Artificial General Intelligence via Finite Covering with Learning

Authors:
Yong K. Hwang;Samuel B. Hwang;David B. Hwang
Affiliations:
Think Life, Inc., Palo Alto, CA, USA;Think Life, Inc., Palo Alto, CA, USA;Think Life, Inc., Palo Alto, CA, USA
Venue:
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Year:
2008

Citing 2
Cited 0

Machine Learning

Machine Learning
The St. Thomas common sense symposium: designing architectures for human-level intelligence

AI Magazine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This position paper claims that the combination of solutions to a finite collection of problem instances and an expansion capability of those solutions to similar problems is enough to achieve the artificial general intelligence comparable to the human intelligence. Learning takes place during expansion of existing solutions using various methods such as trial and error, generalization, case-based reasoning, etc. This paper also looks into the amount of innate problem solving capability an artificial agent must have and the difficulty of the tasks the agent is expected to solve. To illustrate our claim examples in robotics are used where tasks are physical movements of the agent and objects in its environment.