SlideShare a Scribd company logo
1 of 29
Download to read offline
1
ARTIFICIAL NEURON
Biological Neuron
2
ARTIFICIAL NEURON
Biological Neuron
The brain may be thought of as a
complex computer
It has the following amazing
characteristics:
The ability to perform complex tasks (e.g. pattern
recognition, perception & motor control) much faster than
any computer – even though events occur in the nanosecond
range for silicon gates, and milliseconds for neural systems.
The brain has the ability to solve several problems
simultaneously using distributed parts of the brain
3
ARTIFICIAL NEURON
Biological Neuron
The ability to learn, memorize and still generalize
The brain is Fault Tolerant in two respects
- It is able to recognize many input signals that are
somewhat different from any signal we have seen before
(e.g. recognition of person from different pictures)
- It is able to tolerate damage to the neural system itself.
Most of the neurons are not replaced when they die. In
spite of continuous loss of neurons, we continue to learn
4
ARTIFICIAL NEURON
Biological Neuron
These characteristics prompted research in algorithmic
modeling of brain (biological neural systems)
Is it possible to truly model the human brain?
Not at the present. Current successes in neural modeling are
for small artificial NNs aimed at solving a specific task
5
ARTIFICIAL NEURON
Biological Neuron
The basic building blocks of biological neural systems are
nerve cells, referred to as neurons
About 100 billion neuron in the human brain
6
ARTIFICIAL NEURON
Biological Neuron
The neurons are arranged in approximately 1000 main
modules, each having about 500 neural networks
7
Biological Neuron
The main body of the cell collects the incoming signals from
the other neurons through its dendrites
The incoming signals are constantly being summed in the cell
body
If the result of the summation crosses a certain threshold, the
cell body emits a signal of its own (called firing of the
neuron)
This signal passes through the neuron’s axon, from where the
dendrites of other neurons pick it up
ARTIFICIAL NEURON
8
Biological Neuron
There are 1,000 to 10,000 dendrites in each neuron (few
millimeters long).
There is only one axon (several centimeters long)
The connection between dendrites and axon is
electrochemical and it is called synapse
The synapses modify (enhance or inhibit) the signal while
passing it on to dendrites
ARTIFICIAL NEURON
9
Biological Neuron
The human learning is stored in these synapses, and the
connection of neurons with other neurons
If stimulus at a dendrite causes the neuron to fire, then the
connection between that dendrite and axon is strengthened
If the arrival of stimulus does not cause the neuron to fire,
the connection weakens over time
ARTIFICIAL NEURON
10
ARTIFICIAL NEURON
Artificial Neuron Model
11
Artificial Neuron Model
ARTIFICIAL NEURON
12
Artificial Neuron Model
It receives a vector X of I input signals,
X = (x1, x2, …, xI)
either from the environment or from other artificial neurons
Each input signal xi is multiplied by a weight wi to strengthen
or weaken it
The neuron computes the weighted
sum of the input signals
ARTIFICIAL NEURON
13
Artificial Neuron Model
The weighted sum is usually called the activation of the
neuron
An activation function is applied on this weighted sum to
produce the output of the neuron
y = f(activation)
If the activation function is the unit step function, we can say
that an artificial neuron implements a nonlinear mapping
from a vector of real numbers to [-1, 1]
ARTIFICIAL NEURON
14
15
ARTIFICIAL NEURON
Implementation of Logic Functions
16
Artificial Neuron Model
Implementation of AND
function
Let W1 = W2 = 1
X1 X2 X1W1 + X2W2 Y
0 0 0 F
0 1 1 F  = any value >1 but <=2
1 0 1 F = 1.5 (e.g.)
1 1 2 T
With appropriate value of  of the unit step activation
function, we will get correct results
ARTIFICIAL NEURON
17
Artificial Neuron Model
We can graphically show the
AND functions input on a two
coordinate system (X1 and X2)
ARTIFICIAL NEURON
18
Artificial Neuron Model
The neuron outputs a 1, if
X1W1 + X2W2 ≥ θ, otherwise
the output is 0
Let θ = 1.5, W1 = W2 = 1
ARTIFICIAL NEURON
At the boundary between the output of 1 and 0 we have
X1 + X2 = 1.5
For plotting this boundary,
We first take X2 = 0, and get X1 = 1.5
And then we put X1 = 0, and get X2 = 1.5
19
Artificial Neuron Model
ARTIFICIAL NEURON
The neuron has drawn a line
from (1.5, 0) to (0, 1.5) in the
input plane
Any new data falling on the
left side of the line will result
in an output of zero (F)
and the data on the right side
of the line will result in one (T)
20
Artificial Neuron Model
Implementation of OR
function
Let W1 = W2 = 1
X1 X2 X1W1 + X2W2 Y
0 0 0 F
0 1 1 T
1 0 1 T
1 1 2 T
If we make  = 1 (or any value >0 but <=2), we will get
correct results with a unit step activation function
ARTIFICIAL NEURON
21
Artificial Neuron Model
If we place the 4 points in a
two coordinate system (X1 and
X2), we have drawn a line
from (1, 0) to (0, 1) in the
resulting plane
Any new data falling on the
left side of the line will give an
output of zero and the data on
the right side of the line will be
classified as one
ARTIFICIAL NEURON
22
Artificial Neuron Model
If we want to utilize a unit step function centered at zero for
both AND and OR neurons, we can incorporate another
input X0 constantly set at –1
The weight W0 corresponding to this input would be the ,
calculated previously . It is called bias
ARTIFICIAL NEURON
23
Artificial Neuron Model
AND function
W1 = W2 = 1
We have calculated  = 1.5 for this problem, so W0 =  = 1.5
X1 X2 X1W1 + X2W2 + (-1)W0 Y
0 0 0 – 1.5 = -1.5 F With bias
0 1 1 – 1.5 = -0.5 F a unit step
1 0 1 – 1.5 = -0.5 F function
1 1 2 – 1.5 = 0.5 T centered at
0 is used
ARTIFICIAL NEURON
24
ARTIFICIAL NEURON
Linearly Separable Problems
25
Linearly Separable Problems
Those problems for which the data can be correctly divided
into two categories by a line or hyper-plane
ARTIFICIAL NEURON
Because the equation
for the hyperplane is linear, hence
a single neuron is a linear
classifier
26
Linearly Separable Problems
Single neurons can realize linearly separable functions
Linear separation is achieved with the help of an n-
dimensional hyperplane created in the space of n-
dimensional input vectors
The hyperplane forms a boundary between the input vectors
associated with the two output values
ARTIFICIAL NEURON
27
Linearly Separable Problems
X1 X2 Y
1.0 1.0 1
9.4 6.4 -1
2.5 2.1 1
8.0 7.7 -1
0.5 2.2 1
7.9 8.4 -1
7.0 7.0 -1
2.8 0.8 1
1.2 3.0 1
7.8 6.1 -1
ARTIFICIAL NEURON
28
Linearly Separable Problems
Suppose we set the weight vector [w1, w2, ]
to [-1.3, -1.1, 10.9]
ARTIFICIAL NEURON
The output = f(xiwi)
= f(-1.3x1 –1.1x2 + 10.9)
To draw the boundary
line we take the output
as zero on the boundary
i.e.
-1.3x1 – 1.1x2 + 10.9 = 0
29
Linearly Separable Problems
If the data cannot be correctly
separated by a single line or
plane, then it is not linearly
separable
(e.g. exclusive OR problem)
ARTIFICIAL NEURON
A single layered neurons cannot classify the input patterns
that are not linearly separable.
We need more than one neurons arranged in more than one
layers

More Related Content

Similar to Lec-02.pdf

Artificial neural network paper
Artificial neural network paperArtificial neural network paper
Artificial neural network paperAkashRanjandas1
 
Neural network
Neural networkNeural network
Neural networkmarada0033
 
cs4811-ch11-neural-networks.ppt
cs4811-ch11-neural-networks.pptcs4811-ch11-neural-networks.ppt
cs4811-ch11-neural-networks.pptbutest
 
Soft Computering Technics - Unit2
Soft Computering Technics - Unit2Soft Computering Technics - Unit2
Soft Computering Technics - Unit2sravanthi computers
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications Ahmed_hashmi
 
Artificial Neural Networks
Artificial Neural NetworksArtificial Neural Networks
Artificial Neural NetworksArslan Zulfiqar
 
Neural Networks Ver1
Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1ncct
 
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesMultilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesIJCSES Journal
 
Acem neuralnetworks
Acem neuralnetworksAcem neuralnetworks
Acem neuralnetworksAastha Kohli
 
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNSArtificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNSMohammed Bennamoun
 
Neural networks
Neural networksNeural networks
Neural networksBasil John
 
تطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائية
تطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائيةتطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائية
تطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائيةssuserfdec151
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkAtul Krishna
 
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience hirokazutanaka
 
Perceptron (neural network)
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)EdutechLearners
 
Neural-Networks.ppt
Neural-Networks.pptNeural-Networks.ppt
Neural-Networks.pptRINUSATHYAN
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkPrakash K
 

Similar to Lec-02.pdf (20)

Artificial neural network paper
Artificial neural network paperArtificial neural network paper
Artificial neural network paper
 
Neural network
Neural networkNeural network
Neural network
 
Neural Networks.pptx
Neural Networks.pptxNeural Networks.pptx
Neural Networks.pptx
 
cs4811-ch11-neural-networks.ppt
cs4811-ch11-neural-networks.pptcs4811-ch11-neural-networks.ppt
cs4811-ch11-neural-networks.ppt
 
Soft Computering Technics - Unit2
Soft Computering Technics - Unit2Soft Computering Technics - Unit2
Soft Computering Technics - Unit2
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications
 
Artificial Neural Networks
Artificial Neural NetworksArtificial Neural Networks
Artificial Neural Networks
 
Neural Networks Ver1
Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1
 
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesMultilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
 
Acem neuralnetworks
Acem neuralnetworksAcem neuralnetworks
Acem neuralnetworks
 
neural-networks (1)
neural-networks (1)neural-networks (1)
neural-networks (1)
 
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNSArtificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
 
Neural networks
Neural networksNeural networks
Neural networks
 
تطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائية
تطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائيةتطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائية
تطبيق الشبكة العصبية الاصطناعية (( ANN في كشف اعطال منظومة نقل القدرة الكهربائية
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
JAISTサマースクール2016「脳を知るための理論」講義04 Neural Networks and Neuroscience
 
ANN.pptx
ANN.pptxANN.pptx
ANN.pptx
 
Perceptron (neural network)
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)
 
Neural-Networks.ppt
Neural-Networks.pptNeural-Networks.ppt
Neural-Networks.ppt
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 

Recently uploaded

VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130Suhani Kapoor
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSCAESB
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝soniya singh
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
chaitra-1.pptx fake news detection using machine learning
chaitra-1.pptx  fake news detection using machine learningchaitra-1.pptx  fake news detection using machine learning
chaitra-1.pptx fake news detection using machine learningmisbanausheenparvam
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...ranjana rawat
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Dr.Costas Sachpazis
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130Suhani Kapoor
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidNikhilNagaraju
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 

Recently uploaded (20)

VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentation
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptxExploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
chaitra-1.pptx fake news detection using machine learning
chaitra-1.pptx  fake news detection using machine learningchaitra-1.pptx  fake news detection using machine learning
chaitra-1.pptx fake news detection using machine learning
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfid
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 

Lec-02.pdf

  • 2. 2 ARTIFICIAL NEURON Biological Neuron The brain may be thought of as a complex computer It has the following amazing characteristics: The ability to perform complex tasks (e.g. pattern recognition, perception & motor control) much faster than any computer – even though events occur in the nanosecond range for silicon gates, and milliseconds for neural systems. The brain has the ability to solve several problems simultaneously using distributed parts of the brain
  • 3. 3 ARTIFICIAL NEURON Biological Neuron The ability to learn, memorize and still generalize The brain is Fault Tolerant in two respects - It is able to recognize many input signals that are somewhat different from any signal we have seen before (e.g. recognition of person from different pictures) - It is able to tolerate damage to the neural system itself. Most of the neurons are not replaced when they die. In spite of continuous loss of neurons, we continue to learn
  • 4. 4 ARTIFICIAL NEURON Biological Neuron These characteristics prompted research in algorithmic modeling of brain (biological neural systems) Is it possible to truly model the human brain? Not at the present. Current successes in neural modeling are for small artificial NNs aimed at solving a specific task
  • 5. 5 ARTIFICIAL NEURON Biological Neuron The basic building blocks of biological neural systems are nerve cells, referred to as neurons About 100 billion neuron in the human brain
  • 6. 6 ARTIFICIAL NEURON Biological Neuron The neurons are arranged in approximately 1000 main modules, each having about 500 neural networks
  • 7. 7 Biological Neuron The main body of the cell collects the incoming signals from the other neurons through its dendrites The incoming signals are constantly being summed in the cell body If the result of the summation crosses a certain threshold, the cell body emits a signal of its own (called firing of the neuron) This signal passes through the neuron’s axon, from where the dendrites of other neurons pick it up ARTIFICIAL NEURON
  • 8. 8 Biological Neuron There are 1,000 to 10,000 dendrites in each neuron (few millimeters long). There is only one axon (several centimeters long) The connection between dendrites and axon is electrochemical and it is called synapse The synapses modify (enhance or inhibit) the signal while passing it on to dendrites ARTIFICIAL NEURON
  • 9. 9 Biological Neuron The human learning is stored in these synapses, and the connection of neurons with other neurons If stimulus at a dendrite causes the neuron to fire, then the connection between that dendrite and axon is strengthened If the arrival of stimulus does not cause the neuron to fire, the connection weakens over time ARTIFICIAL NEURON
  • 12. 12 Artificial Neuron Model It receives a vector X of I input signals, X = (x1, x2, …, xI) either from the environment or from other artificial neurons Each input signal xi is multiplied by a weight wi to strengthen or weaken it The neuron computes the weighted sum of the input signals ARTIFICIAL NEURON
  • 13. 13 Artificial Neuron Model The weighted sum is usually called the activation of the neuron An activation function is applied on this weighted sum to produce the output of the neuron y = f(activation) If the activation function is the unit step function, we can say that an artificial neuron implements a nonlinear mapping from a vector of real numbers to [-1, 1] ARTIFICIAL NEURON
  • 14. 14
  • 16. 16 Artificial Neuron Model Implementation of AND function Let W1 = W2 = 1 X1 X2 X1W1 + X2W2 Y 0 0 0 F 0 1 1 F  = any value >1 but <=2 1 0 1 F = 1.5 (e.g.) 1 1 2 T With appropriate value of  of the unit step activation function, we will get correct results ARTIFICIAL NEURON
  • 17. 17 Artificial Neuron Model We can graphically show the AND functions input on a two coordinate system (X1 and X2) ARTIFICIAL NEURON
  • 18. 18 Artificial Neuron Model The neuron outputs a 1, if X1W1 + X2W2 ≥ θ, otherwise the output is 0 Let θ = 1.5, W1 = W2 = 1 ARTIFICIAL NEURON At the boundary between the output of 1 and 0 we have X1 + X2 = 1.5 For plotting this boundary, We first take X2 = 0, and get X1 = 1.5 And then we put X1 = 0, and get X2 = 1.5
  • 19. 19 Artificial Neuron Model ARTIFICIAL NEURON The neuron has drawn a line from (1.5, 0) to (0, 1.5) in the input plane Any new data falling on the left side of the line will result in an output of zero (F) and the data on the right side of the line will result in one (T)
  • 20. 20 Artificial Neuron Model Implementation of OR function Let W1 = W2 = 1 X1 X2 X1W1 + X2W2 Y 0 0 0 F 0 1 1 T 1 0 1 T 1 1 2 T If we make  = 1 (or any value >0 but <=2), we will get correct results with a unit step activation function ARTIFICIAL NEURON
  • 21. 21 Artificial Neuron Model If we place the 4 points in a two coordinate system (X1 and X2), we have drawn a line from (1, 0) to (0, 1) in the resulting plane Any new data falling on the left side of the line will give an output of zero and the data on the right side of the line will be classified as one ARTIFICIAL NEURON
  • 22. 22 Artificial Neuron Model If we want to utilize a unit step function centered at zero for both AND and OR neurons, we can incorporate another input X0 constantly set at –1 The weight W0 corresponding to this input would be the , calculated previously . It is called bias ARTIFICIAL NEURON
  • 23. 23 Artificial Neuron Model AND function W1 = W2 = 1 We have calculated  = 1.5 for this problem, so W0 =  = 1.5 X1 X2 X1W1 + X2W2 + (-1)W0 Y 0 0 0 – 1.5 = -1.5 F With bias 0 1 1 – 1.5 = -0.5 F a unit step 1 0 1 – 1.5 = -0.5 F function 1 1 2 – 1.5 = 0.5 T centered at 0 is used ARTIFICIAL NEURON
  • 25. 25 Linearly Separable Problems Those problems for which the data can be correctly divided into two categories by a line or hyper-plane ARTIFICIAL NEURON Because the equation for the hyperplane is linear, hence a single neuron is a linear classifier
  • 26. 26 Linearly Separable Problems Single neurons can realize linearly separable functions Linear separation is achieved with the help of an n- dimensional hyperplane created in the space of n- dimensional input vectors The hyperplane forms a boundary between the input vectors associated with the two output values ARTIFICIAL NEURON
  • 27. 27 Linearly Separable Problems X1 X2 Y 1.0 1.0 1 9.4 6.4 -1 2.5 2.1 1 8.0 7.7 -1 0.5 2.2 1 7.9 8.4 -1 7.0 7.0 -1 2.8 0.8 1 1.2 3.0 1 7.8 6.1 -1 ARTIFICIAL NEURON
  • 28. 28 Linearly Separable Problems Suppose we set the weight vector [w1, w2, ] to [-1.3, -1.1, 10.9] ARTIFICIAL NEURON The output = f(xiwi) = f(-1.3x1 –1.1x2 + 10.9) To draw the boundary line we take the output as zero on the boundary i.e. -1.3x1 – 1.1x2 + 10.9 = 0
  • 29. 29 Linearly Separable Problems If the data cannot be correctly separated by a single line or plane, then it is not linearly separable (e.g. exclusive OR problem) ARTIFICIAL NEURON A single layered neurons cannot classify the input patterns that are not linearly separable. We need more than one neurons arranged in more than one layers