comments

SOAR (an implemented model)

SOAR is a general intelligence system that learns by "chunking"—ie by collapsing the work of satisfying a subgoal into a single condition-action rule, or "production". It searches its explicit representations heuristically by means-ends analysis...

John Land, Allen Newell & Paul Rosenbloom (1987).
RELATED ARTICLESExplain
⌅
Artificial Intelligence
⌃
Can computers think? [1]
⌃
Yes: physical symbol systems can think [3]
■
SOAR (an implemented model)
□
Thermostats can have beliefs
□
Humans learn by adding symbolic data to knowledge base
□
The Biological Assumption
□
The Disembodied Mind Assumption
□
The Heuristic Search Assumption
□
The Knowledge Base Assumption
□
The language of thought
□
The Representationalist Assumption
□
The Rule-Following Assumption
□
The Symbolic Data Assumption
□
The Universal Conceptual Framework Assumption
□
The Chinese Room Argument [4]
□
AI programs are brittle
□
The critique of artificial reason
□
The Lighthill Report
□
Symbol systems can't think dialectically
□
Graph of this discussion
Enter the title of your article


Enter a short (max 500 characters) summation of your article
Enter the main body of your article
Lock
+Comments (0)
+Citations (0)
+About
Enter comment

Select article text to quote
welcome text

First name   Last name 

Email

Skip