neural networks research group
areas
people
projects
demos
publications
software/data
Integrated Connectionist Models: Building AI Systems on Subsymbolic Foundations (1994)
Risto Miikkulainen
Recently there has been a lot of excitement in cognitive science about the subsymbolic (i.e. parallel distributed processing, or distributed connectionist, or distributed neural network) approach. Subsymbolic systems seem to capture a number of intriguing properties of human-like information processing such as learning from examples, context sensitivity, generalization, robustness of behavior, and intuitive reasoning. These properties have been very difficult to model with traditional, symbolic techniques. Within this new paradigm, the central issues are quite different (even incompatible) from the traditional issues in symbolic cognitive science, and the research has proceeded without much in common with the past. However, the ultimate goal is still the same: to understand how human cognition is put together. Even if cognitive science is being built on a new foundation, as can be argued, many of the results obtained through symbolic research are still valid, and could be used as a guideline for developing subsymbolic models of cognitive processes. This is the approach taken in building DISCERN (DIstributed SCript processing and Episodic memoRy Network, a distributed neural network model of script-based story understanding. DISCERN is purely a subsymbolic model, 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 DISCERN. DISCERN is an integrated connectionist architecture. Independent neural network models of the various subtasks are brought together into a single system capable of performing the high-level cognitive task. In this chapter, I present motivation for such integrated connectionist models in general, describe the DISCERN system as an example, and discuss some of the main issues and prospects of the approach.
View:
PDF
,
PS
Citation:
Honavar, V., and Uhr, L., editors,
Artificial Intelligence and Neural Networks: Steps Toward Principled Integration
:483--508, 1994.
Bibtex:
@article{miikkulainen:integration94, title={Integrated Connectionist Models: Building AI Systems on Subsymbolic Foundations}, author={Risto Miikkulainen}, journal={Artificial Intelligence and Neural Networks: Steps Toward Principled Integration}, editor={Honavar, V., and Uhr, L.}, pages={483--508}, url="http://nn.cs.utexas.edu/?miikkulainen:integration94", year={1994} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Projects
Processing Script-Based Stories: The DISCERN System
1990 - 1994
Software/Data
DISCERN
DISCERN is a large, modular neural network system for reading, paraphrasing and answering questions about stereotypical ...
1993
Areas of Interest
Natural Language Processing (Cognitive)
Cognitive Science
Memory