Transcript Artificial Intelligence, Expert Systems, and Neural Networks

Artificial Intelligence, Expert
Systems, and Neural Networks
Group 10
Cameron Kinard
Leaundre Zeno
Heath Carley
Megan Wiedmaier
Introduction
Artificial Intelligence
Expert Systems
Neural Networks
Business Use
Real World Application
What is Artificial Intelligence?
A branch of science dealing with behavior,
learning, and adaptation in machines.
Two Categories
Conventional
Computational
The two most common types of AI are
expert systems and neural networks.
Conventional Artificial Intelligence
A method involving the use of structured
formulas and statistical analysis.
Methods include
Expert systems
Case based reasoning
Bayesian networks
Behavior based AI.
Computational Artificial Intelligence
The method of analyzing existing
information and recognizing patterns.
Simply put, it has the ability to learn from
existing information.
Methods include
Neural networks
Evolutionary computation
Fuzzy systems.
What is an Expert System?
 A program structured by a set of rules and
procedures that take the knowledge, supplied by
an expert, and recommend a course of action in
order to solve specific problems.
 They use reasoning to work through problems
and offer recommendations that address these
problems.
 They are ideal for diagnostic and prescriptive
problems.
 They are usually built for specific applications
called domains.
Expert System Use
Field use
Accounting
Financial management
Production
Process control
Medication prescription
In many other domains
Expert Systems - Advantages
Its gathering and use of expertise
They can perform many functions that will
benefit organizations
Reduction in training costs
Decrease human error
Providing consistent answers to repetitive tasks
Safeguard sensitive company information
Expert Systems - Disadvantages
Its inability to solve problems for which it
was not designed
Its inability to use common sense and
judgment to solve newly encountered
problems
What is a Neural Network?
Artificial intelligence systems that can be
trained to recognize patterns and adapt to
new concepts and knowledge.
They are not bound by a set of rules
designed for a specific application.
They are able to imitate the human ability
to process information without following a
set of rules.
What are Neural Networks?
They use interconnecting neurons to
produce an output.
A neural network uses its neurons
collectively to execute its functions.
A neuron is the basic functioning element in a
neural network that takes inputs and produces
outputs.
This allows the neural network to continue
performing even if some of its neurons are
not functioning
Neural Network Use
 They are useful for identification, classification,
and forecasting when dealing with a large
amount of information.
 They are used in speech and visual recognition.
 Field use
Engineering
Drilling
Meteorology
Medical
Insurance industries
Military.
Neural Networks - Advantages
They can adjust to new information on
their own.
They are able to function without
structured information.
They are able to process large volumes of
data.
Neural Networks - Disadvantage
The neural networks have hidden layers.
The fact that these layers are hidden
prohibits users from adjusting the
connections reducing control of the
system.
Overall Business Use
The systems increase completion rates
and decrease error by reducing human
interaction.
These systems protect information and
utilize knowledge more efficiently to make
intelligent decisions.
Companies can gain an edge over their
competitors by implementing these
systems.
Real World Applications
Banks
Hospitals
Credit Card Companies
Manufacturers
Robotics
Medical Fields
Conclusion
Artificial Intelligence
Expert Systems
Neural Networks
Business Uses
Real World Applications
Any questions?