# prj_550

AI and Robotics

Oct 19, 2013 (4 years and 7 months ago)

90 views

I welcome you all to this
presentation

On:

Neural Network Applications

Systems Engineering Dept. KFUPM

Imran Nadeem & Naveed R. Butt

220504 & 230353

Part II: LMS & RBF

Part I: Introduction to Neural Networks

Part III: Control Applications

Part I: Introduction to Neural
Networks

Part I: Introduction to NN’s

There is
no restriction

on the unknown
function to be linear. Thus, neural
networks provide a logical extension to
schemes.

Universal Approximation Theorem: neural
networks can
reproduce

any nonlinear
function for a limited input set.

Neural networks are parameterized
nonlinear functions

whose parameters can
be adjusted to achieve different shaped
nonlinearities.

In essence, we try to adjust the neural
network to serve as an
approximator

for
an unknown function that we know only
through its inputs and outputs

Human Neuron

Part I: Introduction to Neural
Networks

Artificial Neuron

Part I: Introduction to Neural
Networks

Part I: Introduction to Neural
Networks

Single Layer Feedforward NN’s

Part I: Introduction to Neural
Networks

Part I: Introduction to Neural
Networks

Multi
-
Layer Feedforward NN’s

Recurrent (feedback) NN’s

Part I: Introduction to Neural
Networks

A recurrent neural network distinguishes itself from
the feed
-
forward network in that it has at least one
feedback loop
. For example, a recurrent network may
consist of a single layer of neurons with each neuron
feeding its output signal back to the input of all input
neurons.

Recurrent (feedback) NN’s

Part I: Introduction to Neural
Networks

The presence of feedback loops has a profound impact
on the
learning capability

of the network and on its
performance.

Applications of NN’s

Part I: Introduction to Neural
Networks

Neural networks are applicable in virtually
every situation in which a
relationship

between
the predictor variables (independents, inputs)
and predicted variables (dependents, outputs)
exists, even when that relationship is very
complex
and not easy to articulate in the usual
terms of "correlations" or "differences between
groups”

Applications of NN’s

Part I: Introduction to Neural
Networks

Detection of medical phenomena

Stock market prediction

Credit assignment

Condition Monitoring

Signature analysis

Process control

End of Part I

Part II: LMS & RBF

Part II: LMS & RBF

Part II: LMS & RBF

Estimation Error

Actual Response

Estimated Response

Cost Function

Mean Square Error

Part II: LMS & RBF

RBF
-
NN’s

special class

of
functions. Their characteristic feature is
that their response decreases (or increases)
monotonically

with distance from a central
point and they are

Part II: LMS & RBF

RBF
-
NN’s

Gaussian

RBF

Part II: LMS & RBF

RBF
-
NN’s

Neural Networks based on radial bases
functions are known as RBF Neural Networks
and are among the
most commonly used

Neural Networks

Part II: LMS & RBF

RBF
-
NN’s

Two
-
layer
feed
-
forward

networks.

Output nodes : linear summation.

Very
fast learning

Good for
interpolation, estimation
& Classification

Part III: Control Applications

Part III: Control Applications

Nonlinear System Identification

Nonlinear System Identification

Part III: Control Applications

Nonlinear System Identification

Part III: Control Applications

Continuously Stirred Tank Reactor

Nonlinear System Identification

Part III: Control Applications

Simulation Results

Part III: Control Applications

Part III: Control Applications

Hammerstein Model

Part III: Control Applications

Simulation Results