Abstract
The medial temporal lobe may play a critical role in binding successive events into memory while encoding contextual information in implicit and explicit memory tasks. Information theory provides a quantitative basis to model contextual information engendered by conditional dependence between, or conditional uncertainty about, consecutive events in a sequence. We show that information theoretic indices characterizing contextual dependence within a sequential reaction time task (SRTT) predict regional responses, measured by fMRI, in areas associated with sequence learning and navigation. Specifically, activity of a distributed paralimbic system, centered on the left hippocampus, correlated selectively with predictability as measured with mutual information. This is clear evidence that the brain is sensitive to the probabilistic context in which events are encountered. This is potentially important for theories about how the brain represents uncertainty and makes perceptual inferences, particularly those based on predictive coding and hierarchical Bayes. (c) 2006 Elsevier Ltd. All rights reserved.
| Original language | English |
|---|---|
| Pages (from-to) | 535-546 |
| Number of pages | 12 |
| Journal | Neural Networks |
| Volume | 19 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - Jun 2006 |
Keywords
- sequential reaction time task (SRTT)
- 1st order Markov sequence
- implicit learning
- medial temporal lobe
- information theory
- predictability
- Bayesian observer
- MEDIAL TEMPORAL-LOBE
- EVENT-RELATED FMRI
- IMPLICIT
- INFORMATION
- INFERENCE
- NOVELTY
- MEMORY
- BRAIN