More accurate behavioral predictions with hybrid Bayesian-connectionist models

2026-08-22

AI Summary

研究提出了一种结合贝叶斯模型和神经网络的Bayesian distillation with Behavioral Tuning方法，以提高行为预测准确性。

Abstract

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.

Problem

• behavioral predictions
• Bayesian models
• neural networks
• inductive biases
• over-simplifications

Innovation

• Bayesian distillation
• Behavioral Tuning
• neural network
• Bayesian model
• concept learning