Home
Recent Q&A
Java
Cloud
JavaScript
Python
SQL
PHP
HTML
C++
Data Science
DBMS
Devops
Hadoop
Machine Learning
Azure
Blockchain
Devops
Ask a Question
Deep Learning Interview Questions and Answers
Home
Questions
Deep Learning
+1
vote
Q: You are using a deep neural network for a prediction task. After training your model, you notice that it is strongly overfitting the training set and that the performance on the test isn’t good. What can you do to reduce overfitting?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deepneuralnetwork
0
votes
Q: What is an activation function and discuss the use of an activation function? Explain three different types of activation functions?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
activationfunction
0
votes
Q: What are autoencoders? Explain the different layers of autoencoders and mention three practical usages of them?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
autoencoders
0
votes
Q: You have a pet dog whose mood is heavily dependent on the current and past few days’ weather. You’ve collected data for the past 365 days on the weather, which you represent as a sequence as x<1>,…,x<365>. You’ve also collected data on your dog’s mood, which you represent as y<1>,…,y<365>. You’d like to build a model to map from x→y. Should you use a Unidirectional RNN or Bidirectional RNN for this problem?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deep-learning
0
votes
Q: Here are the equations for the GRU and the LSTM: From these, we can see that the Update Gate and Forget Gate in the LSTM play a role similar to _______ and ______ in the GRU. What should go in the the blanks?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deeplearning
0
votes
Q: Here’re the update equations for the GRU. Alice proposes to simplify the GRU by always removing the Γu. I.e., setting Γu = 1. Betty proposes to simplify the GRU by removing the Γr. I. e.,
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deep-learning
0
votes
Q: Suppose you are training a LSTM. You have a 10000 word vocabulary, and are using an LSTM with 100-dimensional activations a. What is the dimension of Γu at each time step?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deeplearning
0
votes
Q: You are training an RNN, and find that your weights and activations are all taking on the value of NaN (“Not a Number”). Which of these is the most likely cause of this problem?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
rnn
learningdeep
0
votes
Q: You have finished training a language model RNN and are using it to sample random sentences, as follows: What are you doing at each time step t?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deeplearning
0
votes
Q: At the t-th time step, what is the RNN doing? Choose the best answer.
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
rnn
0
votes
Q: To which of these tasks would you apply a many-to-one RNN architecture? (Check all that apply).
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
rnnarchitecture
0
votes
Q: Consider this RNN: This specific type of architecture is appropriate when:
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
rnn
deep-learning
0
votes
Q: Suppose your training examples are sentences (sequences of words). Which of the following refers to the jth word in the ith training example?
asked
Jul 19, 2023
in
Deep Learning
by
SakshiSharma
deep-learning
0
votes
Q: What does a Boltzmann machine encompass?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
0
votes
Q: Weight sharing occurs in which neural network architecture?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
+1
vote
Q: Which strategy does not prevent a model from over-fitting to the training data?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
0
votes
Q: Which of the following options represents the correct sequence of steps involved in employing a gradient descent algorithm?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
0
votes
Q: When using Convolutional Neural Network, does max pooling always result in a decrease in parameters?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
convolutional-neural-network
0
votes
Q: Assume a three-neuron MLP model with inputs 1, 2, and 3. The input neurons' weights are 4,5 and 6, respectively.
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
0
votes
Q: If we want to forecast the probabilities of n classes (p1, p2..pk), which of the following functions can be utilised as an activation function in the output layer so that the sum of p over all n equals 1?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-leanring
0
votes
Q: The input layer has ten nodes, whereas the hidden layer has five. From the input layer to the hidden layer, the maximum number of connections is
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
0
votes
Q: The input image has been transformed into a 28 x 28 matrix and a 7 x 7 kernel/filter with a stride of 1. What will the convoluted matrix's size be?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
0
votes
Q: Which of the following gives non linearity to a neural network?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
neural-network
0
votes
Q: Explain the different types of activation functions.
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
activation-functions
0
votes
Q: Differentiate between Deep Learning and Machine Learning.
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
machine-learning
+1
vote
Q: What do you know about Dropout?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
dropout
deep-learning
0
votes
Q: Mention the applications of autoencoders.
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
encoders
applications
0
votes
Q: What are autoencoders? Explain the different layers of autoencoders.
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
autoencoders
0
votes
Q: What exactly do you mean by exploding and vanishing gradients?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
vanishing-gradients
0
votes
Q: How does Recurrent Neural Network backpropagation vary from Artificial Neural Network backpropagation?
asked
Dec 13, 2022
in
Deep Learning
by
Robindeniel
deep-learning
Page:
« prev
1
2
3
4
5
6
7
next »
...