artificial intelligence quiz
characteristics of an intelligent agent
autonomy, adaptivity, sociability
cube
common term for the representation of multidimensional information
examples of fuzzy logic
washing machines that wash until the water is 'clean'
an expert system is an
artificial intelligence system that applies reasoning capabilities to reach a conclusion - you provide the facts it solves the problem
crossover
combining portions of good outcomes in the hope of creating an even better outcome
information agents
search for information and bring it back to you
a genetic algorithm can find
the best or optimal answer
a neural network is an
AI system which is capable of learning because it is patterned after the human brain, it uses parallel processors (pattern recognition) key word is learning
expert systems
Computerized advisory programs that imitate the reasoning processes of experts. they consist of a knowledge base and set of rules to apply to a situation
compare decision support system with AI:
DSS is actively involved with the system, relies on user expertise, the user makes the ultimate decision/choice AI: user is not actively involved - expertise is built into the system, the system makes the ultimate decision
monitoring and surveillance agents
constantly observe and report back on what they see
takes something user does not know and applies rules to indicate what to do
expert system
which form of AI uses if statements and user answers to questions in order to reason just like a human does?
expert system
what is the most common form of AI in a business?
expert systems
what system uses 'if' statements
expert systems to determine what is 'known'
T/F expert systems can learn and change their own programming
false
what works to find optimal solution?
genetic algorithm
artificial intelligence
is the science of making machines imitate human thinking and behavior - reasoning -being able to adapt - ability to solve a problem
neural networks
mimic the way the brain works, analyzes large quantities of data and info to establish patterns and relationships
the concepts of evolution in genetic algorithm
selection, crossover, mutation
user agents
take action on your behalf
what can expert systems not do?
1. handle all types of domain expertise, can't put everything into machine form 2. can't solve problems in areas not designed for, can't learn to solve new things 3. apply common sense or judgement to a problem
genetic algorithms
mimic the evolutionary, survival-of-the-fittest process to generate increasingly better solutions to a problem - work to find the best/optimal answer
can learn and recognize patterns and can apply that learning to the unknown
neural Network
what network detects fraud detection?
neural network
what network can change?
neural networks
can an expert system be biased?
only if you program in bias
data mining agents
operate in a data warehouse discovering information (relationships and patterns)
selection
or survival of the fittest. the key is to give preference to better outcomes
mutation
randomly trying combinations and evaluating the success or failure of the outcome
neural networks can
recognize problems
expert systems apply
rules to solve a problem
an intelligent agent
senses its environment and then carries out some operations on behalf of a user
types of intelligent agents
-Information -Monitoring and Surveillance or predictive -Data mining -User
what kind of tasks do expert systems perform?
1. auditing and tax planning 2. diagnosing illnesses 3. managing forest resources 4. evaluate credit and loan applications etc
what can expert systems do?
1. handle massive amounts of info and provide new info 2. draw conclusions from complex relationships 3. explain reasoning 4. provide consistency in decision making 5. improve customer service 6. reduce errors and costs 7. provide portable knowledge
neural networks can be used to
1. typically used to combat attempts at fraud 2. able to detect money laundering attempts 3. make investment decisions
AI is never
DSS
where are the letter located? A and B by x and Y
X is in the row position Y is in the column A and B are data points/values
fuzzy logic
a special field of computer science that allows for shades of gray and doesn't require conditions to be black/white yes/no or true/flase
intelligence agents
accomplish a specific task for the user
an intelligent agent can
act on behalf of someone else
monitoring and surveillance agents are
constantly observing and reporting back, such as spell checker, grammar check
the intelligent agent will
take your profile and preferences and then go out and work on your behalf