UGC NET Computer Science Artificial Intelligence (AI) Previous Year Questions (PYQs) – Page 2 of 3
A Place for Latest Exam wise Questions, Videos, Previous Year Papers,
Study Stuff for MCA Examinations
Study Stuff for MCA Examinations
Showing 26 questions
Consider the following table defining the sample inputs and corresponding target values for a perceptron model.
| Sample No | x1 | x2 | target | w1 | w2 |
|---|---|---|---|---|---|
| S1 | 0 | 0 | 0 | 0 | 0 |
| S2 | 0 | 1 | 1 | ||
| S3 | 1 | 0 | 1 | ||
| S4 | 1 | 1 | 1 |
What shall be the value of updated weights after applying all the samples S1 to S4 (in the order S1, S2, S3, S4) to this model. Given that the initial weights w1=0, w2=0, learning rate=0.1 and no bias is involved in the perceptron. The activation function for this perceptron is given below:
yobserved =
{ 1 if yin > 0
0 if yin < 0 }
- w1 = 0.1, w2 = 0.1
- w1 = 0.0, w2 = 0.2
- w1 = 0.0, w2 = 0.1
- w1 = 0.2, w2 = 0.2
1
2
3
4
Solution
Using perceptron learning rule: Δw = η (t − y) x, where y = 1 if yin > 0 else 0.
S1 (0,0,t=0): yin=0 ⇒ y=0 ⇒ no change ⇒ (w1,w2)=(0,0)
S2 (0,1,t=1): yin=0 ⇒ y=0 ⇒ Δw=0.1(1−0)(0,1) ⇒ (w1,w2)=(0,0.1)
S3 (1,0,t=1): yin=0 ⇒ y=0 ⇒ Δw=0.1(1−0)(1,0) ⇒ (w1,w2)=(0.1,0.1)
S4 (1,1,t=1): yin=0.1+0.1=0.2>0 ⇒ y=1 ⇒ no change
Final Weights: w1=0.1, w2=0.1
Answer: (1)
Considering the following statements:
A. Data transformation is involved in Data mining process.
B. Online database is used in Data warehouse.
C. Classification is a measure of accuracy.
D. K-means clustering algorithm is based on the concept of minimizing the within-cluster variance.
E. Pattern evaluation is a process to identify knowledge based on interestingness measure.
1
2
3
4
Solution
B – True: Data warehouses are used for online analytical processing (OLAP).
D – True: K-means minimizes within-cluster sum of squares (variance).
E – True: Pattern evaluation identifies useful patterns using interestingness measures.
A – Data transformation happens before mining (in preprocessing).
C – Classification is a process, not a measure of accuracy.
Match List I with List II
| List I (Operations on Fuzzy Sets) | List II (Description) |
|---|---|
| A. Intersection | IV. $\min(\mu_A(x), \mu_B(x))$ |
| B. Bounded Sum | III. $\min(1, \mu_A(x) + \mu_B(x))$ |
| C. Bounded Difference | II. $\max(0, \mu_A(x) - \mu_B(x))$ |
| D. Algebraic Sum | I. $\mu_A(x) + \mu_B(x) - \mu_A(x)\mu_B(x)$ |
Choose the correct answer from the options given below:
1
2
3
4
Solution
Explanation:
- A → IV → Intersection → $\min(\mu_A(x), \mu_B(x))$
- B → III → Bounded Sum → $\min(1, \mu_A(x) + \mu_B(x))$
- C → II → Bounded Difference → $\max(0, \mu_A(x) - \mu_B(x))$
- D → I → Algebraic Sum → $\mu_A(x) + \mu_B(x) - \mu_A(x)\mu_B(x)$
Consider the following steps involved in the application of Genetic Algorithm for a problem:
A. Select a pair of parents from the population
B. Apply mutation at each locus with probability $p_m$
C. Calculate fitness of each member of the population
D. Apply crossover with probability $p_c$ to form offsprings
Choose the correct answer from the options given below describing the correct order of the above steps:
1
2
3
4
Solution
The correct sequence in a Genetic Algorithm is —
C: Calculate fitness of each member of the population.
A: Select a pair of parents based on fitness.
D: Apply crossover ($p_c$) to form offspring.
B: Apply mutation ($p_m$) to maintain diversity.
Hence, the correct order is C → A → D → B.
Match List – I with List – II.
| List – I | List – II |
| (A) Natural language processing | (I) A method of training algorithm by rewarding desired behaviour and/or punishing undesired one. |
| (B) Reinforcement learning | (II) System designed to emulate the decision making abilities of a human expert. |
| (C) Support vector machine | (III) A branch of AI focused on understanding and generating human language. |
| (D) Expert system | (IV) A machine learning technique that finds the hyperplane that best separates different classes in a feature space. |
Choose the correct answer from the options given below :
1
2
3
4
Solution
(A) Natural language processing → Understanding human language → (III)
(B) Reinforcement learning → Reward and punishment learning → (I)
(C) Support vector machine → Hyperplane classification method → (IV)
(D) Expert system → Decision making like human expert → (II)
Read the below passage and answer the questions.
Artificial Neural Networks (ANNs) are computational models inspired by the human brain’s neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.
Which of the following is/are the application area(s) of ANN ?
Which of the following is/are the application area(s) of ANN ?
(A) Natural Language Processing
(B) Image Processing
(C) Pattern Recognition
(D) Speech Recognition
Choose the correct answer from the options given below :
1
2
3
4
Solution
The passage clearly states that ANNs are useful in:
• Image recognition
• Speech recognition
• Natural language processing
• Pattern recognition
Thus all listed areas are applications of ANN.
Which of the following is NOT a parent selection technique used in genetic algorithm implementations?
1
2
3
4
Solution
Common parent selection methods in Genetic Algorithms include —
Roulette Wheel Selection
Tournament Selection
Rank Selection
Boltzmann Selection
“Radial” is not a valid selection technique.
Read the below passage and answer the questions.
Artificial Neural Networks (ANNs) are computational models inspired by the human brain’s neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.
Which of the following layers may be more than one in number?
1
2
3
4
Solution
In an Artificial Neural Network:
• Input layer → usually only one
• Output layer → usually only one
• Hidden layers → can be one or more layers
Thus the layer that may be more than one is hidden layer.
Read the below passage and answer the questions.
Artificial Neural Networks (ANNs) are computational models inspired by the human brain’s neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.
Artificial Neural Networks (ANNs) are inspired by:
1
2
3
4
Solution
The passage states that ANN models are inspired by the human brain’s neural networks.
Read the below passage and answer the questions.
Artificial Neural Networks (ANNs) are computational models inspired by the human brain’s neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.
What is the role of weights in an ANN?
1
2
3
4
Solution
Weights represent the strength of connections between neurons.
During training, weights are adjusted to reduce error and improve performance.
UGC NET Computer Science
Online Test Series, Information About Examination,
Syllabus, Notification
and More.
View More
UGC NET Computer Science
Online Test Series, Information About Examination,
Syllabus, Notification
and More.
View More
Ask Your Question or Put Your Review.
