[go: up one dir, main page]
Scribd
Upload
169 views13 pages

ANN Matlab

Uploaded by

Akhil Arora

This document discusses artificial neural networks in Matlab. It covers the basic architecture of a single neuron with weights, inputs and bias. It then discusses implementing perceptrons in Matlab to model logic gates like AND, OR, NAND and NOR gates. Finally, it briefly discusses implementing backpropagation networks and linear filters using neural networks in Matlab.

Copyright:

© All Rights Reserved
Download as PPS, PDF, TXT or read online from Scribd
Download as pps, pdf, or txt

ANN Matlab

Uploaded by

Akhil Arora
169 views13 pages
This document discusses artificial neural networks in Matlab. It covers the basic architecture of a single neuron with weights, inputs and bias. It then discusses implementing perceptrons in Matlab to model logic gates like AND, OR, NAND and NOR gates. Finally, it briefly discusses implementing backpropagation networks and linear filters using neural networks in Matlab.

Original Description:

MATLAB

Copyright

© © All Rights Reserved

Available Formats

PPS, PDF, TXT or read online from Scribd

Did you find this document useful?

Is this content inappropriate?

This document discusses artificial neural networks in Matlab. It covers the basic architecture of a single neuron with weights, inputs and bias. It then discusses implementing perceptrons in Matlab to model logic gates like AND, OR, NAND and NOR gates. Finally, it briefly discusses implementing backpropagation networks and linear filters using neural networks in Matlab.

Copyright:

© All Rights Reserved
Download as PPS, PDF, TXT or read online from Scribd
Download as pps, pdf, or txt
169 views13 pages

ANN Matlab

Uploaded by

Akhil Arora
This document discusses artificial neural networks in Matlab. It covers the basic architecture of a single neuron with weights, inputs and bias. It then discusses implementing perceptrons in Matlab to model logic gates like AND, OR, NAND and NOR gates. Finally, it briefly discusses implementing backpropagation networks and linear filters using neural networks in Matlab.

Copyright:

© All Rights Reserved
Download as PPS, PDF, TXT or read online from Scribd
Download as pps, pdf, or txt
You are on page 1/ 13

Artificial Neural Network

in Matlab
Hany Ferdinando

Architecture (single neuron)

w is weight matrices, dimension 1xR


p is input vector, dimension Rx1
b is bias

a = f(Wp + b)
Neural Network in Matlab

Transfer Function

Neural Network in Matlab

Architecture with neurons

w is weight matrices, dimension SxR


p is input vector, dimension Rxn
b is bias

Neural Network in Matlab

Multiple layers

Neural Network in Matlab

Perceptrons in Matlab
Make the perceptrons with net = newp(PR,S,TF,LF)
PR = Rx2 matrix of min and max values for R input elements
S = number of output vector
TF = Transfer function, default = hardlim, other option = hardlims
LF = Learning function, default = learnp, other option = learnpn

hardlim = hardlimit function


hardlims = symetric hardlimit function
learnpw = (t-a)pT = epT
learnpn normalized learnp
Wnew = Wold + W
bnew = bold + e
Neural Network in Matlab

where e = t - a

Compute manually
This

is an exercise how to run the artificial


neural network
From the next problem, we will compute
the weights and biases manually

Neural Network in Matlab

AND Gate in Perceptron


Performance is 0, Goal is 0

P = [0 0 1 1; 0 1 0 1];
T = [0 0 0 1];

0.9

net = newp([0 1; 0 1],1);


weight_init = net.IW{1,1}

bias_init = net.b{1}
net.trainParam.epochs = 20;
net = train(net,P,T);
weight_final = net.IW{1,1}

bias_final = net.b{1}
simulation = sim(net,P)

Training-Blue Goal-Black

0.8
0.7
0.6
0.5
0.4
0.3
0.2
0.1
0

3
6 Epochs

weight_init = [0 0], bias_init = 0


weight_final = [2 1], bias_final = -3
Neural Network in Matlab

OR Gate in Perceptron
P = [0 0 1 1; 0 1 0 1];
T = [0 1 1 1];

bias_init = net.b{1}
net.trainParam.epochs = 20;
net = train(net,P,T);
weight_final = net.IW{1,1}

0.9
0.8
Training-Blue Goal-Black

net = newp([0 1; 0 1],1);


weight_init = net.IW{1,1}

Performance is 0, Goal is 0

0.7
0.6
0.5
0.4
0.3

bias_final = net.b{1}

0.2

simulation = sim(net,P)

0.1
0

0.5

1.5

2
4 Epochs

2.5

3.5

weight_init = [0 0], bias_init = 0


weight_final = [1 1], bias_final = -1
Neural Network in Matlab

NAND Gate in Perceptron


Performance is 0, Goal is 0

P = [0 0 1 1; 0 1 0 1];
T = [1 1 1 0];

0.9

net = newp([0 1; 0 1],1);


weight_init = net.IW{1,1}

bias_init = net.b{1}
net.trainParam.epochs = 20;
net = train(net,P,T);
weight_final = net.IW{1,1}

Training-Blue Goal-Black

0.8
0.7
0.6
0.5
0.4
0.3

bias_final = net.b{1}

0.2

simulation = sim(net,P)

0.1
0

3
6 Epochs

weight_init = [0 0], bias_init = 0


weight_final = [-2 -1], bias_final = 2
Neural Network in Matlab

10

NOR Gate in Perceptron


Performance is 0, Goal is 0

P = [0 0 1 1; 0 1 0 1];
T = [1 0 0 0];

0.9

net = newp([0 1; 0 1],1);


weight_init = net.IW{1,1}
bias_init = net.b{1}
net.trainParam.epochs = 20;
net = train(net,P,T);
weight_final = net.IW{1,1}

bias_final = net.b{1}
simulation = sim(net,P)

Training-Blue Goal-Black

0.8
0.7
0.6
0.5
0.4
0.3
0.2
0.1
0

0.5

1.5

2
4 Epochs

2.5

3.5

weight_init = [0 0], bias_init = 0


weight_final = [-1 -1], bias_final = 0
Neural Network in Matlab

11

Backpropagation in Matlab
Make the backpropagation with
net = newff(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF)

PR = Rx2 matrix of min and max values for R input elements


S = number of output vector
BTF = Transfer function (user can use any transfer functions)
BLF = Learning function
PF = performance

xk+1 = xk - kgk
Neural Network in Matlab

12

Linear Filter (with ANN) in Matlab


Make the Linear Filter with newlin(PR,S,ID,LR)
PR = Rx2 matrix of min and max values for R input elements
S = number of output vector
ID = delay
LR = Learning Rate
Transfer function for linear filter is only linear line (purelin)

Neural Network in Matlab

13

You might also like