Page 191 - AI Computer 10

The activation function compares this weighted sum to a threshold value, T. If the sum is larger than the threshold
value, the output is 1; otherwise, it is 0.
Example: Perceptron Model for Cricket Match Decision

Let us represent a perceptron for deciding whether a cricket match can be conducted or not, by defining the
inputs that might be relevant for the match conditions, the weights for these inputs, the bias, and the threshold
value for the function.
Inputs:
a. Dry Pitch, X1 → Weight, W1 = 0.8

b. Clear skies, X2 → Weight, W2 = 0.6
c. Humidity above 50%, X3 → Weight, W3 = –0.5

d. Sufficient light, X4 → Weight, W4 = 0.7
Bias, b = 0.6
Threshold, T = 1.5

Scenario 1: Conditions (a, b, c) met
Pitch Dry: Yes → X1 = 1

Clear Skies: Yes → X2 = 1
Humidity > 50%: Yes → X3 = 1
Sufficient Light: No → X4 = 0

Step 1: Compute Weighted Sum
Z = (0.8 × 1) + (0.6 × 1) + (−0.5 × 1) + (0.7 × 0) + 0.6

= 0.8 + 0.6 − 0.5 + 0 + 0.6 = 1.5
Step 2: Apply Threshold
Since 1.5 ≥ 1.5, the match will take place

Thus, Output = 1, i.e., match happens
Scenario 2: Conditions (b, c, d) met

a. Pitch Dry: No → X1 = 0
b. Clear Skies: Yes → X2 = 1
c. Humidity > 50%: Yes → X3 = 1

d. Sufficient Light: Yes → X4 = 1
Step 1: Compute Weighted Sum

Z = (0.8 × 0) + (0.6 × 1) + (−0.5 × 1) + (0.7 × 1) + 0.6
= 0 + 0.6 − 0.5 + 0.7 + 0.6 =1.4 = 1.4
Step 2: Apply Threshold

Since 1.4 < 1.5, the match will NOT take place Thus, Output = 0, i.e., match cancelled

Scenario Inputs (a, b, c, d) Weighted Sum Match Happens?
1 (1, 1, 1, 0) 1.5 Yes
2 (0, 1, 1, 1) 1.4 No

57
57