Structured Event Memory: A Neuro-Symbolic Model of Event Cognition

Nicholas T. Franklin, Kenneth A. Norman, Charan Ranganath, Jeffrey M. Zacks, Samuel J. Gershman

Research output: Contribution to journalArticlepeer-review

76 Scopus citations


Humans spontaneously organize a continuous experience into discrete events and use the learned structure of these events to generalize and organize memory. We introduce the Structured Event Memory (SEM) model of event cognition, which accounts for human abilities in event segmentation, memory, and generalization. SEM is derived from a probabilistic generative model of event dynamics defined over structured symbolic scenes. By embedding symbolic scene representations in a vector space and parametrizing the scene dynamics in this continuous space, SEM combines the advantages of structured and neural network approaches to high-level cognition. Using probabilistic reasoning over this generative model, SEM can infer event boundaries, learn event schemata, and use event knowledge to reconstruct past experience. We show that SEM can scale up to highdimensional input spaces, producing human-like event segmentation for naturalistic video data, and accounts for a wide array of memory phenomena.

Original languageEnglish (US)
Pages (from-to)327-361
Number of pages35
JournalPsychological Review
Issue number3
StatePublished - 2020

All Science Journal Classification (ASJC) codes

  • General Psychology


  • Bayesian nonparametric models
  • Event cognition
  • Latent structure
  • Memory
  • Neural networks


Dive into the research topics of 'Structured Event Memory: A Neuro-Symbolic Model of Event Cognition'. Together they form a unique fingerprint.

Cite this