|国家预印本平台
首页|神经模拟推断:基于神经网络和模拟推断的认知建模方法

神经模拟推断:基于神经网络和模拟推断的认知建模方法

Neural simulation-based inference: a neural network and simulation-based inference approach to cognitive modelling

中文摘要英文摘要

认知建模是量化和理解人类心智过程的重要方法,但目前该方法多集中于简单实验任务和数据结构,当试图构建复杂模型以解释复杂认知过程时,能否确定其似然并完成参数推断是严峻的挑战。基于神经网络的模拟推断方法结合了模拟推断与分摊技术,无需计算似然函数,直接利用模拟数据来参数推断,并通过神经网络训练控制计算成本,可快速稳健地进行参数推断。该方法已成功应用于证据积累模型框架下的大规模数据、动态潜变量以及联合建模等场景,并开始扩展到强化学习和贝叶斯决策模型。未来的研究可以进一步验证神经模拟推断的有效性,应用该方法拓展认知模型的应用范围,理解人类复杂认知加工的规律。

ognitive computational modeling quantifies human mental processes using mathematical frameworks, translating cognitive theories into testable hypotheses. Modern cognitive modeling involves four interconnected stages: defining models by formalizing symbolic theories into generative computational frameworks, collecting data through hypothesis-driven experiments, inferring parameters to quantify cognitive processes, and evaluating or comparing models. Parameter inference, a critical step bridging models and data, traditionally relies on maximum likelihood estimation (MLE) and Bayesian methods like Markov Chain Monte Carlo (MCMC). These approaches depend on explicit likelihood functions, which become computationally intractable for complex modelssuch as those with nonlinear parameters (e.g., learning dynamics) or hierarchical/multimodal data structures.To address these challenges, simulation-based inference (SBI) emerged, leveraging parameter-data mappings via simulations to bypass likelihood calculations. Early SBI methods, however, faced computational redundancy and scalability limitations. Recent advances in neural simulation-based inference (NSBI), or neural amortized inference (NAI), harness neural networks to pretrain parameter-data relationships, enabling rapid posterior estimation.Despite its advantages, NSBI remains underutilized in psychology due to technical complexity. This work focuses on neural posterior estimation, one of three NSBI approaches alongside neural likelihood estimation and neural model comparison. Neural posterior estimation operates in two phases: training and inference. During training, parameters are sampled from prior distributions, and synthetic data are generated using the model; a neural network then learns to approximate the true posterior from these training pairs. In the inference stage, real data are input to the trained network to generate parameter samples. The BayesFlow framework enhances neural posterior estimation by integrating normalizing flowsflexible density estimatorsand summary statistic networks, enabling variable-length data handling and unsupervised posterior approximation. Its GPU-accelerated implementation further boosts efficiency.Neural posterior estimation has expanded the scope of evidence accumulation models (EAMs), one of the most widely used framework in cognitive modeling. First, it enables large-scale behavioral analyses, as demonstrated by von Krause et al. (2022), who applied neural posterior estimation to drift-diffusion models (DDMs) for 1.2 million implicit association test participants. By modeling condition-dependent drift rates and decision thresholds, they revealed age-related nonlinear cognitive speed changes, peaking at age 30 and declining post-60. Neural posterior estimation completed inference in 24 hours versus MCMCs 50+ hours for a small subset, demonstrating its scalability.Second, neural posterior estimation supports dynamic decision-making frameworks, exemplified by Schumacher et al. (2023), who combined high-level dynamics with low-level mechanisms using recurrent neural networks (RNNs). Their simultaneous estimation of hierarchical parameters achieved over 0.9 recovery correlations and superior predictive accuracy compared to static models.Finally, neural posterior estimation facilitates neurocognitive integration, as shown by Ghaderi-Kangavari et al. (2023), who linked single-trial EEG components (e.g., CPP slope) to behavior via shared latent variables like drift rate. This approach circumvented intractable likelihoods and revealed associations between CPP slope and non-decision time.NSBI enhances cognitive modeling by enabling efficient analysis of complex, high-dimensional datasets. Its key limitations include model validity risks (biased estimates from incorrect generative assumptions), overfitting concerns (overconfident posteriors on novel data), and upfront training costs for amortized methods. Future work should refine validity checkssuch as detecting model misspecificationand develop hybrid inference techniques. NSBIs potential extends to computational psychiatry and educational psychology, promising deeper insights into cognition across domains. By addressing complexity barriers, NSBI could democratize advanced modeling for interdisciplinary research, advancing our understanding of human cognition through scalable, data-driven frameworks.

潘晚坷、胡传鹏

社会科学

认知建模生成模型贝叶斯基于模拟的推断基于神经网络的模拟推断

Cognitive ModelingGenerative ModelsBayesianSimulation-based InferenceNeural NetworkNeural Amortized Bayesian Inference

潘晚坷,胡传鹏.神经模拟推断:基于神经网络和模拟推断的认知建模方法[EB/OL].(2025-02-16)[2025-03-14].https://chinaxiv.org/abs/202407.00277.点此复制

评论