最小化前向-前向算法中睡眠剥夺的影响
Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm
浏览论文内容
中文总结 AI 辅助
针对前向-前向算法中睡眠剥夺导致的学习效率下降，提出替代激活、优化损失函数和阈值调整等方法，并模拟休息和咖啡因刺激，在MNIST和Fashion-MNIST上实现2%-62%的准确率提升。
中文摘要 AI 辅助
本文解决了前向-前向算法中睡眠剥夺带来的挑战，其中将该算法中的两次前向传递分离并失衡各传递中的数据处理，被视为对人类睡眠剥夺时观察到的认知过程的模仿。先前研究表明，前向-前向算法中的睡眠剥夺对学习效率具有灾难性影响。为缓解此问题，我们探索了多种方法，包括替代激活函数、优化损失函数和阈值调整。为模拟周期性休息，我们在交替周期中减少正传递次数，从而创建短暂休息阶段。我们还研究了咖啡因诱导的刺激在睡眠剥夺条件下提升性能的潜力。在MNIST和Fashion-MNIST数据集上进行的实验评估表明，这些修改在睡眠剥夺情境下提高了准确率。例如，在严重睡眠剥夺设置（16个正传递或清醒期和1个负传递或睡眠期）下，观察到2%-62%的准确率提升。这些方法还增强了算法的鲁棒性及其与人类认知适应机制的一致性。
英文摘要
This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and imbalancing the data processing in the passes is considered an imitation of the cognitive processes observed in humans suffering from sleep deprivation. Previous research has demonstrated that sleep deprivation in the Forward-Forward algorithm has a catastrophic effect on learning efficacy. To mitigate this issue, we explore several approaches; these include alternative activation, optimized loss function, and threshold tuning. To simulate periodic rest, we reduce the number of positive passes in alternating epochs, creating short break phases. We additionally investigate the potential of caffeine-induced stimulation to enhance performance during sleep-deprived conditions. Experimental evaluations conducted on the MNIST and Fashion-MNIST datasets demonstrate that these modifications improve accuracy under the context of sleep deprivation. For example, a 2%-62% accuracy gain is observed in a severe sleep deprivation setting (16 positive or awake periods and 1 negative or sleep period). The approaches also enhance the resilience of the algorithm and its alignment with the adaptive mechanisms of human cognition.
发表机构
- Brac University（布拉克大学）
- Rajshahi University of Engineering and Technology（拉杰沙希工程技术大学）
- Ohio University（俄亥俄大学）
机构由 AI 辅助整理，请以论文原文为准。
