Computer Sciences MCQs for Pak Army Tests

Important Questions of Computer Science (Part-5)

What is meant by an auto-associative neural network?

1. A neural network including feedback
2. A neural network containing no loops
3. A neural network having a single loop
4. A single layer feed-forward neural network containing feedback

Answer: a)

Which of the following is correct?

1. In contrast to conventional computers, neural networks have much higher computational rates.
2. Neural networks learn by example.
3. III. Neural networks mimic the same way as that of the human brain
4. All of the above

1. (ii) and (iii) are true
2. (i), (ii) and (iii) are true
3. None of the above

Answer: a)

Which of the following is correct for the neural network?

1. The training time is dependent on the size of the network
2. Neural networks can be simulated on the conventional computers
3. III. Artificial neurons are identical in operation to a biological one
4. All of the above

1. (ii) is true
2. (i) and (ii) are true
3. None of the above

Answer: c)

What are the advantages of neural networks over conventional computers?

1. Neural networks learn from examples
2. They are more fault-tolerant
3. III. They are well suited for real-time operation due to their high computational rates

1. (i) and (ii) are correct
2. (i) and (iii) are correct
3. Only (i)
4. All of the above

Answer: d)

Backpropagation can be defined as _________

1. It is another name given to the curvy function in the perceptron.
2. It is the transmission of errors back through the network to adjust the inputs.
3. It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.
4. None of the above

Answer: c)

Which of the following is not the promise of an artificial neural network?

1. It can survive the failure of some nodes
2. It can handle noise
3. It can explain the result
4. It has inherent parallelism

Answer: c)

Having multiple perceptron can solve the XOR problem satisfactorily because each perceptron can partition off a linear part of the space itself, and they can then combine their results.

1. True – This works always, and these multiple perceptrons learn to classify even complex problems.
2. False – Perceptron are mathematically incapable of solving linearly inseparable functions, no matter what you do
3. True – Perceptron can do this but are unable to learn to do it – they have to be explicitly hand-coded
4. False – Just having a single perceptron is enough

Answer: c)

Based on _________ membership function can be used to solve empirical problems.

1. Knowledge
2. Learning
3. Examples
4. Experience

Answer: d)

A 3-input neuron is trained to output a 0 when the input is 110 and a 1 when the input is 111. After generalization, the output will be 0, when and only when the input is:

1. 000 or 110 or 011 or 101
2. 000 or 010 or 110 or 100
3. 100 or 111 or 101 or 001
4. 010 or 100 or 110 or 101

Answer: b)

A 4-input neuron has weights 1, 2, 3, and 4. The transfer function is linear, with the constant of proportionality being equal to 2. The inputs are 4, 10, 5, and 20, respectively. The output will be:

1. 76
2. 238
3. 123
4. 119

Answer: b)

A neuro software can be defined as:

1. A powerful and easy neural network
2. A software that is used to analyze neurons
3. Software utilized by a neurosurgeon
4. A software aimed to assist experts in the real world

Answer: a)

What is the name of the network, which includes backward links from the output to the inputs as well as the hidden layers?

1. Perceptron
2. Self-organizing maps
3. Multi-layered perceptron
4. Recurrent neural network

Answer: d)

Which of the following is true for unsupervised learning?

1. Some specific output values are disclosed
2. Some specific output values aren’t disclosed
3. No relevant inputs value is specified
4. Both inputs as well outputs are specified
5. Neither inputs nor outputs are given

Answer: b)

What is involved in inductive learning?

1. Inconsistent Hypothesis
2. Consistent Hypothesis
3. Estimated Hypothesis
4. Irregular Hypothesis
5. Regular Hypothesis

Answer: b)

Which of the following statement is correct?

1. Not all formal languages are context-free
2. All formal languages are context-free
3. All formal languages are like natural language
4. Natural languages are context-oriented free
5. Natural language is normal

Answer: a)

Which of the following is incorrect?

1. The union and intersection of two context-free languages are context-free.
2. The reverse of context-free language is context-free, but its complement does not need to be.
3. Every regular language is context-free as it can be easily explained by regular grammar.
4. The intersection of a context-free language and a regular language is always context-free.
5. The intersection of two context-free languages is context-free.

Answer: e)

Automated vehicle is an application of _________

1. Unsupervised learning
2. Supervised learning
3. Reinforcement learning
4. Active learning

Answer: b)

_________ is not counted in different learning method.

1. Analogy
2. Memorization
3. Introduction
4. Deduction

Answer: c)

Which of the following models are utilized for learning?

1. Neural networks
2. Decision trees
3. Propositional and FOL rules
4. All of the above

Answer: d)

Which of the following is the correct example of active learning?

1. Dust Cleaning Machine
2. News Recommender System
3. Automated Vehicle
4. None of the above

Answer: b)

Which of the following is termed exploratory learning?

1. Active learning
2. Supervised learning
3. Reinforcement learning
4. Unsupervised learning

Answer: d)

_________ helps in modifying the performance element, assisting in making a better decision.

1. Learning element
2. Performance element
3. Changing element
4. None of the above

Answer: a)

Which of the following is considered while determining the nature of the learning problem?

1. Problem
2. Feedback
3. Environment
4. All of the above

Answer: b)

Which of the following is chosen among the multiple consistent hypotheses?

1. Ockham razor
2. Learning element
3. Razor
4. None of the above

Answer: a)

Which of the following takes input as an object described by a set of attributes?

1. Graph
2. Decision graph
3. Tree
4. Decision tree

Answer: d)

A neural network can answer

1. For Loop questions
2. What-if questions
3. If-The-Else Analysis questions
4. None of the above
5. Hide Answer Workspace

Answer: b)

Feature of ANN in which ANN creates its own organization of representation of information it receives during learning time is

1. Adaptive Learning
2. What-if analysis
3. Self-Organization
4. Supervised learning

Answer: c)

In artificial neural network, interconnected processing elements are termed as _________

1. Weights
2. Nodes or neurons
3. Axon
4. Soma

Answer: b)

Each connection link in ANN is linked with ________ that contains statics about the input signal.

1. Neurons
2. Activation function
3. Weights
4. Bias

Answer: c)

Artificial neurons are capable enough to model original neurons networks similarly as they are found in the human brain

1. True
2. False

Answer: a)

Name the input function received by neurons, which is also known as the neuron’s internal state.

1. Weight
2. Bias
3. Activation or neuron’s activity level
4. None of the above

Answer: c)