Question 10
Which of the following do not suffer from the vanishing gradient problem as well as the dead neurons problem?
1. Sigmoid
2. Tanh
3. ReLU
4. Leaky ReLU
Only 1
Only 2
Only 3
Only 4
Both 3 and 4
Both 1 and 2
Question 10: Which of the following do not suffer from the vanishing …
Show answer
Correct answer
Only 4
Question 10 of 16 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 4 Aug 2024, in the May 2024 term (IIT M DEGREE AN EXAM QDB2 4 Aug 2024). It carries 3 marks.
More questions from this paper
- Figure question
- Which of the following statements accurately describes the behavior of the learning rate in the AdaGrad algorithm?
- Figure question
- What is the primary purpose of using cosine annealing with warm restarts in optimization algorithms?
- How does dropout affect the behavior of the neural network during the inference phase?
- Which of the following options correctly describes the effect of early stopping as a regularization technique in traini…
- You are experimenting with L1 and L2 regularization techniques on a deep neural network trained on a moderately sized d…
- What is the impact of using a sigmoid activation function on the gradients when the input to the neuron is a very large…
- What is the derivative of the Leaky ReLU activation function with respect to its input?
- Both sigmoid and tanh activation functions saturate:
- You are working on a project where you aim to predict housing prices based on various features. You have split your dat…
- Based on the above data, answer the given subquestions.
- Pass a through the ReLU activation function and assign the output to h. ReLU(x) = \begin{cases} x, & if\ x \ge 0 \ 0, &…
- Consider a Convolutional Neural Network (CNN) architecture for image classification with the following layers:\ Convolu…
- Consider an intermediate feature map H obtained after applying convolution operation on the input X using kernel F. H =…