The Forward-Forward (FF) Algorithm has been recently proposed to alleviate the issues of backpropagation (BP) commonly used to train deep neural networks. However, its current formulation exhibits limitations such as the generation of negative data, slower convergence, and inadequate performance on complex tasks. In this paper, we take the main ideas of FF and improve them by leveraging channel-wise competitive learning in the context of convolutional neural networks for image classification tasks. A layer-wise loss function is introduced that promotes competitive learning and eliminates the need for negative data construction. To enhance both the learning of compositional features and feature space partitioning, a channel-wise feature separator and extractor block is proposed that complements the competitive learning process. Our method outperforms recent FF-based models on image classification tasks, achieving testing errors of 0.58%, 7.69%, 21.89%, and 48.77% on MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 respectively. Our approach bridges the performance gap between FF learning and BP methods, indicating the potential of our proposed approach to learn useful representations in a layer-wise modular fashion, enabling more efficient and flexible learning.

翻译：前向-前向（FF）算法近期被提出，旨在缓解深度神经网络训练中常用的反向传播（BP）算法所面临的问题。然而，当前FF算法存在负数据生成、收敛速度较慢以及在复杂任务中性能不足等局限性。本文在卷积神经网络图像分类任务中，通过引入通道级竞争学习机制改进FF的核心思想。我们提出一种逐层损失函数，该函数促进竞争学习并消除构造负数据的必要。为增强组合特征学习与特征空间划分能力，我们设计了一个通道级特征分离与提取模块，该模块与竞争学习过程形成互补。在图像分类任务中，本方法优于近期基于FF的模型：在MNIST、Fashion-MNIST、CIFAR-10和CIFAR-100数据集上分别取得了0.58%、7.69%、21.89%和48.77%的测试错误率。本方法弥合了FF学习与BP方法之间的性能差距，表明所提方案具备以逐层模块化方式学习有效表征的潜力，从而推动更高效、更灵活的学习范式。