UGC NET Computer Science December 2019 | Question 113

Question 113

---

Let W_ij, represents weight between node i at layer k and node j at layer (k-1) of a given multilayer perceptron. The weight updation using gradient descent method is given by

Where α and E represents learning rate and Error in the output respectively.

1. 1. W_ij(t+1)=W_ij(t)+α ∂E/∂W_ij , 0<=α<=1
2. 2. W_ij(t+1)=W_ij(t)-α ∂E/∂W_ij , 0<=α<=1
3. 3. W_ij(t+1)=α ∂E/∂W_ij , 0<=α<=1
4. 4. W_ij(t+1)= - α ∂E/∂W_ij , 0<=α<=1

Answer : 2. Wij(t+1)=Wij(t)-α ∂E/∂Wij , 0<=α<=1

Explanation Question 113

Option 2 is correct answer

Previous	Next
UGC NET CS December 2019 - Question 112	UGC NET CS December 2019 - Question 114