Publications

Planning beyond the next trial in adaptive experiments: A dynamic programming approach

W Kim, MA Pitt, Z-L Lu, & JI Myung

To date, most adaptive experiments have relied on myopic, one-step-ahead strategies in which the stimulus on each trial is selected to maximize inference on the next trial only. A lingering question in the field has been how much additional benefit would be gained by optimizing beyond the next trial. This study applies dynamic programming (DP), a technique applicable for such full-horizon, “global” optimization, to model-based perceptual threshold estimation, a domain that has been a major beneficiary of adaptive methods. The results provide insight into conditions that will benefit from optimizing beyond the next trial.

Cognitive Science, 41, 2234-2252 (2017)

A hierarchical Bayesian approach to adaptive vision testing A case study with the contrast sensitivity function

H Gu, W Kim, F Hou, LA Lesmes, MA Pitt, Z-L Lu, & JI Myung

This study empirically validates the method of hierarchical adaptive design optimization (HADO; Kim, Pitt, Lu, Steyvers, & Myung, 2014) in the context of vision testing. The performance of HADO in estimating human contrast sensitivity function is compared with that of standard Bayesian adaptive testing. The improvement with HADO over the standard approach was maintained even when the prior information was constructed from heterogeneous populations or a relatively small number of observers.

Journal of Vision, 16, 15, 1-17 (2016)

A hierarchical adaptive approach to optimal experimental design

W Kim, MA Pitt, Z-L Lu, M Steyvers, & JI Myung

This research proposes a hierarchical Bayes extension of adaptive design optimization that provides a judicious way to exploit two complementary schemes of inference (with past and future data) to achieve even greater accuracy and efficiency in information gain. We demonstrate the method in a simulation experiment in the field of visual perception.

Neural Computation, 26, 2465-2492 (2014)

How do PDP models learn quasiregularity?

W Kim, MA Pitt, & JI Myung

Parallel distributed processing (PDP) models have had a profound impact on the study of cognition. One domain in which they have been particularly influential is learning quasiregularity, in which mastery requires both learning regularities that capture the majority of the structure in the input plus learning exceptions that violate the regularities. This study, by conducting, small- and large-scale analyses of a feedforward, 3-layer network, addresses 2 fundamental issues about network functioning: how the model can learn both regularities and exceptions without sacrificing generalizability and the nature of the hidden representation that makes this learning possible.

Psychological Review, 124, 903-916 (2013)