Let \(W_{๐‘–๐‘—}\) represents weight between node \(๐‘–\) at layer \(๐‘˜\) andโ€ฆ

2019

Letย \(W_{๐‘–๐‘—}\)ย represents weight between nodeย \(๐‘–\)ย at layerย \(๐‘˜\)ย and nodeย \(๐‘—\)ย at layerย \((๐‘˜โˆ’1)\)ย of a given multilayer perceptron. The weight updation using gradient descent method is given by

  1. A.

    \(\textbf{W}_{ij}(t+1) = \textbf{W}_{ij}(t)+ \alpha \dfrac{\partial \textbf{E}}{\partial \textbf{W}_{ij}}, 0 \leq \alpha \leq 1\)

  2. B.

    \(\textbf{W}_{ij}(t+1) = \textbf{W}_{ij}(t)- \alpha \dfrac{\partial \textbf{E}}{\partial \textbf{W}_{ij}}, 0 \leq \alpha \leq 1\)

  3. C.

    \(\textbf{W}_{ij}(t+1) = \alpha \dfrac{\partial \textbf{E}}{\partial \textbf{W}_{ij}}, 0 \leq \alpha \leq 1\)

  4. D.

    \(\textbf{W}_{ij}(t+1) = โ€“ \alpha \dfrac{\partial \textbf{E}}{\partial \textbf{W}_{ij}}, 0 \leq \alpha \leq 1\)

Attempted by 57 students.

Show answer & explanation

Correct answer: B

Correct update rule: W_ij(t+1) = W_ij(t) - ฮฑ * (โˆ‚E/โˆ‚W_ij).

Explanation:

  • The gradient โˆ‚E/โˆ‚W_ij points in the direction of greatest increase of the error E.

  • Subtracting ฮฑ times the gradient moves the weight opposite to that direction, reducing the error.

  • W_ij(t) is the current weight; the update is incremental (new = old + step). Do not discard the current weight.

  • ฮฑ (the learning rate) is a small positive scalar that controls step size. Typical practice is to choose ฮฑ small enough to ensure stable descent.

Summary: The correct weight update for gradient descent uses the previous weight minus the learning rate times the gradient, which ensures movement toward lower error.

A video solution is available for this question โ€” log in and enroll to watch it.

Explore the full course: Nta Ugc Net Paper 2

Loading lessonโ€ฆ