Scribd
Upload
4 views5 pages

High Level MCQ Soft Computing

The document contains a series of multiple-choice questions (MCQs) focused on Soft Computing and Neural Networks, covering topics such as the aims of Soft Computing, components like Fuzzy Logic, and the differences between hard and soft computing. It also addresses concepts related to artificial neurons, activation functions, learning rates, and the structure of Feedforward Neural Networks. Each question is accompanied by the correct answer, providing a comprehensive overview of fundamental concepts in the field.

Uploaded by

manaspateell
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
4 views5 pages

High Level MCQ Soft Computing

The document contains a series of multiple-choice questions (MCQs) focused on Soft Computing and Neural Networks, covering topics such as the aims of Soft Computing, components like Fuzzy Logic, and the differences between hard and soft computing. It also addresses concepts related to artificial neurons, activation functions, learning rates, and the structure of Feedforward Neural Networks. Each question is accompanied by the correct answer, providing a comprehensive overview of fundamental concepts in the field.

Uploaded by

manaspateell
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

High-Level MCQs on Soft Computing and Neural Networks

1. What does Soft Computing primarily aim to solve?

 A. Well-defined mathematical problems


 B. Structured data mining
 C. Real-world problems with uncertainty and approximation
 D. Only image processing problems

Answer: C

2. Which of the following is a component of Soft Computing?

 A. Blockchain
 B. Fuzzy Logic
 C. Binary Search Trees
 D. Hash Functions

Answer: B

3. What is the major difference between hard and soft computing?

 A. Soft computing uses exact input values


 B. Hard computing is trainable
 C. Soft computing allows approximate models and noisy input
 D. Hard computing relies on neural networks

Answer: C

4. What is the full form of ANN?

 A. Automatic Neural Network


 B. Artificial Numeric Network
 C. Approximate Neural Network
 D. Artificial Neural Network

Answer: D
5. Which biological structure inspires the concept of neurons in neural networks?

 A. Muscles
 B. Eyes
 C. Brain
 D. Skin

Answer: C

6. What is the function of dendrites in a biological neuron?

 A. Transmit signals
 B. Send outputs
 C. Receive input signals
 D. Store memory

Answer: C

7. In an artificial neuron, what does a weight represent?

 A. Data storage
 B. Importance of an input
 C. Final decision
 D. Output signal

Answer: B

8. Why is a bias term added in an artificial neuron?

 A. To speed up processing
 B. To prevent errors
 C. To shift the activation function
 D. To reduce input size

Answer: C

9. What is the purpose of an activation function in neural networks?

 A. It helps calculate loss


 B. It allows learning of non-linear patterns
 C. It adjusts the learning rate
 D. It stops overfitting

Answer: B

10. Which of the following is a common activation function?

 A. Max-Pooling
 B. Linear Regression
 C. ReLU
 D. Dropout

Answer: C

11. The Perceptron Learning Algorithm is used for:

 A. Regression problems
 B. Binary classification tasks
 C. Text summarization
 D. Reinforcement learning

Answer: B

12. What does the learning rate (η) control in training a model?

 A. Output range
 B. Frequency of activation
 C. Size of the training data
 D. Size of weight updates

Answer: D

13. If the learning rate is too low, what will happen?

 A. The model will stop learning


 B. The model will learn too slowly
 C. The weights will explode
 D. It will overfit the data

Answer: B

14. Which layer in a Feedforward Neural Network (FNN) performs no computation?

 A. Input Layer
 B. Hidden Layer
 C. Output Layer
 D. All layers

Answer: A

15. How does data flow in a Feedforward Neural Network?

 A. Back and forth between layers


 B. Randomly through nodes
 C. In loops
 D. In one direction from input to output

Answer: D

16. How many output neurons are typically used for multi-class classification in FNN?

 A. One
 B. Two
 C. Equal to the number of classes
 D. Equal to the number of features

Answer: C

17. What activation function is commonly used in the output layer for binary classification?

 A. ReLU
 B. Tanh
 C. Sigmoid
 D. Softmax
Answer: C

18. In digit recognition, what kind of image input is commonly used?

 A. RGB color image


 B. Gray scale image
 C. 3D image
 D. Text file

Answer: B

19. In neural networks, what does a loss function measure?

 A. Number of correct predictions


 B. Model accuracy
 C. Difference between predicted and actual output
 D. Number of input neurons

Answer: C

20. Optical computation in neural networks is used to:

 A. Speed up arithmetic operations using light


 B. Replace neural networks with lasers
 C. Convert data into sound
 D. Improve memory storage

Answer: A

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy