Consider the following statements about a perception : I. Feature detector can…
2014
Consider the following statements about a perception :
I. Feature detector can be any function of the input parameters.
II. Learning procedure only adjusts the connection weights to the output layer.
Identify the correct statement out of the following :
- A.
I is false and II is false.
- B.
I is true and II is false.
- C.
I is false and II is true.
- D.
I is true and II is true.
Attempted by 67 students.
Show answer & explanation
Correct answer: D
Answer: Both statements are true. Explanation:
Statement I — The feature detector can be any function of the input parameters.
In the perceptron model inputs are commonly transformed by a feature mapping φ(x). The model computes y = sign(w · φ(x) + b). The mapping φ can be any fixed function (including non-linear transforms or kernel-induced mappings), so statement I is true.
Statement II — The learning procedure only adjusts the connection weights to the output layer.
In the basic perceptron the feature mapping φ is fixed and not learned. The learning algorithm updates only the weight vector w (and bias b) that connects the features to the output. For a misclassified example with target t ∈ {−1,+1}, a common update is w ← w + t·φ(x) (optionally scaled by a learning rate). This shows statement II is true.
Therefore both statements are true; the correct choice is the one that states both I and II are true.