Rxivist logo

Structured event memory: a neuro-symbolic model of event cognition

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

Posted 05 Feb 2019
bioRxiv DOI: 10.1101/541607 (published DOI: 10.1037/rev0000177)

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 high-dimensional input spaces, producing human-like event segmentation for naturalistic video data, and accounts for a wide array of memory phenomena.

Download data

  • Downloaded 4,554 times
  • Download rankings, all-time:
    • Site-wide: 2,883
    • In neuroscience: 178
  • Year to date:
    • Site-wide: 4,824
  • Since beginning of last month:
    • Site-wide: 4,570

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide