模仿生物睡眠机制，用重放优化神经网络置信度。
Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes
- 训练后引入类睡眠重放，重播内部表征更新权重。
- 与温度缩放结合使AlexNet和VGG19的Brier分数最优。
- 无需监督微调，适合提升模型可信置信度。
人工神经网络常过度自信，导致预测概率与实际准确率不匹配，削弱信任度。受生物睡眠及自发重放对记忆与学习作用的启发，我们提出睡眠重放巩固（Sleep Replay Consolidation, SRC）这一新型校准方法。SRC是一种训练后、类睡眠阶段，通过选择性重播内部表征来更新网络权重，从而改善校准，且无需监督微调。在多个实验中，SRC表现与温度缩放相当，并具互补性；结合两者可实现AlexNet和VGG19在Brier分数与熵之间的最佳权衡。结果表明，SRC为提升神经网络校准提供了根本性新路径，有助于实现更可信的置信度估计，缩小现代深度网络与人类不确定性处理之间的差距。
原文摘要 · Abstract (English)
Artificial neural networks are often overconfident, undermining trust because their predicted probabilities do not match actual accuracy. Inspired by biological sleep and the role of spontaneous replay in memory and learning, we introduce Sleep Replay Consolidation (SRC), a novel calibration approach. SRC is a post-training, sleep-like phase that selectively replays internal representations to update network weights and improve calibration without supervised retraining. Across multiple experiments, SRC is competitive with and complementary to standard approaches such as temperature scaling. Combining SRC with temperature scaling achieves the best Brier score and entropy trade-offs for AlexNet and VGG19. These results show that SRC provides a fundamentally novel approach to improving neural network calibration. SRC-based calibration offers a practical path toward more trustworthy confidence estimates and narrows the gap between human-like uncertainty handling and modern deep 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。