A Neural Model of Rule Discovery with Relatively Short-Term Sequence Memory
This addresses the problem of understanding fluid intelligence in cognitive science, but it appears incremental as it builds on existing neural network approaches for sequence memory.
The authors tackled the problem of discovering regularities in event sequences using a neural cognitive model, achieving results in explaining fluid intelligence through implementation and testing with delayed match-to-sample tasks.
This report proposes a neural cognitive model for discovering regularities in event sequences. In a fluid intelligence task, the subject is required to discover regularities from relatively short-term memory of the first-seen task. Some fluid intelligence tasks require discovering regularities in event sequences. Thus, a neural network model was constructed to explain fluid intelligence or regularity discovery in event sequences with relatively short-term memory. The model was implemented and tested with delayed match-to-sample tasks.