Scribd
Upload
54 views28 pages

ANN: Architectures: Ms. Manisha Saini

The document discusses perceptrons and their applications in classification problems. It describes single layer perceptrons that can classify linearly separable problems and multi-layer perceptrons that can handle non-linearly separable problems like the XOR problem. It provides flowcharts that outline the basic steps of how perceptrons are used for classification, including initializing weights, calculating activations, updating weights, and determining the decision boundary.

Uploaded by

Netaji Gandi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
54 views28 pages

ANN: Architectures: Ms. Manisha Saini

The document discusses perceptrons and their applications in classification problems. It describes single layer perceptrons that can classify linearly separable problems and multi-layer perceptrons that can handle non-linearly separable problems like the XOR problem. It provides flowcharts that outline the basic steps of how perceptrons are used for classification, including initializing weights, calculating activations, updating weights, and determining the decision boundary.

Uploaded by

Netaji Gandi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 28

ANN: Architectures

Ms. Manisha Saini


Assistant Professor
G D Goenka University
Perceptron
• Single layer feed-forward Perceptron
• Multi layer feed-forward Perceptron
Perceptron: Applications
• The perceptron is used for classification: classify correctly a set of
examples into one of the two classes C 1 and C 2.

• If the output of the perceptron is +1, then the input is assigned to


class C1
If the output of the perceptron is -1, then the input is assigned to C2
Perceptron: Classification
• Geometrically, we try to find a hyper-plane that separates the
examples of the two classes.
Decision boundary
Start

Initialize weights and bias


Set a(0 to 1)

For each
s:t 𝑁𝑜
 
Activation Input units
 
=  
𝑦𝑒𝑠

Flowchart
Activate net units yin

Apply Activation obtain


Y=f (yin)
If 𝑁𝑜
 
Y=t
 𝑦𝑒𝑠
   
b b

  𝑦𝑒𝑠 If weight
changes
𝑁𝑜
 
Stop
Linear Separable Problem
(Example :Linear Problem)
Can be solved using Single layer Feed
forward Perceptron
Define data /Define input and output data
Generation of random Numbers for Input
Generation of random Numbers for Output
Create and train perceptron
Plot decision boundary
Non Linear Separable Problem
(Example: XOR Problem)
Can be solved using Multi-layer
Perceptron
Define data/ Define input and output data
Prepare inputs & outputs for network
training
Create and train a multilayer perceptron
Plot classification result for the complete
input space

You might also like