Many have tried to reduce the "mind" to a set of basic components
that function as a system. Albus and Meystel present their viewpoint, and it is from an engineering rather than
psychological perspective.
p.xx"This book [published in 2002] is about robotic brains as they
should be implemented in the very near future. The biologists and psychologists will find the engineering views on cognitive
processes in [the] human brain."
Here is the reduction of intelligence to a set of system-level components:
p.1"The phenomenon of intelligence is demonstrated as a computational
phenomenon. It emerges as a result of the joint functioning of several operators: grouping, focusing attention, searching,
and formation of combinations. When information is processed by these operators, multiresolutional systems of knowledge develop,
and nested loops of knowledge processing emerge. This conceptual structure permits the explanation of most of the processes
characteristic of intelligent systems."
p.2"What is lacking is a general theoretical model of intelligence that ties all these separate
areas of knowledge into a unified framework... it is emphasized that an intelligent system always has an architecture that
develops as a result of the joint functioning of certain computational operators. The architecture that emerges as a result
has multiple closed loops, each loop at a particular level of resolution.
Our model is to be used for the analysis of all kinds of intelligent systems, including
animals, humans, automated machines, robots, autonomous vehicles, and integrated manufacturing systems."
Here we define intelligence as a capacity to increase the chances of achieving goals.
p.3"Intelligence is the ability of a system to act appropriately in an uncertain environment,
where an appropriate action is that which increases the probability of success, and success is the achievement of behavioral
subgoals that support the system's ultimate goal."
Systems composed of carefully constructed parts can appear to behave intelligently. The intelligent
system attempts to achieve goals in uncertain environments, primarily by "knowing" how to maneuver in its environment.
p.11"In this book, we approach the phenomenon of intelligence from a systems engineering viewpoint.
Our goal is to develop engineering guidelines that enable the design and construction of intelligent systems that rival natural
intelligence in performance of significant tasks in the natural world. In the following pages we set forth an outline for
a theory of intelligence and propose a reference model architecture that can serve as a guideline for engineering intelligent
systems."
The internal model that an intelligent system creates, updates, and generally
uses to plan interactions in the world is a critical component of an intelligent system.
p.17"The ability to transform 'reality' into a 'representation of reality' can be considered to
be one of the most important phenomena linked with intelligence."
Objects in the world model of an intelligent system are composed of smaller pieces, intelligently
placed into "groups" for handling at a higher level.
p.44"Grouping includes various procedures of clustering, class formation, unifying of sets, construction
of strings, n-tuples, and so on."
Focusing attention is a critical component of an intelligent system. Due to the huge amount
of information available from sensors, we need a practical way to locate the cues that are important for problem
solving which are often buried in other non-essential information.
p.44"The scope of representation is satisfied by focusing attention upon a subset of the world sufficient
for problem solving. After this, the rest of the information about the world can be neglected... We will never use information
more precise (and detailed) than that available at the resolution of the level of consideration... Condition of windowing.
This condition is satisfied by proper selection of the size and the law of motion within the scene for the sliding window
applied for the consecutive clustering and generalization procedures... All three conditions are prerequisites for the operation
of search"
Attention focusing permits us to extract meaningful information from our world which is
strategically useful for decision making.
p.80"The development of human intelligence would be impossible without attention focusing"
Grouping, focusing attention, and combinatorial search (often abbreviated
GFACS) are essential features for intelligent behavior. It would therefore seem essential when developing a computer
program that plays chess to identify and optimize the components that perform these features.
If your program out thinks other programs, it will be due to the fact that it performs these functions
better than the competition:
p.83"No matter what the package is that one acquires for an intelligent system, no matter from which
company it is bought, this package, if it is complete, will perform attention focusing, grouping, and combinatorial search."
Intelligent systems can either react to the present location of objects in their world, or they
can react to the anticipated locations of these objects. Anyone who has played on a sports team knows that anticipating what
your opponent is going to do (by looking for cues in behavior) and estimating what he or she can do will generally
make you a better player.
p.350-351"in reactive behavior, robots usually react to the present situation. In a system with
planning they react to the anticipated future.
Thus planning can be considered an anticipatory reactive behavior. The difference is
in the fact that anticipation requires richer representation than the simple reactive behavior requires."
