Advanced

Natural Intelligence in Artificial Creatures

Balkenius, Christian LU (1995) 37.
Abstract
What mechanisms are needed in a cognitive system, such as an animal or a robot, and how do these mechanisms interact with each other?



The thesis presents a study of this problem within the field of behavior-based systems and artificial neural networks. The thesis brings together ideas from behavior-based robotics, control theory and machine learning and combines them with models from ethology, psychology and neurobiology in an attempt to synthesize a complete, artificial nervous system for a simulated artificial creature.



It is argued that an intelligent system cannot be based on a single general principle, but requires a large set of interacting systems. The main goal of the thesis is to identify... (More)
What mechanisms are needed in a cognitive system, such as an animal or a robot, and how do these mechanisms interact with each other?



The thesis presents a study of this problem within the field of behavior-based systems and artificial neural networks. The thesis brings together ideas from behavior-based robotics, control theory and machine learning and combines them with models from ethology, psychology and neurobiology in an attempt to synthesize a complete, artificial nervous system for a simulated artificial creature.



It is argued that an intelligent system cannot be based on a single general principle, but requires a large set of interacting systems. The main goal of the thesis is to identify these functional subsystems and to develop computational miniature models of them that can be combined into a complete system.



It is shown how goal-directed behavior can be categorized as appetitive, aversive, exploratory or neutral. This classification is a step away from a single hedonic dimension, and gives a richer framework for understanding reactive behavior. A number of learning mechanisms are developed that take this new framework into account, and it is shown how these mechanisms can account for a large range of classical and instrumental conditioning experiments, as well as more cognitive processes such as category learning, exploratory behavior and cognitive mapping. The role of expectations in learning is emphasized to map out the way for more cognitive abilities such as planning and problem solving. It is also shown how categorical, procedural and expectancy learning can all be based on different types of matching between the actual and the expected sensory state.



The central role of motivation and emotion within a cognitive theory is discussed, and it is shown that a central motivational system is necessary to coordinate behavior. (Less)
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • professor Lansner, Anders, NADA, KTH
organization
publishing date
type
Thesis
publication status
published
subject
keywords
Cognitive Studies
volume
37
pages
286 pages
defense location
N/A
defense date
1995-01-01 10:15
ISSN
1101-8453
ISBN
91-628-1599-7
language
English
LU publication?
yes
id
24d13168-0114-4073-9829-8a2f9d996acd (old id 526178)
alternative location
http://www.lucs.lu.se/People/Christian.Balkenius/Thesis/
date added to LUP
2007-10-03 14:00:06
date last changed
2016-09-19 08:45:00
@misc{24d13168-0114-4073-9829-8a2f9d996acd,
  abstract     = {What mechanisms are needed in a cognitive system, such as an animal or a robot, and how do these mechanisms interact with each other?<br/><br>
<br/><br>
The thesis presents a study of this problem within the field of behavior-based systems and artificial neural networks. The thesis brings together ideas from behavior-based robotics, control theory and machine learning and combines them with models from ethology, psychology and neurobiology in an attempt to synthesize a complete, artificial nervous system for a simulated artificial creature.<br/><br>
<br/><br>
It is argued that an intelligent system cannot be based on a single general principle, but requires a large set of interacting systems. The main goal of the thesis is to identify these functional subsystems and to develop computational miniature models of them that can be combined into a complete system.<br/><br>
<br/><br>
It is shown how goal-directed behavior can be categorized as appetitive, aversive, exploratory or neutral. This classification is a step away from a single hedonic dimension, and gives a richer framework for understanding reactive behavior. A number of learning mechanisms are developed that take this new framework into account, and it is shown how these mechanisms can account for a large range of classical and instrumental conditioning experiments, as well as more cognitive processes such as category learning, exploratory behavior and cognitive mapping. The role of expectations in learning is emphasized to map out the way for more cognitive abilities such as planning and problem solving. It is also shown how categorical, procedural and expectancy learning can all be based on different types of matching between the actual and the expected sensory state.<br/><br>
<br/><br>
The central role of motivation and emotion within a cognitive theory is discussed, and it is shown that a central motivational system is necessary to coordinate behavior.},
  author       = {Balkenius, Christian},
  isbn         = {91-628-1599-7},
  issn         = {1101-8453},
  keyword      = {Cognitive Studies},
  language     = {eng},
  pages        = {286},
  title        = {Natural Intelligence in Artificial Creatures},
  volume       = {37},
  year         = {1995},
}