AI TOOLS
ARTIFICIAL INTELLIGENCE
• Artificial intelligence (AI) – the science of
making machines imitate human thinking and
behavior
• Normally associated with Robot – a
mechanical
h i l device
d i equipped
i d with
i h simulated
i l d
human senses and the ability to take action on
its own
ARTIFICIAL INTELLIGENCE
• Some of AI systems/technologies
– Expert systems
– Neural networks
– Genetic algorithms
– Intelligent
I t lli t agentst (hundred
(h d d available)
il bl )
EXPERT SYSTEMS is an AI
• Expert (knowledge‐based) system – an
artificial
ifi i l intelligence
i lli system that
h applies
li
reasoning capabilities to reach a conclusion
• Used for
– Diagnostic problems (what’s wrong?)
– Prescriptive problems (what to do?)
Traffic Light Expert System
Developing and Using an Expert
System
• Step 1: expert provide expertise to knowledge
engineer
• Step 2: knowledge engineer converts expertise
to rules
• Step
S 3
3: computer – expert systems
• Step 4: user interface delivers facts to expert
system and sends back the conclusions to the
user
Wh Expert
What E Systems
S C and
Can dCCan’t
’ DDo
• An expert system can
– Reduce errors
– Improve customer service
– Reduce cost
• An expert system can’t
– Use common sense like human
– Automate all processes
NEURAL NETWORKS
Neural network (artificial neural network or
ANN) – an artificial intelligence system that is
capable of finding and differentiating patterns
Layers of a Neural Network
N
Neural
lNNetworks
t k Can…
C
• Learn and adjust to new circumstances on
their own
• Take
T k part in
i massive
i parallel
ll l processing
i
• Function without complete information
• Cope with huge volumes of information
• Analyze nonlinear relationships
GENETIC ALGORITHMS
Genetic algorithm – an artificial intelligence
system that mimics the evolutionary,
evolutionary survival
survival‐
of‐the‐fittest process to generate increasingly
better solutions to a problem
Evolutionary Principles of
Genetic Algorithms
1 Selection – or survival of the fittest or giving
1.
preference to better outcomes
2 Crossover
2. C – combining
bi i portioni off good d
outcomes to create even better outcomes
3. Mutation – randomly trying combinations
and evaluating the success of each
Genetic Algorithms
l h Can…
• Take thousands or even millions of possible
p
solutions and combining and recombining
p
them until it finds the optimal solution
INTELLIGENT AGENTS
• Intelligent agent – software that assists you,
or acts on yyour behalf,, in p
performingg
repetitive computer‐related tasks
Intelligent agent/software on a Web sites that
helps you, the customer, find products and
services you want –Amazon.com
Intelligent agent that takes action on your
o r
behalf
• Examples:
– Prioritize e‐mail
– Act as gaming partner (partner in game)
– Assemble customized news reports
p
– Fill out forms for you
– “Discuss” topics with you
Intelligent agents that can observe and report on
equipment such as a software that can
evaluate the performance of your computer,
scheduling antivirus scan etc.
Intelligent agent/software that can discover
important information from a data warehouse
– data mining(knowledge discovery)‐
discovery) google
Reflection: state some keywords which
can associate with words below
Expert systems
Neural networks
Genetic algorithms
I t lli
Intelligent
t agents
t
