Unit I

Part – A Questions
Artificial Intelligence and Data Science
CCS337 – COGNITIVE SCIENCE
Sixth Semester

QNo Bloom’s
Questions COs
Level
1. What is the mental-physical relation in philosophy? CO1 K1
2. Define materialism in the context of mental science. CO1 K1
Explain, How does logic contribute to the sciences of the CO1 K2
3.
mind?
4. What is the role of psychology in cognitive science? CO1 K1
5. Define information processing in psychology. CO1 K1
6. What is cognitive neuroscience? CO1 K1
Explain, How does perception influence cognitive CO1 K2
7.
processes?
8. Define decision-making in the context of cognitive science. CO1 K1
What is the significance of learning and memory in CO1 K1
9.
cognition?
Explain, How does language understanding contribute to CO1 K2
10.
cognitive science?
11. Compare between materialism and mental science. CO1 K2

12. What are the key components of information processing? CO1 K1

13. Compare the relationship between perception and learning. CO1 K2

How does cognitive neuroscience help in language CO1 K1
14.
processing?
What is the importance of decision-making in mental CO1 K1
15.
processing?
Part – B
Explain the evolution of the mental-physical relation from
1. materialism to mental science. How has this transition CO1 K2
influenced modern cognitive science?
2. Discuss the interdisciplinary nature of psychology in CO2 K2
cognitive science. How does it contribute to understanding
perception, learning, and decision-making?
3. Explain the concept of information processing in psychology CO1
K2
and its relevance to artificial intelligence.
4. 4Explain the significance of logic in understanding the CO1 K2
 sciences of the mind. How does logical reasoning contribute
to cognitive models?

5. 5Explain, How does cognitive neuroscience contribute to our CO1

understanding of learning and memory? Discuss the key
K2
neural mechanisms involved.

6. 6Illustrate the role of perception in human cognition and CO1 K2

artificial intelligence. How do cognitive biases impact
decision-making?

Part – C
1. 3How do humans process and understand language? Explain
. the cognitive and neural mechanisms involved in language CO1 K2
comprehension and production.
2. 2What are the major contributions of neuroscience to K2
cognitive science? Summarize the impact of brain imaging CO1
techniques on understanding cognition.

UNIT II

Q. CO’s Bloom’s
Questions Level
No

1Define computational intelligence. CO2 K1

2What are the cognitive architectures? CO2 K1
3Explain, How does artificial intelligence simulate human cognition? CO2 K2
4Define knowledge-based systems. CO2 K1
5What is logical representation in AI? CO2 K1
6Explain the importance of logical decision-making. CO2 K2
7What is the role of learning in AI? CO2 K1
8Define machine vision in AI. CO2 K1
9Compare the differences between symbolic and connectionist AI. CO2 K2
10How do expert systems work? CO2 K1
11What are the components of a cognitive architecture? CO2 K1
12Explain the concept of rule-based reasoning in AI. CO2 K2
13How do neural networks mimic cognitive processes? CO2 K1
14What is the role of AI in decision-making? CO2 K1
15Define the term "Artificial General Intelligence (AGI)”. CO2 K1
Part – B
1 Explain artificial intelligence and its role in computational CO2 K2
 intelligence. How does AI contribute to human-like cognition?
Describe and explain different architectures of cognition and CO2
2 K2
compare their approaches to human thinking.
Discuss knowledge-based systems and their role in artificial CO2
3 K2
intelligence. And, Summarize the real-world applications.
What is logical representation in AI? Explain the propositional logic, CO2
4 K2
predicate logic, and their applications in reasoning.
Explain logical decision-making techniques in AI, including decision CO2 K2
5
trees, Bayesian networks, and Markov models.
Discuss how machine learning contributes to AI. Explain, How does CO2 K2
6
supervised and unsupervised learning differ?
PART –C
How does AI process language? Discuss and Explain various natural CO2 K2
1
language processing techniques and applications.
Explain the role of vision in artificial intelligence and how machines CO2 K2
2
interpret visual information.

UNIT III

Q. CO’s Bloom’s
Questions Level
No

1 What is probabilistic programming? CO3 K1

2 Define WebPPL and its significance. CO3 K1
3 What are probability distributions in WebPPL? CO3 K1
4 Explain the role of JavaScript in WebPPL. CO3 K2
6 What are coroutines in programming? CO3 K1
7 Define inference in probabilistic programming. CO3 K1
8 Explain, How is random computation used in AI? CO3 K2
9 What is enumeration in WebPPL? CO3 K1
10 Explain the term "probabilistic inference." CO3 K2
11 Explain, How does WebPPL handle probability types? CO3 K2
12 What is a generative model? CO3 K1
13 Define Bayesian networks in probabilistic modeling. CO3 K1
14 Explain, How does WebPPL support decision-making? CO3 K2
15 What are Markov chains in probabilistic modeling? CO3 K1
PART- B
Build a probabilistic model using WebPPL. Explain its syntax, key CO3
1 K3
features, and how it handles probability distributions.
 Construct a real-world application using probabilistic programming CO3
2 in WebPPL. Explain, how it manipulates probability types and K3
distributions.
Develop an inference model in WebPPL using JavaScript libraries. CO3
3 K3
Explain how external libraries enhance probabilistic programming.
Identify the different probabilistic programming techniques in CO3
4 K3
WebPPL. Compare their effectiveness in handling uncertainty.
Identify the advantages and limitations of using WebPPL for CO3
5 probabilistic inference in AI applications. And, Provide real-world K3
examples.
Make use of WebPPL’s coroutines and random computation CO3
6 K3
techniques to implement probabilistic decision-making.
PART –C
Model a probabilistic reasoning framework using WebPPL. Explain
1. K3
how it can be used for AI-driven predictions. CO3
Plan a machine learning system that incorporates probabilistic
2. programming. Explain the role of inference and enumeration in CO3 K3
decision-making.

UNIT IV

Q. CO’s Bloom’s
Questions Level
No

1 What are inference models in cognition? CO4 K1

2. Define generative models. CO4 K1
3 Explain the concept of conditioning in probability. CO4 K2
4 What is causal dependence? CO4 K1
5 Define statistical dependence in cognition. CO4 K1
6 What is conditional dependence? CO4 K1
7 Explain, How data analysis used in inference models? CO4 K2
8 Define utility theory. CO4 K1
9 What are the key applications of inference models? CO4 K1
10 How do algorithms contribute to inference models? CO4 K1
11 Explain the concept of uncertainty in AI. CO4 K2
12 What is Bayesian inference? CO4 K1
13 Define likelihood estimation in probabilistic inference. CO4 K1
14 Explain, How does machine learning use inference models? CO4 K2
15 What are some challenges in inference modeling? CO4 K1
 PART - B
Apply generative models in cognitive inference. Explain their role in
1 CO4 K3
machine learning and probabilistic reasoning.
Choose an AI system that utilizes inference models for decision-
2 CO4 K3
making. Explain its applications in real-world scenarios.
Choose an appropriate probabilistic inference algorithm for a given
3 CO4 K3
cognitive task. Justify your selection with examples.
Construct an inference-based AI system that incorporates statistical
4 CO4 K3
and causal dependencies. Explain how it processes data.
Develop a conditional inference model that enhances AI-driven
5 CO4 K3
predictions. Explain how it can be optimized for accuracy.
Identify different inference algorithms and compare their efficiency
6 CO4 K3
in handling uncertainty in AI models.
PART – C
Utilized a structured framework for probabilistic reasoning and
1. Explain how different inference models contribute to cognitive CO4 K3
computing.
Solve a real-world problem using inference models in AI.
2 Demonstrate the role of generative and Bayesian models in your CO4 K3
solution.

UNIT V

Q. CO’s Bloom’s
Questions Level
No

1 Define learning models in cognition. CO5 K1

2. What is conditional inference in learning? CO5 K1
3 Explain the Language of Thought hypothesis. CO5 K2
4 Define hierarchical models in AI. CO6 K1
5 What are mixture models? CO6 K1
6 How does deep learning contribute to cognition? CO5 K1
7 Explain reinforcement learning in AI. CO5 K2
8 What is a cognitive neural network? CO5 K1
9 Define probabilistic learning. CO5 K1
9 How does unsupervised learning relate to cognition? CO5 K1
10 Explain the role of neural computation in learning. CO5 K2
11 What are self-organizing maps? CO5 K1
12 Define cognitive reinforcement learning. CO5 K1
13 Explain, How do mixture models support probabilistic reasoning? CO6 K2
14 What are hierarchical Bayesian models? CO6 K1
15 Define learning models in cognition. CO5 K1
 PART- B
Apply learning models to AI-driven cognitive computing. Explain
1 CO5 K3
the impact of conditional inference on learning.
Build a hierarchical model for learning cognitive functions. Explain K3
2 CO6
its significance in artificial intelligence.
Choose between supervised and unsupervised learning for cognitive K3
3 CO5
AI tasks. Justify your choice with case studies.
Construct a deep learning framework that enhances machine K3
4 CO5
cognition. Explain how it incorporates hierarchical models.
Develop an AI system that learns through probabilistic modeling. K3
5 CO6
Explain the role of Bayesian networks and mixture models.
Utilize hierarchical Bayesian models for improving AI learning K3
6 CO6
mechanisms. Explain their role in knowledge representation.
PART – C
Make use of cognitive neural networks in learning and Explain how
1. CO5 K3
they help in human-like reasoning in AI systems.
Identify reinforcement learning techniques and Compare their
2 CO5 K3
efficiency in decision-making and problem-solving.