发表机构
Princeton University; Princeton AI Lab; Massachusetts Institute of Technology（普林斯顿大学; 普林斯顿人工智能实验室; 麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出带行为调优的贝叶斯蒸馏（BBT）混合模型，结合贝叶斯与神经网络模型优势，在人类概念学习案例中更准确预测人类行为并揭示心理学洞见。
AI 中文摘要
研究人员在构建行为模型时，常需在贝叶斯模型与神经网络模型之间做出选择，这两种范式各有优劣且互补。理想的范式应能便捷地测试多种表征形式与归纳偏置，贝叶斯模型可轻松做到这一点，而神经网络模型则难以实现；同时还应能避免过度简化，神经网络模型能轻松做到这一点，而贝叶斯模型则难以实现。本文提出一种融合两种范式优势的方法：带行为调优的贝叶斯蒸馏（BBT）。BBT提供了简单的建模流程：首先在合成数据上训练神经网络以模仿贝叶斯模型，随后在人类行为数据上对该网络进行微调，从而捕捉额外的结构与细微差别。在人类概念学习的四个案例研究中，研究发现BBT在预测人类行为方面优于传统方法，同时还能揭示心理学洞见，所得模型既能模仿贝叶斯先验，又能捕捉违背简单建模假设的启发式策略与偏差。
英文摘要
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.
