Artificial Intelligence Quiz For Beginners - QUIZ TOPIC - DEEP LEARNING

 

QUIZ TOPIC - DEEP LEARNING

1. Which is the following is true about neurons?

---

 A. A neuron has a single input and only single output

 B. A neuron has multiple inputs and multiple outputs

 C. A neuron has a single input and multiple outputs

 D. All of the above

2. Which of the following is an example of deep learning?

---

 A. Self-driving cars

 B. Pattern recognition

 C. Natural language processing

 D. All of the above

3. Which of the following statement is not correct?

---

 A. Neural networks mimic the human brain

 B. It can only work for a single input and a single output

 C. It can be used in image processing

 D. None

4. Autoencoder is an example of-

---

 A. Deep learning

 B. Machine learning

 C. Data mining

 D. None

5. Which of the following deep learning models uses backpropagation?

---

 A. Convolutional Neural Network

 B. Multilayer Perceptron Network

 C. Recurrent Neural Network

 D. All of the above

6. Which of the following steps can be taken to prevent overfitting in a neural network?

---

 A. Dropout of neurons

 B. Early stopping

 C. Batch normalization

 D. All of the above

7. Neural networks can be used in-

---

 A. Regression problems

 B. Classification problems

 C. Clustering problems

 D. All of the above

8. In a classification problem, which of the following activation function is most widely used in the output layer of neural networks?

---

 A. Sigmoid function

 B. Hyperbolic function

 C. Rectifier function

 D. All of the above

9. Which of the following is a deep learning library?

---

 A. Tensorflow

 B. Keras

 C. PyTorch

 D. All of the above

10. Which of the following is true about bias?

---

 A. Bias is inherent in any predictive model

 B. Bias impacts the output of the neurons

 C. Both A and B

 D. None

11. What is the purpose of a loss function?

---

 A. Calculate the error value of the forward network

 B. Optimize the error values according to the error rate

 C. Both A and B

 D. None

12. Which of the following is a loss function?

---

 A. Sigmoid function

 B. Cross entropy

 C. ReLu

 D. All of the above

13. Which of the following loss function is used in regression?

---

 A. Logarithmic loss

 B. Cross entropy

 C. Mean squared error

 D. None

14. Suppose you have a dataset from where you have to predict three classes. Then which of the following configuration you should use in the output layer?

---

 A. Activation function = softmax, loss function = cross entropy

 B. Activation function = sigmoid, loss function = cross entropy

 C. Activation function = softmax, loss function = mean squared error

 D. Activation function = sigmoid, loss function = mean squared error

15. What is gradient descent?

---

 A. Activation function

 B. Loss function

 C. Optimization algorithm

 D. None

16. What does a gradient descent algorithm do?

---

 A. Tries to find the parameters of a model that minimizes the cost function

 B. Adjusts the weights at the input layers

 C. Both A and B

 D. None

17. Which of the following activation function can not be used in the output layer of an image classification model?

---

 A. ReLu

 B. Softmax

 C. Sigmoid

 D. None

18. For a binary classification problem, which of the following activation function is used?

---

 A. ReLu

 B. Softmax

 C. Sigmoid

 D. None

19. Which of the following makes a neural network non-linear?

---

 A. Convolution function

 B. Batch gradient descent

 C. Rectified linear unit

 D. All of the above

20. In a neural network, which of the following causes the loss not to decrease faster?

---

 A. Stuck at a local minima

 B. High regularization parameter

 C. Slow learning rate

 D. All of the above

21. For an image classification task, which of the following deep learning algorithm is best suited?

---

 A. Recurrent Neural Network

 B. Multi-Layer Perceptron

 C. Convolution Neural Network

 D. All of the above

22. Suppose the number of nodes in the input layer is 5 and the hidden layer is 10. The maximum number of connections from the input layer to the hidden layer would be-

---

 A. More than 50

 B. Less than 50

 C. 50

 D. None

23. Which of the following is true about dropout?

---

 A. Applied in the hidden layer nodes

 B. Applied in the output layer nodes

 C. Both A and B

 D. None

24. Which of the following is a correct order for the Convolutional Neural Network operation?

---

 A. Convolution -> max pooling -> flattening -> full connection

 B. Max pooling -> convolution -> flattening -> full connection

 C. Flattening -> max pooling -> convolution -> full connection

 D. None

25. Convolutional Neural Network is used in-

---

 A. Image classification

 B. Text classification

 C. Computer vision

 D. All of the above

26. Which of the following neural network model has a shared weight structure?

---

 A. Recurrent Neural Network

 B. Convolution Neural Network

 C. Both A and B

 D. None

27. LSTM is a variation of-

---

 A. Convolutional Neural Network

 B. Recurrent Neural Network

 C. Multi-Layer Perceptron Network

 D. None

28. Which of the following neural networks is the best for machine translation?

---

 A. 1D Convolutional Neural Network

 B. 2D Convolutional Neural Network

 C. Recurrent Neural Network

 D. None

29. Which of the following neural networks has a memory?

---

 A. 1D CNN

 B. 2D CNN

 C. LSTM

 D. None

30. Batch normalization helps to prevent-

---

 A. activation functions to become too high or low

 B. the training speed to become too slow

 C. Both A and B

 D. None