# Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment

arXiv: https://arxiv.org/abs/2606.09928 · HTML: https://mlsanity.com/paper/2606.09928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Direct Feedback Alignment Provides Learning in Deep Neural Networks](https://mlsanity.com/paper/1609.01596/) (2016)
- [Difference Target Propagation](https://mlsanity.com/paper/1412.7525/) (2014)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures](https://mlsanity.com/paper/1807.04587/) (2018)
- [Deep Learning without Weight Transport](https://mlsanity.com/paper/1904.05391/) (2019)
- [Decoupled Greedy Learning of CNNs](https://mlsanity.com/paper/1901.08164/) (2019)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [Decoupled Parallel Backpropagation with Convergence Guarantee](https://mlsanity.com/paper/1804.10574/) (2018)
- [Understanding Synthetic Gradients and Decoupled Neural Interfaces](https://mlsanity.com/paper/1703.00522/) (2017)
- [The Predictive Forward-Forward Algorithm](https://mlsanity.com/paper/2301.01452/) (2023)
- [Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective](https://mlsanity.com/paper/2302.03751/) (2023)
- [SymBa: Symmetric Backpropagation-Free Contrastive Learning with Forward-Forward Algorithm for Optimizing Convergence](https://mlsanity.com/paper/2303.08418/) (2023)
- [Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm](https://mlsanity.com/paper/2312.12668/) (2023)
- [Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits](https://mlsanity.com/paper/2303.18187/) (2023)
- [A theory for the sparsity emerged in the Forward Forward algorithm](https://mlsanity.com/paper/2311.05667/) (2023)
- [HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion](https://mlsanity.com/paper/2407.05638/) (2024)
- [Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm](https://mlsanity.com/paper/2502.20411/) (2025)
- [Feed-Forward Optimization With Delayed Feedback for Neural Network Training](https://mlsanity.com/paper/2304.13372/) (2023)
- [Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks](https://mlsanity.com/paper/2312.13311/) (2023)
- [Forward-Forward Learning achieves Highly Selective Latent Representations for Out-of-Distribution Detection in Fully Spiking Neural Networks](https://mlsanity.com/paper/2407.14097/) (2024)
- [Emerging NeoHebbian Dynamics in Forward-Forward Learning: Implications for Neuromorphic Computing](https://mlsanity.com/paper/2406.16479/) (2024)
- [Deep Companion Learning: Enhancing Generalization Through Historical Consistency](https://mlsanity.com/paper/2407.18821/) (2024)

## Abstract (arXiv)

The Forward-Forward (FF) algorithm offers a biologically inspired alternative to backpropagation by replacing gradient-based credit assignment with local, forward-only objectives. While recent extensions have adapted FF to convolutional neural networks (CNNs), existing formulations rely on static channel-class partitions and struggle to perform effectively in complex tasks. In this work, we introduce a learnable channel-class assignment mechanism that enables adaptive, data-driven specialization of convolutional channels, supported by entropy and orthogonality regularization to promote learning performance. We further propose a loss-aware layer contribution strategy that adaptively weights intermediate-layer predictions based on their validation performance, enhancing the effectiveness of forward-only inference. Integrated into residual CNNs, the proposed method achieves consistently superior performance across CIFAR-10, CIFAR-100, and Tiny-ImageNet compared to existing similar forward-only methods. Notably, it establishes new state-of-the-art performance among FF-based models, substantially narrowing the gap with backpropagation. These findings demonstrate that introducing learnable channel specialization and layer contribution weighting significantly enhances the representational capacity of forward-only learning in deep CNNs.