This book names and explains the high-level components of an intelligent system. It's all here: the parts to the system, how they interact,
what they do, and how they are all connected. Pretty scary that intelligence has been reduced to a set of system components.
Pretty scary when system designers start to put these pieces into machinery that operates or inhabits our present society.
p.15"The convergence of results from the neurosciences, artificial intelligence, robotics, computer-integrated
manufacturing, information science, and cognitive psychology suggests that at long last we are entering a period where the
study of mind can become a hard science. Theories can be formulated in terms of computational processes and tested experimentally
in software and hardware."
p.18"Our thesis is that mind will emerge from intelligent systems,
and intelligence will emerge from the joint functioning of four fundamental processes: behavior generation, world modeling,
sensory processing, and value judgment. We will show how these four processes can work together to process sensory information,
to build, maintain, and use an internal representation of the external world to select goals, react to sensory input, execute
tasks, and control actions. Sensory processing focuses attention, detects and groups features, computes attributes, compares
observations with expectations, recognizes objects and events, and analyzes situations. World modeling constructs and maintains
an internal representation of entities, events, relationships, and situations. It generates predictions, expectations, beliefs,
and estimates of the probable results of future actions. Value judgment assigns value to objects, events, and situations.
It computes the cost, benefit, risk, and expected payoff of future plans. It decides what is important or trivial, what is
rewarding or punishing, and what degree of confidence should be assigned to entries in the world model. Behavior generation
uses value judgment results to select goals, decompose tasks, generate plans, and control action."
You have to focus the machine's attention on building a model of the external world and searching
for ways to accomplish goals, based on how things are predicted to behave in the real world. There really is no other approach
that will make your proposed system smart:
p.80"the key to building practical intelligent systems lies in understanding
how to focus attention on what is important and ignore what is irrelevant. Attention is a mechanism for allocating sensors
and focusing computational resources on particular regions of time and space. Attention allows computational resources to
be dedicated to processing input that is most relevant to behavioral goals. Focusing of attention can be accomplished by directing
sensors toward regions in space classified as important and by masking, windowing, and filtering out input from sensors or
regions in space classified as unimportant."
Most intelligent systems focus on objects near them. Sometimes there is a need to focus on distant
objects, and this might involve a lot of computation and complex prediction of behavior. In certain circumstances, this is
necessary and has a definite payoff in term of system performance.
p.82"In most cases the region in space and time that is most relevant to the behavioral choices
of an intelligent system centers around the 'here and now.' Each intelligent system always resides at the center of
its own egosphere, in both space and time. The relevance of objects in the world is typically inversely proportional to their
spatial distance... Objects and events that lie far away in space and time can usually be safely ignored.
But not always. Sometimes distant objects and remote events can be very important. There
are occasions where the ability to perceive distant objects and predict events far in the future has significant survival
benefit. However, this capability incurs computational costs... Only likely future scenarios should be considered seriously,
and only the most important ones should be analyzed in any detail."
To focus attention implies that we know how to separate things that are important from those that
are not. This involves predicting how things in our world behave, and anticipating their movement ahead of time. We should
be able to simulate the likely unfolding of events and choose the path(s) which allow us to accomplish short-term
goals. We must be able to recognize situations that are favorable to us, or are likely to be favorable in the long run, by
performing value judgments/ assessments that are relatively fast and accurate. We should consider allowing margin
for a flexible response if/ when our predictions turn out to be inaccurate or when we face unexpected events in
the real world that our intelligent system inhabits.
p.82"In all cases, knowledge of what is important and the ability to focus attention on what is
important are critical to the design of intelligent systems. They are fundamental to a theory of mind. To build practical
cost-effective intelligent systems, we must understand how to design sensory processing systems that mask, window, and filter
the sensory data to extract information that is relevant to what is important in the world. We must understand how to build
value judgment systems that can distinguish between what is important and what is not. And we must understand how to design
behavior generation systems that can allocate behavioral resources to accomplish what is important to achieve."
Creatures in nature exhibit intelligent behavior for various reasons relating to survival and
reproduction. For intelligent machines, intelligent behavior is used to accomplish goals and for general maneuvering
relating to outwitting objects in their world that are blocking access to their goals. General-purpose 'positioning' is also
intelligent behavior - predicting how things might behave and anticipating actions (even if the 'forecast'
for expected behavior is only roughly accurate) is another hallmark of intelligence.
p.91"There are many things about intelligent behavior that remain a mystery, but one thing is perfectly
clear - the concept of a goal is central. Intelligent creatures do not wander aimlessly or simply react reflexively to their
immediate environment. They act proactively to accomplish their goals of survival and propagation in the most efficient manner
possible under given environmental conditions. They react to perturbations and unexpected events with alternative tactics
and behaviors so as to accomplish their goals despite difficulties and distractions along the way. Intelligent creatures are
goal-directed in performing behaviors... Intelligent creatures from insects to humans conserve resources and focus attention
on entities and events such as food and danger that are relevant to their goals. The more intelligent creatures are,
the more resourceful they are in dealing with difficulties and unexpected events. The most intelligent creatures can predict
the future. They can make plans that anticipate or preempt problems, and invoke tactics that accommodate difficulties and
compensate for unexpected events."
