.com/paper/2008.01342/) (2020)
- [Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm](https://mlsanity.com/paper/2312.12668/) (2023)
- [Parallel Training of Deep Networks with Local Updates](https://mlsanity.com/paper/2012.03837/) (2020)
- [Self-Contrastive Forward-Forward Algorithm](https://mlsanity.com/paper/2409.11593/) (2024)
- [Training Convolutional Neural Networks with the Forward-Forward algorithm](https://mlsanity.com/paper/2312.14924/) (2023)
- [The Trifecta: Three simple techniques for training deeper Forward-Forward networks](https://mlsanity.com/paper/2311.18130/) (2023)
- [Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning](https://mlsanity.com/paper/2408.14925/) (2024)
- [LightFF: Lightweight Inference for Forward-Forward Algorithm](https://mlsanity.com/paper/2404.05241/) (2024)
- [Employing Layerwised Unsupervised Learning to Lessen Data and Loss Requirements in Forward-Forward Algorithms](https://mlsanity.com/paper/2404.14664/) (2024)

## Built on by (most cited first, 1 of 1)

- [Hyperspherical Forward-Forward with Prototypical Representations](https://mlsanity.com/paper/2605.00082/) (2026)

## Abstract (arXiv)

The Forward-Forward algorithm has evolved in machine learning research, tackling more complex tasks that mimic real-life applications. In the last years, it has been improved by several techniques to perform better than its original version, handling a challenging dataset like CIFAR10 without losing its flexibility and low memory usage. We have shown in our results that improvements are achieved through a combination of convolutional channel grouping, learning rate schedules, and independent block structures during training that lead to a 20% decrease in test error percentage. Additionally, to approach further implementations on low-capacity hardware projects, we have presented a series of lighter models that achieve low test error percentages within (21±3)% and number of trainable parameters between 164,706 and 754,386. This serves as a basis for our future study on complete verification and validation of these kinds of neural networks.