Statistical Learning Speeds Visual Search: More Efficient Selection, or Faster Response?

Learning statistical regularities of target objects speeds visual search performance. However, we do not yet know whether this statistical learning effect is driven by biasing attentional selection at the early perceptual stage of processing, as theories of attention propose, or by improving the decision-making efficiency at a late response-related stage. Leveraging the high-temporal resolution of the event-related potential (ERP) technique, we had 16 human observers perform a visual search task where we inserted a fine-grained statistical regularity that the target shapes appeared in different colors with six unique probabilities. Observers unintentionally learned these regularities such that they were faster to report targets that appeared in more likely target colors. The observers' ERPs showed that this learning effect resulted in subjects making faster decisions about the target presence, and not by preferentially shifting attention to more rapidly select likely target colors, as is often assumed by the attentional selection account, supporting a post-selection account for statistical learning of the probabilistic regularities of target features. These results provide fundamental insights into the attentional control mechanisms of statistical learning. Public Significance Statement Humans are able to learn regularities from the surrounding environment to increase their efficiency. However, the mechanisms underlying this statistical learning are not yet clear. Leveraging the high-temporal resolution of human electrophysiology, we examined the attentional control mechanisms of statistical learning with a novel visual search paradigm. We used fine-grained statistical regularities that paired target shapes with different colors across trials. Our results demonstrated that observers could successfully learn the complex statistical regularities of the environment unintentionally. Contrary to theories of attentional selection, we found that this statistical learning effect was driven by more efficient decision making, not biasing attention to select targets with prioritized features, helping solve the long-standing theoretical controversy regarding the cognitive control mechanisms underlying statistical learning.