标题： 关于前向-前向算法的进展 显示英文标题

标题： On Advancements of the Forward-Forward Algorithm

摘要： 前向-前向算法在机器学习研究中不断发展，解决更加复杂的任务，这些任务模仿了现实世界的应用。 近年来，通过多种技术对其进行了改进，使其表现优于原始版本，在处理具有挑战性的数据集（如CIFAR10）时，同时保持其灵活性和低内存使用。 我们的结果显示，通过卷积通道分组、学习率调度以及训练期间的独立块结构的组合，测试错误率降低了20%。 此外，为了进一步在低容量硬件项目上实施，我们提出了一系列较轻量的模型，其测试错误率在(21$\pm$6)%范围内，可训练参数数量介于164,706到754,386之间。 这也为我们未来对该类神经网络进行全面验证和确认的研究奠定了基础。 显示英文摘要

摘要： 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$6)\% and number of trainable parameters between 164,706 and 754,386. This serving also as a basis for our future study on complete verification and validation of these kinds of neural networks.