融合贝叶斯与神经网络优势，提升行为预测准确性
More accurate behavioral predictions with hybrid Bayesian-connectionist models
- 用神经网络模仿贝叶斯模型，再通过人类行为数据微调
- 在四个人类概念学习案例中，预测精度超越传统方法
- 适合研究认知偏差与心理机制的计算建模者
研究人员常需在贝叶斯模型与神经网络模型之间抉择，二者各有优劣。理想模型应能灵活测试多种表征和归纳偏置，贝叶斯模型易实现，而神经网络难以做到；同时应避免过度简化，神经网络具备此能力，贝叶斯模型则不足。本文提出贝叶斯蒸馏结合行为调优（BBT）方法，实现两者的互补：首先用合成数据训练神经网络模仿贝叶斯模型，再在真实人类行为数据上微调以捕捉额外结构与细微特征。在四个人类概念学习案例中，BBT模型显著优于传统方法，既能模拟贝叶斯先验，又能揭示违反简单假设的启发式与偏差，带来新的心理学洞见。
原文摘要 · Abstract (English)
Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate testing many kinds of representations and inductive biases; Bayesian models make this easy, while neural networks do not. Similarly, an ideal paradigm would avoid over-simplifications; neural networks make this easy, while Bayesian models do not. Here, we introduce Bayesian distillation with Behavioral Tuning (BBT) as an approach to getting the best of both traditions. BBT offers a simple recipe for model building: first, a neural network is trained to mimic a Bayesian model through synthetic data, and second, the network is fine-tuned on human behavior to capture additional structure and nuance. Across four case studies in human concept learning, we find that BBT outperforms traditional approaches at predicting human behavior while also revealing psychological insights, resulting in models that can both mimic Bayesian priors and capture heuristics and biases that violate simple modeling assumptions.
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。