Documente Academic
Documente Profesional
Documente Cultură
Applications
Presented By:
Ahmed Hashmi
Chinmoy Das
Inspiration from
Neurobiology
A neuron: many-inputs /
one-output unit
output can be excited or
not excited
incoming signals from
other neurons determine
if the neuron shall excite
("fire")
Output subject to
attenuation in the
synapses, which are
junction parts of the
neuron
A simple neuron
Takes the Inputs .
Calculate the
summation of the
Inputs .
Compare it with the
threshold being set
during the learning
stage.
Firing Rules
A firing rule determines how one calculates
whether a neuron should fire for any input
pattern.
some sets cause it to fire (the 1-taught set
of patterns) and others which prevent it from
doing so (the 0-taught set)
Example
For example, a 3input neuron is
taught to output 1
when the input
(X1,X2 and X3) is 111
or 101 and to output
0 when the input is
000 or 001.
X
1
:
0 0 0 0 1 1 1 1
X
2
:
X
3
:
0
/
1
0
/
1
0
/
1
0
/
1
O
U
T:
Example
Take the pattern 010. It differs
from 000 in 1 element, from 001 in
2 elements, from 101 in 3
elements and from 111 in 2
elements. Therefore, the 'nearest'
pattern is 000 which belongs in
the 0-taught set. Thus the firing
rule requires that the neuron
should not fire when the input is
001. On the other hand, 011 is
equally distant from two taught
patterns that have different
outputs and thus the output stays
undefined (0/1).
X
1
:
0 0 0 0 1 1 1 1
X
2
:
X
3
:
0
/
1
0
/
1
O
U
T:
Supervised Learning
Supervised learningwhich incorporates an
external teacher, so that each output unit is told what
its desired response to input signals ought to be.
During the learning process global information may
be required. Paradigms of supervised learning include
error-correction learning, reinforcement learning and
stochastic learning.
An important issue concerning supervised learning is
the problem of error convergence, ie the minimisation
of error between the desired and computed unit
values. The aim is to determine a set of weights
which minimises the error. One well-known method,
which is common to many learning paradigms is the
least mean square (LMS) convergence.
Unsupervised Learning
Unsupervised learninguses no external teacher and
is based upon only local information. It is also referred
to as self-organisation, in the sense that it selforganises data presented to the network and detects
their emergent collective properties.
From Human Neurons to Artificial Neurons their aspect
of learning concerns the distinction or not of a
separate phase, during which the network is trained,
and a subsequent operation phase. We say that a
neural network learns off-line if the learning phase and
the operation phase are distinct. A neural network
learns on-line if it learns and operates at the same
time. Usually, supervised learning is performed off-line,
whereas unsupervised learning is performed on-line.
Back-propagation Algorithm
it calculates how the error changes as each
weight is increased or decreased slightly.
The algorithm computes eachEWby first
computing theEA, the rate at which the
error changes as the activity level of a unit is
changed. For output units, theEAis simply
the difference between the actual and the
desired output.
Transfer Function
The behaviour of an ANN (Artificial Neural Network) depends on both
the weights and the input-output function (transfer function) that is
specified for the units. This function typically falls into one of three
categories:
linear (or ramp)
threshold
sigmoid
Forlinear units, the output activity is proportional to the total
weighted output.
Forthreshold units, the output is set at one of two levels,
depending on whether the total input is greater than or less than
some threshold value.
Forsigmoid units, the output varies continuously but not linearly
as the input changes. Sigmoid units bear a greater resemblance to
real neurones than do linear or threshold units, but all three must be
considered rough approximations.
Application
INTRODUCTION
Features of finger prints
Finger print recognition system
Why neural networks?
Goal of the system
Preprocessing system
Feature extraction using neural networks
Classification
result
edge
detecti
on
Ridge
extractio
n
Thinin
g
Feature
extractio
n
classifi
cation
Preprocessing system
Preprocessing system
After image is captured
,noise is removed using
edge detection, ridge
extraction and thinning.
Preprocessing system
Thinning: the extracted
ridges are converted into
skeletal structure in which
ridges are only one pixel
wide. thinning should not Remove isolated as well as
surrounded pixel.
Break connectedness.
Make the image shorter.
classification
Arch
Tented arch
Right loop
Left loop
Applications of Fingerprint
Recognition
As finger print recognition system can be
easily embedded in any system. It is used in Recognition of criminals in law enforcement bodies.
Used to provide security to cars, lockers, banks
,shops.
To differentiate between a person who has voted
and those who have not voted in govt. elections.
To count individuals.
Key Features
Neural network design, training, and simulation
Pattern recognition, clustering, and data-fitting tools
Supervised networks including feedforward, radial basis, LVQ,
time delay, nonlinear autoregressive (NARX), and layer-recurrent
Unsupervised networks including self-organizing maps and
competitive layers
Preprocessing and postprocessing for improving the efficiency of
network training and assessing network performance
Modular network representation for managing and visualizing
networks of arbitrary size
Routines for improving generalization to prevent overfitting
Simulinkblocks for building and evaluating neural networks, and
advanced blocks for control systems applications
Network Architectures
Neural Network Toolbox supports a variety of
supervised and unsupervised network
architectures. With the toolboxs modular
approach to building networks, you can develop
custom architectures for your specific problem.
You can view the network architecture including
all inputs, layers, outputs, and interconnections.
Supervised Networks
Supervised neural networks are trained to produce desired outputs in response to
sample inputs, making them particularly well-suited to modeling and controlling
dynamic systems, classifying noisy data, and predicting future events.
Neural Network Toolbox supports four types of supervised networks:
Feedforward networkshave one-way connections from input to output layers. They
are most commonly used for prediction, pattern recognition, and nonlinear function
fitting. Supported feedforward networks include feedforward backpropagation, cascadeforward backpropagation, feedforward input-delay backpropagation, linear, and
perceptron networks.
Radial basis networksprovide an alternative, fast method for designing nonlinear
feedforward networks. Supported variations include generalized regression and
probabilistic neural networks.
Dynamic networksuse memory and recurrent feedback connections to recognize
spatial and temporal patterns in data. They are commonly used for time-series
prediction, nonlinear dynamic system modeling, and control systems applications.
Prebuilt dynamic networks in the toolbox include focused and distributed time-delay,
nonlinear autoregressive (NARX), layer-recurrent, Elman, and Hopfield networks. The
toolbox also supports dynamic training of custom networks with arbitrary connections.
Learning vector quantization (LVQ)is a powerful method for classifying patterns
that are not linearly separable. LVQ lets you specify class boundaries and the
granularity of classification.
Unsupervised Networks
Unsupervised neural networks are trained by letting the network
continually adjust itself to new inputs. They find relationships
within data and can automatically define classification schemes.
Neural Network Toolbox supports two types of self-organizing,
unsupervised networks:
Competitive layersrecognize and group similar input vectors,
enabling them to automatically sort inputs into categories.
Competitive layers are commonly used for classification and
pattern recognition.
Self-organizing mapslearn to classify input vectors according
to similarity. Like competitive layers, they are used for
classification and pattern recognition tasks; however, they differ
from competitive layers because they are able to preserve the
topology of the input vectors, assigning nearby inputs to nearby
categories.
Improving Generalization
Improving the networks ability to generalize helps prevent
overfitting, a common problem in neural network design.
Overfitting occurs when a network has memorized the training set
but has not learned to generalize to new inputs. Overfitting
produces a relatively small error on the training set but a much
larger error when new data is presented to the network.
Application principles
The solution of a problem must be the simple.
Application principles
The speed is crucial for computer game applications.
If it is possible on-line neural network solutions should be
avoided, because they are big time consumers. Preferably,
neural networks should be applied in an off-line fashion, when
the learning phase doesnt happen during the game playing
time.
Application principles
On-line neural network solutions should be very simple.
Using many layer neural networks should be avoided, if
possible. Complex learning algorithms should be avoided. If
possible a priori knowledge should be used to set the initial
parameters such that very short training is needed for
optimal performance.
Application principles
All the available data should be collected about the problem.
Having redundant data is usually a smaller problem than not
having the necessary data.
The data should be partitioned in training, validation and
testing data.
Application principles
The neural network solution of a problem should be selected
from a large enough pool of potential solutions.
Because of the nature of the neural networks, it is likely that
if a single solution is build than that will not be the optimal
one.
If a pool of potential solutions is generated and trained, it is
more likely that one which is close to the optimal one is
found.
Problem
Problem analysis:
variables
modularisation into sub-problems
objectives
data collection
5
5
2
.
0
4
12345
3
2
1
7
.
5
5
5
5
2
.
2
.
2
0
0
0
4
4
4
3
1
1
3
1
3
2
2
2
23451234512
341
Network 11
Network 4
Network 7
Summary
Neural network solutions should be kept as simple as possible.
For the sake of the gaming speed neural networks should be
applied preferably off-line.
A large data set should be collected and it should be divided into
training, validation, and testing data.
Neural networks fit as solutions of complex problems.
A pool of candidate solutions should be generated, and the best
candidate solution should be selected using the validation data.
The solution should be represented to allow fast application.