DISCERN

DISCERN (Distributed SCript processing and Episodic memoRy Net­work) is a distributed artificial neural network system and model of Script Process­ing that learns to process simple stereotypical narratives.

DISCERN is built purely on paral­lel distributed mechanisms, but at the high level it consists of modules and information structures similar to those of symbolic systems, such as scripts, lexicon, and Episodic Memory.

At the highest level of cog­nitive modeling, the symbolic and subsymbolic paradigms have to ad­dress the same basic issues. Outlining a parallel distributed approach to those issues is the purpose of this book. DISCERN is, above all, a prototype of a subsymbolic natural language processing system.

MIIKKULAINEN, Risto, 1993. Subsymbolic natural language processing: an integrated model of scripts, lexicon, and memory. . Cambridge, Mass: MIT Press. Neural network modeling and connectionism. ISBN 978-0-262-13290-9.

The terms "distributed neural networks/' "parallel distributed processing (PDP)/' and "subsymbolic" are used interchangeably in this book to refer to neural network models that process distributed representations of data. The term "connectionist" is used in a wider sense that also includes models based on local representations (distributed and local representations are discussed in section 2.2).