Soft Computing

300 (3)
Dr. Lekshmi R. R.
Asst. Prof.
Department of Electrical & Electronics
Engineering
Amrita School of Engineering 1
Perceptron
 Introduction
• More powerful learning rule
• Has 3 layers
– Sensory unit
– Associative unit
– Response unit
1 𝑖𝑓 𝑦𝑖𝑛 > 𝜃
𝑦 = ቐ 0 𝑖𝑓 −𝜃 ≤ 𝑦𝑖𝑛 ≤ 𝜃
−1 𝑖𝑓 𝑦𝑖𝑛 < −𝜃
• Weights adjusted using perceptron learning rule
𝑤𝑛𝑒𝑤 = 𝑤𝑜𝑙𝑑 + ∆𝑤
∆𝑤 = 𝛼𝑡𝑥𝑖
• 𝑡: target
• 𝛼 : learning rate
• 𝑥𝑖 : input
 Architecture
1
𝑏
Application
𝑥1 𝑋1 𝑤1 Classification
y
𝑤2 𝑌
𝑥2
𝑋2
 Perceptron Learning
Step 1: Initialize weights and bias. Step 7: Adjust the weights and bias if error exist
Set learning rate α (0< α<1) (y≠t) new

Step 2: While termination condition is false, do 𝑤𝑖 = 𝑤𝑖 𝑜𝑙𝑑 + 𝛼𝑡𝑥𝑖

steps 3 - 8 𝑏new = 𝑏𝑜𝑙𝑑 + 𝛼𝑡
Step 3: For each training pair, do steps 4-7
Step 4: Set input activation functions; xi=si Else new
𝑤𝑖 = 𝑤𝑖 𝑜𝑙𝑑
Step 5: Compute response of system
𝑛 𝑏new = 𝑏𝑜𝑙𝑑
𝑦𝑖𝑛 = 𝑏 + ෍ 𝑥𝑖 𝑤𝑖
𝑖=1
Step 8: Test stopping condition
Step 6: Set output activation functions
1 𝑖𝑓 𝑦𝑖𝑛 > 𝜃 – If no weights are changed, stop
𝑦 = ቐ 0 𝑖𝑓 −𝜃 ≤ 𝑦𝑖𝑛 ≤ 𝜃 – Else continue
−1 𝑖𝑓 𝑦𝑖𝑛 < −𝜃
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 1 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 𝛼=1 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

0 0 0
1 1 1 1 0 0 N 1 1 1 1 1 1
1 0 1 -1 2 1 N -1 0 -1 0 1 0
0 1 1 -1 1 1 N 0 -1 -1 0 0 -1
0 0 1 -1 -1 -1 Y 0 0 0 0 0 -1
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 2 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

0 0 -1
1 1 1 1 -1 -1 N 1 1 1 1 1 0
1 0 1 -1 1 1 N -1 0 -1 0 1 -1
0 1 1 -1 0 0 N 0 -1 -1 0 0 -2
0 0 1 -1 -2 -1 Y 0 0 0 0 0 -2
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 3 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

0 0 -2
1 1 1 1 -2 -1 N 1 1 1 1 1 -1
1 0 1 -1 0 0 N -1 0 -1 0 1 -2
0 1 1 -1 -1 -1 Y 0 0 0 0 1 -2
0 0 1 -1 -2 -1 Y 0 0 0 0 1 -2
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 4 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

0 1 -2
1 1 1 1 -1 -1 N 1 1 1 1 2 -1
1 0 1 -1 0 0 N -1 0 -1 0 2 -2
0 1 1 -1 0 0 N 0 -1 -1 0 1 -3
0 0 1 -1 -3 -1 Y 0 0 0 0 1 -3
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 5 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

0 1 -3
1 1 1 1 -2 -1 N 1 1 1 1 2 -2
1 0 1 -1 -1 -1 Y 0 0 0 1 2 -2
0 1 1 -1 0 0 N 0 -1 -1 1 1 -3
0 0 1 -1 -3 -1 Y 0 0 0 1 1 -3
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 6 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

1 1 -3
1 1 1 1 -1 -1 N 1 1 1 2 2 -2
1 0 1 -1 0 0 N -1 0 -1 1 2 -3
0 1 1 -1 -1 -1 Y 0 0 0 1 2 -3
0 0 1 -1 -3 -1 Y 0 0 0 1 2 -3
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 7 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

1 2 -3
1 1 1 1 -1 -1 N 1 1 1 2 3 -2
1 0 1 -1 1 1 N -1 0 -1 1 3 -3
0 1 1 -1 0 0 N 0 -1 -1 1 2 -4
0 0 1 -1 -4 -1 Y 0 0 0 1 2 -4
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 8 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

1 2 -4
1 1 1 1 -2 -1 N 1 1 1 2 3 -3
1 0 1 -1 -2 -1 Y 0 0 0 2 3 -3
0 1 1 -1 0 0 N 0 -1 -1 2 2 -4
0 0 1 -1 -4 -1 Y 0 0 0 2 2 -4
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 9 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

2 2 -4
1 1 1 1 0 0 N 1 1 1 3 3 -3
1 0 1 -1 0 0 N -1 0 -1 2 3 -4
0 1 1 -1 -1 -1 Y 0 0 0 2 3 -4
0 0 1 -1 -4 -1 Y 0 0 0 2 3 -4
 Design a Perceptron to implement AND gate
No. of inputs: 3 Weight Value
x1 x2 1 t
𝑤1 0
1 1 1 1 No. of outputs:1
𝑤2 0
1 0 1 -1
b 0
0 1 1 -1
0 0 1 -1 1 𝑖𝑓 𝑦𝑖𝑛 > 0.2
Epoch 10 𝑦 = ቐ 0 𝑖𝑓 −0.2 ≤ 𝑦𝑖𝑛 ≤ 0.2
𝜃 = 0.2 −1 𝑖𝑓 𝑦𝑖𝑛 < −0.2

x1 x2 1 t yin y Y=t? Δw1 Δw2 Δb w1 w2 b

2 3 -4
1 1 1 1 1 1 Y 0 0 0 2 3 -4
1 0 1 -1 -1 -1 Y 0 0 0 2 3 -4
0 1 1 -1 -1 -1 Y 0 0 0 2 3 -4
0 0 1 -1 -4 -1 Y 0 0 0 2 3 -4
 Design a nn for the following truth table
w1=2; w2=3; b=-4 𝑥1 𝑤1 + 𝑥2 𝑤2 + 𝑏 = ±𝜃
𝑥2 0 1.4 2𝑥1 + 3𝑥2 − 4 = 0.2
𝑥1 2.1 0
2𝑥1 + 3𝑥2 = 4.2
𝑥2 0 1.27
2𝑥1 + 3𝑥2 − 4 = −0.2
𝑥1 1.9 0
2𝑥1 + 3𝑥2 = 3.8

Activaton function: Bipolar Threshold: 1

x1 x2 1 t x1w1 x2 w 2 b yin y
1 1 1 -1 2 3 -4 1 1
1 0 1 -1 2 0 -4 -2 -1
0 1 1 -1 0 3 -4 -1 -1
0 0 1 1 0 0 -4 -4 -1
Thank you