# Learning Using a Single Forward Pass

arXiv: https://arxiv.org/abs/2402.09769 · HTML: https://mlsanity.com/paper/2402.09769/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Deep Learning without Weight Transport](https://mlsanity.com/paper/1904.05391/) (2019)
- [Why should we add early exits to neural networks?](https://mlsanity.com/paper/2004.12814/) (2020)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [How Important is Weight Symmetry in Backpropagation?](https://mlsanity.com/paper/1510.05067/) (2015)
- [Random feedback weights support learning in deep neural networks](https://mlsanity.com/paper/1411.0247/) (2014)
- [Local plasticity rules can learn deep representations using self-supervised contrastive predictions](https://mlsanity.com/paper/2010.08262/) (2020)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Understanding Synthetic Gradients and Decoupled Neural Interfaces](https://mlsanity.com/paper/1703.00522/) (2017)
- [SymBa: Symmetric Backpropagation-Free Contrastive Learning with Forward-Forward Algorithm for Optimizing Convergence](https://mlsanity.com/paper/2303.08418/) (2023)
- [Learning to solve the credit assignment problem](https://mlsanity.com/paper/1906.00889/) (2019)
- [The High-Dimensional Geometry of Binary Neural Networks](https://mlsanity.com/paper/1705.07199/) (2017)
- [Theoretical Analysis of Inductive Biases in Deep Convolutional Networks](https://mlsanity.com/paper/2305.08404/) (2023)
- [On-device Training: A First Overview on Existing Systems](https://mlsanity.com/paper/2212.00824/) (2022)
- [The Trifecta: Three simple techniques for training deeper Forward-Forward networks](https://mlsanity.com/paper/2311.18130/) (2023)
- [A Spiking Neural Network with Local Learning Rules Derived From Nonnegative Similarity Matching](https://mlsanity.com/paper/1902.01429/) (2019)

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

- [Learning without Global Backpropagation via Synergistic Information Distillation](https://mlsanity.com/paper/2510.03273/) (2025)

## Abstract (arXiv)

We propose a learning algorithm to overcome the limitations of traditional backpropagation in resource-constrained environments: Solo Pass Embedded Learning Algorithm (SPELA). SPELA operates with local loss functions to update weights, significantly saving on resources allocated to the propagation of gradients and storing computational graphs while being sufficiently accurate. Consequently, SPELA can closely match backpropagation using less memory. Moreover, SPELA can effectively fine-tune pre-trained image recognition models for new tasks. Further, SPELA is extended with significant modifications to train CNN networks, which we evaluate on CIFAR-10, CIFAR-100, and SVHN 10 datasets, showing equivalent performance compared to backpropagation. Our results indicate that SPELA, with its features such as local learning and early exit, is a potential candidate for learning in resource-constrained edge AI applications.