Consider the following table defining the sample inputs and corresponding…
2025
Consider the following table defining the sample inputs and corresponding target values for a perceptron model. What shall be the value of updated weights after applying all the samples S1 to S4 (in the order S1, S2, S3, S4) to this model?
Given that the initial weights are w1=0, w2=0, learning rate = 0.1, and no bias is involved in the perceptron. The activation function for this perceptron is:
Sample No | x1 | x2 | target | w1 | w2 |
S1 | 0 | 0 | 0 | 0 | 0 |
S2 | 0 | 1 | 1 |
|
|
S3 | 1 | 0 | 1 |
|
|
S4 | 1 | 1 | 1 |
|
|
- A.
w1=0.1,w2=0.1
- B.
w1=0.0,w2=0.2
- C.
w1=0.0,w2=0.1
- D.
w1=0.2,w2=0.2
Attempted by 39 students.
Show answer & explanation
Correct answer: A
Assumption: perceptron uses a step activation with output 1 if net > 0, and 0 otherwise. Initial weights: w1=0, w2=0. Learning rate = 0.1.
S1: x=(0,0), target=0. Net = 0 → output = 0. Error = 0 → no update. Weights remain (0, 0).
S2: x=(0,1), target=1. Net = 0 → output = 0. Error = 1. Δw = learning_rate * error * x = 0.1 * 1 * (0,1) = (0, 0.1). New weights: (0, 0.1).
S3: x=(1,0), target=1. Net = 0 → output = 0. Error = 1. Δw = 0.1 * 1 * (1,0) = (0.1, 0). New weights: (0.1, 0.1).
S4: x=(1,1), target=1. Net = 0.1 + 0.1 = 0.2 → output = 1. Error = 0 → no update.
Final weights: w1=0.1, w2=0.1
A video solution is available for this question — log in and enroll to watch it.