改进前向-前向算法，显著降低错误率并适配低资源设备。
On Advancements of the Forward-Forward Algorithm
- 通过卷积通道分组与独立块结构提升训练效率。
- 在CIFAR10上测试误差降低20%，参数量仅16万至75万。
- 提出轻量化模型，适合部署在资源受限的硬件上。
前向-前向算法在机器学习研究中持续演进，已能应对更复杂的现实应用任务。近年来，通过卷积通道分组、学习率调度和独立块结构等技术改进，该算法在不牺牲灵活性和低内存消耗的前提下，成功处理了如CIFAR10这类挑战性数据集，测试误差降低了20%。为推动其在低算力硬件上的应用，本文还设计了一系列轻量化模型，测试误差维持在(21±3)%，可训练参数量介于164,706至754,386之间。这些成果为后续对这类神经网络的全面验证奠定了基础。
原文摘要 · Abstract (English)
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$\pm$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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。