IGI PUBLISHING
ITJ4001
Int’l Journal of Cognitive Informatics and Natural Intelligence, 2(1), 1-16, January-March 2008 1
701 E. Chocolate Avenue, Suite 200, Hershey PA 17033-1240, USA
Tel: 717/533-8845; Fax 717/533-8661; URL-http://www.igi-global.com
This paper appears in the publication, International Journal of Cognitive Informatics and Natural Intelligence, Volume 2, Issue 1
edited by Yingxu Wang © 2008, IGI Global
A Cognitive Approach to the
Mechanism of Intelligence1
Yi X. Zhong, Beijing University of Posts and Telecommunications, China
ABstRACt
An attempt was made in the article to propose a new approach to the intelligence research, namely the
cognitive approach that tries to explore in depth the core mechanism of intelligence formation of intelligent
systems from the cognitive viewpoint. It is discovered, as result, that the mechanism of intelligence formation
in general case is implemented by a sequence of transformations conversing the information to knowledge
and further to intelligence (i.e., the intelligent strategy, the embodiment of intelligence in a narrower sense).
It is also discovered that the three major approaches to AI that exist, the structural simulation approach,
the functional simulation approach, and the behavior simulation approach, can all be harmoniously unified
within the framework of the cognitive approach. These two discoveries, as well as the related background,
will be reported here in the article.
Keywords:
core mechanism of intelligence formation; information theory; information-knowledgeintelligence transformation; intelligence theory; knowledge theory
IntRodUCtIon
Artificial intelligence is a branch of modern
science and technology aiming at the exploration
of the secrets of human intelligence on one hand
and the transplantation of human intelligence to
machines on the other hand, so that machines
are able to perform functions as intelligently as
they can. What is the essence of intelligence, as
we should understand it in the scientific context,
then? What are the parts of human intelligence
that can technically be feasible for transplanting
to machines? In what ways would humans be
able to make machines really intelligent? These
are some of the major issues we should make
clear in AI research.
Due to the high complexity of the issues,
there have been many approaches proposed
in history to the research of these secrets.
The three dominant approaches are: (1) the
structural simulation approach, whose typical
representative is neural networks, (2) the
functional simulation approach, whose typical
representative is expert systems, and (3) the
behavior simulation approach, whose typical
representative is sensory-motor systems.
They study the intelligence, respectively, from
different angles of views: (1) the views of the
biological neural networks structure in human
brain, (2) the views of its logical reasoning
processes, and (3) the views of its input-output
behavior. They are good approaches to the
intelligence research, and therefore have all
made certain progresses so far.
Copyright © 2008, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global
is prohibited.
2
Int’l Journal of Cognitive Informatics and Natural Intelligence, 2(1), 1-16, January-March 2008
Some of the technically well-known
contributors of the three approaches to AI can
be briefly listed as the following.
A great number of artificial neural network
models, algorithms, and applications have been
developed in the line of the first approach. The
well-known contributions can be seen from,
for example, McCulloch and Pitts (1943),
Rosenblatt (1958), Hopfield (1982), Rumelhart
et al. (1990), and Ruan (2006). Various results
in symbolic logic and expert systems with applications in wide areas have been presented
in the stream of the second approach. The
impressive achievements can be found from,
for instance, Feigenbaum and Feldman (1963),
Simon (1969), Newell and Simon (1972), Barr
et al. (1982), Russell and Norvig (2006), and
many more. Quite extractive sensory-motor
systems have been designed in the thought of
the third approach. The outstanding examples
can be seen from Brooks (1990, 1991). Note
that the neural networks approach (also called
connectionism approach), has been renamed
the computational intelligence since the early
1990s through the process of combining fuzzy
logic and genetic algorithms.
On the other hand, however, each of the
three approaches has also been confronted with
respective and critical difficulties.
The neural networks approach faces
the dilemma in dealing with the relationship
between the structural complexity and the
intelligent performance of neural networks. The
number of neurons in the human brain is as large
as 1010, and the total number of connections
among the neurons is in the order of 1014, and the
huge number of connections gives the guarantee
of high intelligence to the human brain. This
scale would be impossible, nevertheless, for
artificial neural networks to reach based on
industrial capability in modern technology. If the
number of neurons and connections in artificial
neural networks are reduced to the feasible order
for industrial implementation, the performance
in intelligence will be severely reduced, too. It is
very difficult, even for today and the near future,
to find a satisfactory compromise between the
complexity in structure and the performance
in intelligence.
The expert systems approach is confronted
with the difficulty in such issues as knowledge
acquisition, representation, and inference.
Knowledge is one of the most crucial bases for
any expert system, and nonetheless, most of
the knowledge bases have been basically built
up manually relying on the system designers.
It is, of course, hard work with low efficiency.
At the same time, the power of the means of
knowledge representation and inference based
on mathematical logic are also rather limited in
expression and operation. This leads to another
problem, severe limitation in practical applications. The low efficiencies, as a bottleneck, in
knowledge acquisition, representation, and
inference make the expert systems approach
far from as promising as it was announced and
expected in the early days of AI history.
Because the sensory-motor approach does
neither simulate the biological neural networks
of human brain, nor simulate the process
of symbolic manipulation, it therefore does
not need knowledge bases as that in expert
systems, nor does it suffer from the structural
dilemma mentioned before. It seems that it
is able to totally avoid such difficulties as
that seen either in neural networks or in the
expert systems approach. This may be true to
a certain extent. However, the sensory-motor
approach suffers from another difficulty, the
difficulty of having higher-level intelligence.
The performance the sensory-motor systems can
achieve is relatively simple in general, although
useful. It is really difficult for the sensorymotor approach to implement the high level
intelligence like thinking, reasoning, and many
other complicated features in intelligence.
Moreover, while facing certain critical
difficulties, the three approaches seemed not
quite harmonious to each other in the history of
their development, and it is still difficult to work
with them together nowadays. People from the
three disciplines sometimes even argued among
one another as to which one among the three
is the best. This makes researchers re-evaluate
the approaches to AI and find some new and
Copyright © 2008, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global
is prohibited.
14 more pages are available in the full version of this document,
which may be purchased using the "Add to Cart" button on the
publisher's webpage:
www.igi-global.com/article/cognitive-approach-mechanismintelligence/1550
Related Content
Interactive Feature Visualization and Detection for 3D Face Classification
Jason McLaughlin, Shiaofen Fang, Sandra W. Jacobson, H. Eugene Hoyme, Luther
Robinson and Tatiana Foroud (2013). Cognitive Informatics for Revealing Human
Cognition: Knowledge Manipulations in Natural Intelligence (pp. 98-110).
www.irma-international.org/chapter/interactive-feature-visualization-detectionface/72285/
Approximations in Rough Sets vs Granular Computing for Coverings
Guilong Liu and William Zhu (2010). International Journal of Cognitive Informatics and
Natural Intelligence (pp. 63-76).
www.irma-international.org/article/approximations-rough-sets-granularcomputing/43878/
Main Retina Information Processing Pathways Modeling
Hui Wei, Qingsong Zuo and XuDong Guan (2011). International Journal of Cognitive
Informatics and Natural Intelligence (pp. 30-46).
www.irma-international.org/article/main-retina-information-processingpathways/60740/
Wisdom as a Mental Tool of the Symbolic Species
(2011). Cognitive Informatics and Wisdom Development: Interdisciplinary Approaches
(pp. 90-106).
www.irma-international.org/chapter/wisdom-mental-tool-symbolicspecies/51437/
Cognitive Dynamic Systems
Simon Haykin (2011). International Journal of Cognitive Informatics and Natural
Intelligence (pp. 33-43).
www.irma-international.org/article/cognitive-dynamic-systems/63620/