Skip to main content
eScholarship
Open Access Publications from the University of California

Learning Via Compact Data Representation

Abstract

We present an unsupervised learning methodology derived from compact data encoding and demonstrate how to construct models of polysemy, priming, semantic disambiguation and learning using this theoretical basis. The model is capable of simulating human-like performance on artificial grammar learning.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View