Fitting, Evaluating, and Comparing Cognitive Architecture Models Using Likelihood: A Primer With Examples in ACT-R
Cognitive architectures are influential, integrated computational frameworks for modeling cognitive processes. Due to a variety of factors, however, researchers using cognitive architectures to explain and predict human performance rarely employ model validation, comparison, and selection techniques based on likelihood. This paper provides a primer on how to implement maximum likelihood techniques and its derivatives to fit and compare models at the individual and group level, using models implemented in the ACT-R cognitive architecture as examples. The paper covers the most common ways in which likelihood measures can be applied, under different scenarios, for models of different complexity, and provides further technical references for the interested reader. An accompanying notebook in Python provides the code to implement all of the suggestions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Neural Posterior Estimation on Exponential Random Graph Models: Evaluating Bias and Implementation Challenges
Exponential random graph models (ERGMs) are flexible probabilistic frameworks to model statistical networks through a variety of network summary statistics. Conventional Bayesian estimation for ERGMs involves iteratively…
Unbiased and Efficient Log-Likelihood Estimation with Inverse Binomial Sampling
The fate of scientific hypotheses often relies on the ability of a computational model to explain the data, quantified in modern statistical approaches by the likelihood function. The log-likelihood is the key element fo…
parameter estimationPyBADS: Fast and robust black-box optimization in Python
PyBADS is a Python implementation of the Bayesian Adaptive Direct Search (BADS) algorithm for fast and robust black-box optimization (Acerbi and Ma 2017). BADS is an optimization algorithm designed to efficiently solve d…
Bayesian Conditional Gaussian Network Classifiers with Applications to Mass Spectra Classification
Classifiers based on probabilistic graphical models are very effective. In continuous domains, maximum likelihood is usually used to assess the predictions of those classifiers. When data is scarce, this can easily lead …
General ClassificationAmortized Bayesian model comparison with evidential deep learning
Comparing competing mathematical models of complex natural processes is a shared goal among many branches of science. The Bayesian probabilistic framework offers a principled way to perform model comparison and extract u…
Deep Learningmodel