p.1"Philosophers have been trying for over two thousand years to
understand and resolve two big questions of the universe: how does a human mind work, and can non-humans have minds? However,
these questions are still unanswered."
What is the goal when setting out to build an intelligent machine?
p.4"To build an intelligent computer system, we have to capture,
organise and use human expert knowledge in some narrow area of expertise."
What does machine intelligence mean? For Negnevitsky:
p.18"A machine is thought intelligent if it can achieve human-level
performance in some cognitive task. To build an intelligent machine, we have to capture, organise and use human expert knowledge
in some problem area."
The following quote identifies a key problem area in the field of
artificial intelligence:
p.20"One of the main difficulties in building intelligent machines,
or in other words in knowledge engineering, is the 'knowledge acquisition bottleneck' - extracting knowledge from human experts.
What is knowledge? What qualifies someone to be an expert?
p.25"Knowledge is a theoretical or practical understanding of a
subject or a domain. Knowledge is also the sum of what is currently known... Those who possess knowledge are called experts...
Anyone can be considered a domain expert if he or she has deep knowledge (of both facts and rules) and strong practical experience
in a particular domain... most experts are capable of expressing their knowledge in the form of rules for problem solving."
How specifically does an expert system work?
p.35"In a rule-based expert system, the domain knowledge is represented
by a set of IF-THEN production rules and data is represented by a set of facts about the current situation. The inference
engine compares each rule stored in the knowledge base with facts contained in the database. When the IF (condition) part
of the rule matches a fact, the rule is fired and its THEN (action) part is executed... The matching of the rule IF parts
to the facts produces inference chains."
Here is another way to represent knowledge in a computer:
p.131"Knowledge in a computer can be represented through several
techniques. In the previous chapters, we considered rules. In this chapter, we will use frames for the knowledge representation...
A frame is a data structure with typical knowledge about a particular object or concept. Frames... are used to capture and
represent knowledge in a frame-based expert system."
What did chess champion Kasparov have to say about his defeat at
the hands of a machine in a 1997 exhibition tournament?
p.165"'The computer hasn't proved anything yet', angry Garry Kasparov,
the world chess champion, said after his defeat in New York in May 1997, 'If we were playing a real competitive match, I would
tear down Deep Blue into pieces.'"
Can you build an expert system without knowing intimate details
about the field in question? Negnevitsky thinks not:
p.301"The process of building an intelligent system begins with
gaining an understanding of the problem domain. We first must assess the problem and determine what data are available and
what is needed to solve the problem. Once the problem is understood, we can choose an appropriate tool and develop the system
with this tool. The process of building intelligent knowledge-based systems is called knowledge engineering."
Do experts know, in all cases, how to quantify their knowledge in
rules? Not all the time:
p.305"Quite often the experts are unaware of what knowledge they
have and the problem-solving strategy they use, or are unable to verbalize it... Understanding the problem domain is critical
for building intelligent systems. A classical example is given by Donald Mitchie (1982). A cheese factory had a very experienced
cheese-tester who was approaching retirement age. The factory manager decided to replace him with an 'intelligent machine'.
The human tester tested the cheese by sticking his finger into a sample and deciding if it 'felt right'. So it was assumed
the machine had to do the same - test for the right surface tension. But the machine was useless. Eventually, it turned out
that the human tester subconsciously relied on the cheese's smell rather than on its surface tension and used his finger just
to break the crust and let the aroma out."
Can we go directly to building an expert system, or do we need to
do something else first? Negnevitsky thinks that we first need to build a prototype:
p.305"We must not make a detailed analysis of the problem before
[first creating and then] evaluating the prototype. This involves creating an intelligent system - or, rather, a small version
of it - and testing it with a number of test cases... The main goal of the prototyping phase is to obtain a better understanding
of the problem... As soon as the prototype begins functioning satisfactorily, we can assess what is actually involved in developing
a full-scale system... The development of an intelligent system is, in fact, an evolutionary process."
What is the difference between data and knowledge?
p.349"Data is what we collect and store, and knowledge is what helps
us to make informed decisions. The extraction of knowledge from data is called data mining... The ultimate
goal of data mining is to discover knowledge."
What tools do we use for data mining?
p.352"The most popular tool used for data mining is a decision
tree. A decision tree can be defined as a map of the reasoning process... A decision tree consists of nodes, branches
and leaves."
Does a decision tree guarantee good results?
p.358"Decision trees are as good as the data they represent."
