Plot of one weight w in the first hidden layer over training time t, noisy and decreasing then flat

(B) The neuron in the hidden layer might be experiencing a vanishing gradient problem

(C) The loss could have converged to the local minimum after a finite number of iterations

(D) The loss value at the end of the training may not necessarily be zero

(A) definitely, the loss value at the end of the training is zero

Deep Learning · End Term · 24 Dec 2023 · September 2023 term · Set ADB3

Deep Learning End Term 24 Dec 2023 — Question 9

Question 9

+5 marksOne or more correct options

Select all that apply.

A
definitely, the loss value at the end of the training is zero
B
The neuron in the hidden layer might be experiencing a vanishing gradient problem
C
The loss could have converged to the local minimum after a finite number of iterations
D
The loss value at the end of the training may not necessarily be zero

Show answer

Correct answers

B
The neuron in the hidden layer might be experiencing a vanishing gradient problem
C
The loss could have converged to the local minimum after a finite number of iterations
D
The loss value at the end of the training may not necessarily be zero

See the whole paper Take it as a mock test

Question 9 of 18 in the IIT Madras BS Deep Learning (Deep Learning) End Term paper sat on 24 Dec 2023, in the September 2023 term (IIT M DEGREE FN EXAM FDB1 24 Dec 2023). It carries 5 marks.

Deep Learning End Term 24 Dec 2023 — Question 9

Question 9

More questions from this paper