ix Intelligence surrounds us. It is more than the occurrence
of artistic and creative brilliance. It is present in the moment-to-moment adaptation of systems to complex environments.
It is present in the recognition of patterns of energy, in the fine adjustment of motor movements to changes in physical orientation,
and even in the retrieval of old memories. Do systems that are capable of exhibiting this behavior have something
in common? If they do, what is it, and how might we describe it?
ix What does it mean to have intelligence in a computing device?
Can computers have intentions or exhibit purpose? Can computers learn new things or understand the meaning
of sentences? Just what is the nature of intelligence? Can intelligence exist outside the human person?
Can it be described by a set of abstract laws? What is consciousness and what is its relationship to intelligence? What is
perception and how can abstract concepts arise from perceptual experience? What is the mind and how does it relate to the
body? How can immaterial and abstract ideas affect material reality? These and similar questions make up the subject
matter of cognitive science.
p.3 Meaning is not a thing; it involves what is meaningful to us. Nothing is meaningful in itself.
Meaningfulness derives from the experience of a being of a certain sort in an environment of a certain sort...
George Lakoff (1987)
p.4 Cognitive science begins with the assumption that there is a common set of principles underlying
all instances of intelligence.
p.8 Intelligence is the ability to acquire knowledge, and not the knowledge itself. Although it may be relevant
to distinguish between intelligence and knowledge, it is also the case that it requires knowledge to acquire knowledge.
p.9 Reactivity, as defined here, relates to intelligence by the fact that any system's ability to
adapt to the environment is limited by its sensitivity to changes within that environment.
p.10 Strong method problem solvers depend on a large amount of knowledge for their intelligent behavior.
p.29 Artificial intelligence is that branch of computer science concerned with the creation
of a kind of software that might be considered to exhibit "intelligent" behavior.
p.30 The focus of AI is on building computational structures and designing strategies to search these structures
for a solution. From an AI perspective, problem solving is construed as a series of operations on the models of a domain...
The primary goal of the AI practitioner is to build successful software, and not necessarily to implement human
intelligence!
p.75 Since no organism can cope with infinite diversity, one of the most basic functions of all
organisms is the cutting up of the environment into classifications by which non-identical stimuli can be treated as equivalent...
Eleanor Rosch (1978)
p.75, 76 For cognitive scientists there is no topic more important, or more controversial, than
the role of representation in intelligence... To achieve a clear understanding of mental representations we first
make precise our task. Remember that our goal is to model intelligent systems; towards this end we need to understand how
intelligent systems represent their world. Furthermore, we need to understand the knowledge they acquire from their experiences
in the world... A representational scheme must be able to capture all types of knowledge.
p.144 Cosmides and Tooby (1992, pg.163) write:
Because we know that the human mind is the product of the evolutionary process, we know something vitally
illuminating: that, aside from those properties acquired by chance, the mind consists of a set of adaptations, designed
to solve the long-standing adaptive problems humans encountered as hunter-gatherers.
p.255 An ant, viewed as a behaving system, is quite simple. The apparent complexity of its behavior
is largely a reflection of the complexity of the environment in which it finds itself.
Herbert Simon (1981)
Intelligence for a system with limited processing resources consists in making wise choices of what
to do next.
Newell & Simon (1976)
p.268-269 humans do play chess, and some humans play it quite well. We contend that they use heuristics
to calculate and prune subsections of the potentially huge search space.
p.293 There are three reasons for employing an heuristic search algorithm. The first is as a method
for modeling the search patterns intelligent humans employ in their problem solving... Knowledge based heuristics
rest on the amount and quality of knowledge in the application, the ordering of the knowledge, and the shape of the representation
that captures this knowledge.
The second reason for heuristic search is as a method for dealing with complex search spaces.
The third is to help cope with imprecise or missing data. Handling complexity is a mark of intelligence, as is the
ability to reason with imprecise or missing data.
p.319 There are three components of the blackboard system: 1) the central global data base
called the blackboard, 2) one or more independent knowledge sources, KSs, each operating independently on the global
data base, using the data base to receive its data for processing as well as for posting the results of its work, and 3) a
control regime for handling the interaction of the knowledge sources with the blackboard... each knowledge source
(KS) gets its data from the blackboard, processes it, and returns its results to the blackboard to be used by the other knowledge
sources. Each KS is independent in that it is a separate process operating according to its own specifications...
p.382 The computational techniques presented in this chapter are designed to model adaptive and emergent
behavior... In fact, the methods of this chapter work best on those tasks which symbolic models seem to handle poorly.
