Close
This site uses cookies

By using this site, you consent to our use of cookies. You can view our terms and conditions for more information.

Return to Session

Beyond pattern completion with short-term plasticity

Authors
Kevin Shabahang
University of Melbourne ~ Psychology
Dr. Hyungwook Yim
The University of Melbourne ~ School of Psychological Sciences
Prof. Simon Dennis
University of Melbourne ~ University of Melbourne
Abstract

In a Linear Associative Net (LAN), all input settles to a single pattern, therefore Anderson, Silverstein, Ritz, and Jones (1977) introduced saturation to force the system to reach other steady-states in the Brain-State-in-a-Box (BSB). Unfortunately, the BSB is limited in its ability to generalize because its responses are restricted to previously stored patterns. We present simulations showing how a Dynamic-Eigen-Net (DEN), a LAN with Short-Term Plasticity (STP), overcomes the single-response limitation. Critically, a DEN also accommodates novel patterns by aligning them with encoded structure. We train a two-slot DEN on a text corpus, and provide an account of lexical decision and judgement-of-grammaticality (JOG) tasks showing how grammatical bi-grams yield stronger responses relative to ungrammatical bi-grams. Finally, we present a simulation showing how a DEN is sensitive to syntactic violations introduced in novel bi-grams. We propose DENs as associative nets with great.

Tags

Keywords

Content Addressable Memory
Auto-associative
Short-Term Plasticity
Generalization

Topics

Cognitive Modeling
Learning
Memory Models
Dynamical Systems
Discussion
New

There is nothing here, yet. Be the first to create a thread