FAI Course File Umar
FAI Course File Umar
Umar Farooq
Assistant Professor
L T P C
3 0 0 0
UNIT I
Introduction: What is artificial intelligence, foundations of artificial intelligence, history of
artificial intelligence Intelligent Agents – agents and environments, the structure, good
behavior: the concept of rationality, the nature of environments, the structure of agents.
UNIT II
Solving Problem by Searching – Problem solving agents, example problems, searching for
solutions. Uninformed Search Strategies – Breadth first search, uniform-cost search, depth
first search, depth limited search, iterative deepening search, bidirectional search,
comparing uninformed search strategies.
UNIT III
Logical Agents – Knowledge-based agents, the Wumpus world, logic, propositional logic:
the very simple logic. Knowledge Representation – Introduction, approaches to knowledge
representation-relational knowledge, knowledge represented as logic, procedural
knowledge, knowledge representation using semantic networks, inheritance in semantic
net.
UNIT IV
Expert System & Applications – Introduction, phases in building expert systems-
knowledge engineering, knowledge representation, expert systems architecture-
knowledgebase, inference engine, knowledge acquisition, expert systems versus traditional
systems-characteristics of expert systems, evolution of expert systems, advantages and
disadvantages of expert systems, languages for es development., applications of expert
systems.
UNIT V
Learning: Machine Learning Paradigm – Introduction, machine learning system-
components of learning system, rote learning, learning by taking advice. Supervised &
Unsupervised Learning – supervised concept learning, unsupervised concept learning,
reinforcement learning.
1. Artificial Intelligence-A Modern Approach, 3rd Edition, Stuart J. Russell, Peter Norvig,
Pearson Education.
2. Artificial Intelligence, Saroj Kaushik, Cengage Publication
REFERENCE BOOKS:
1. Artificial Intelligence, Elaine Rich, Kevin Knight, Shivashankar B. Nair, 3rd Edition, McGraw
Hill.
2. Principles of Artificial Intelligence, Nils J. Nilson, Morgan Kaufmann Publishers.
3. Artificial Intelligence, 3rd Edition, Patric Henry Winston, Pearson Education.
4. Artificial Intelligence Illuminated, Ben Coppin, Narosa Publication
QUALITY POLICY:
GNITC is committed to provide quality education through dedicated and talented faculty, world
class infrastructure, labs and updated research center to the students. Quality teaching-learning
process and system will help students to attain placements and prepare them for higher studies.
PEO 1: Graduates shall have the ability to apply knowledge across the disciplines and in emerging
areas of Computer Science and Engineering for higher studies, research, employability, product
development and handle the realistic problems.
PEO 2: Graduates shall have good communication skills, possess ethical conduct, sense of
responsibility to serve the society, and protect the environment.
PEO 3: Graduates shall possess academic excellence with innovative insight, soft skills,
managerial skills, leadership qualities, Knowledge of contemporary issues and understand the need
for lifelong learning for a successful professional career.
The following list of programme outcomes describes what graduates are expected to know and be
able to do at the time of graduation. Graduates at graduation will have:
1. Engineering knowledge: Apply the knowledge of mathematics, science, engineering
fundamentals, and an engineering specialization to the solution of complex engineering problems.
2. Problem analysis: Identify, formulate, review research literature, and analyze complex
engineering problems reaching substantiated conclusions using first principles of mathematics,
natural sciences, and engineering sciences.
3. Design/Development of solutions: Design solutions for complex engineering problems and
design system components or processes that meet the specified needs with appropriate
consideration for the public health and safety, and the cultural, societal, and environmental
considerations.
4. Conduct investigations of complex problems: Use research-based knowledge and research
methods including design of experiments, analysis and interpretation of data, and synthesis of the
information to provide valid conclusions.
5. Modern tool usage: Create, select, and apply appropriate techniques, resources, and modern
engineering and IT tools including prediction and modeling to complex engineering activities with
an understanding of the limitations.
PSO 1: Ability to apply software engineering skills to design, develop and debug optimized
solutions for all real world problems.
PSO 2: Ascertain knowledge in diverse areas of Computer Science and experience an
environment conducive in novel skills for successful career, entrepreneurship and higher studies.
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
PEO1 √ √ √ √ √ √ √ √ √
PEO2 √ √ √ √ √ √ √
PEO3 √ √ √ √ √ √ √
Reference Books
Book 3 Artificial Intelligence, Elaine Rich, Kevin Knight, Shivashankar B. Nair, 3rd Edition, McGraw Hill.
Book 5 Artificial Intelligence, 3rd Edition, Patric Henry Winston, Pearson Education.
Chapters
Unit No of
Topic Book 1 Book 2 Book 3 Book 4 Book 5 Classes
Classes for beyond syllabus :02 Descriptive tests: 02 Gaps in the syllabus:02 08
Remedial Classes: 02
Tutorial classes 16
Total classes 80
SYLLABUS:
UNIT DETAILS HOURS
I Introduction – What is artificial intelligence, foundations of artificial 12
intelligence, history of artificial intelligence, applications of AI.
Intelligent Agents – agents and environments, good behavior: the concept of
rationality, the nature of environments, the structure of agents.
II Solving Problem by Searching – Problem solving agents, example problems, 14
searching for solutions.
Uninformed Search Strategies – Breadth first search, uniform-cost search,
depth first search, depth limited search, iterative deepening search, bidirectional
search, comparing uninformed search strategies.
III Logical Agents – Knowledge-based agents, the Wumpus world, logic, 10
propositional logic: the very simple logic.
Knowledge Representation – Introduction, approaches to knowledge
representation-relational knowledge, knowledge represented as logic,
procedural knowledge, knowledge representation using semantic networks,
inheritance in semantic net.
IV Expert System & Applications – Introduction, phases in building expert 10
systems-knowledge engineering, knowledge representation, expert systems
architecture-knowledgebase, inference engine, knowledge acquisition,
Expert systems versus traditional systems-characteristics of expert systems,
evolution of expert systems, advantages and disadvantages of expert systems,
languages for expert system development, applications of expert systems.
V Machine Learning Paradigm – Introduction, machine learning system-
components of learning system, rote learning, learning by taking advice.
10
Supervised & Unsupervised Learning – supervised concept learning,
unsupervised concept learning, reinforcement learning
Total 56
Tutorial classes 16
Descriptive 2
Classes beyond Syllabus 2
Gaps in the syllabus 2
Remedial classes 2
TOTAL HOURS 80
COURSE PRE-REQUISITES:
C.CODE COURSE NAME DESCRIPTION SEM
--- NIL ---
COURSE OBJECTIVES:
1. The course is introduced to familiarize the basic concepts of artificial intelligence, its
relevance in the modern era and various applications.
COURSE OUTCOMES:
SNO DESCRIPTION
1 Identify the importance of artificial intelligence.
2 Apply various search strategies to provide efficient solutions for problem space.
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 0 3 0 1 0 0 0 0 0 0 0 0 0 1
CO2 3 2 2 0 2 3 2 3 0 1 2 0 2 0
CO3 1 1 1 2 0 2 2 0 0 3 1 0 0 2
CO4 3 2 2 1 3 2 1 0 0 1 2 0 2 1
CO5 1 1 3 1 2 0 0 1 0 1 1 3 2 0
DELIVERY/INSTRUCTIONAL METHODOLOGIES:
PPT & TALK STUD. WEB RESOURCES VIDEO
ASSIGNMENT- LECTURES
LCD/SMART BOARDS STUD. SEMINARS ☐ ADD-ON COURSES
ASSESSMENT METHODOLOGIES-DIRECT:
✓ASSIGNMENTS √ STUD. SEMINARS √ TESTS/MODEL EXAMS √ UNIV.
EXAMINATION
☐ STUD. LAB PRACTICES ☐STUD. VIVA ☐ MINI/MAJOR ☐ CERTIFICATIONS
PROJECTS
☐ ADD-ON COURSES ☐ OTHERS
ASSESSMENT METHODOLOGIES-INDIRECT:
√ASSESSMENT OF COURSE OUTCOMES (BY STUDENT FEEDBACK ON FACULTY
FEEDBACK, ONCE) (TWICE)-YES
☐ ASSESSMENT OF MINI/MAJOR PROJECTS BY EXT. ☐ OTHERS
EXPERTS
Teaching
S. No. Date Name of the Topic BTL
AID
UNIT-1
1 Introduction – What is artificial intelligence 1,2 Talk & PPT
2 Foundations of artificial intelligence 1,2 Talk & PPT
3 History of artificial intelligence 1,2 Talk & PPT
4 Tutorial-1 1,2 Practice
5 Intelligent Agents 1,2,3 Talk & PPT
6 Agents and environments 1,2,3 Talk & PPT
7 Good behaviour 1,2,3 Talk & PPT
8 Tutorial-2 1,2 Practice
9 The concept of rationality 1,2,3 Talk & PPT
10 The nature of environments 1,2,3 Talk & PPT
11 The structure of agents 1,2,3 Talk & PPT
12 Tutorial-3 1,2 Practice
13 Applications of AI. 1,2,3 Talk & PPT
14 Gap in the syllabus 1,2,3 Seminar
15 Discussion of previous year question papers Talk & PPT
16 Unit-1 Assignments
UNIT-2
17 Solving Problem by Searching 1,2,3 Talk & PPT
18 Problem solving agents 1,2,3 Talk & PPT
19 Example problems 1,2,3 Talk & PPT
20 Tutorial-4 1,2 Practice
21 Searching for solutions 1,2,3 Talk & PPT
22 Uninformed Search Strategies 1,2,3 Talk & PPT
23 Breadth first search 1,2,3 Digital Board
24 Tutorial-5 1,2 Practice
25 Uniform-cost search 1,2,3 Digital Board
26 Depth first search 1,2,3 Digital Board
27 Depth limited search 1,2,3 Digital Board
28 Tutorial-6 1,2 Practice
29 Iterative deepening search 1,2,3 Digital Board
30 Bidirectional search 1,2,3 Digital Board
31 Tutorial-7 1,2 Practice
32 Comparing uninformed search strategies 1,2,3 Talk & PPT
33 Discussion on Question papers 1,2,3 Talk & PPT
Teaching
Cumm. Time
Topics BTL - Learning
Periods (Min)
Method
10 Attendance and Introduction of AI 1,2 Talk
1 30 Introduction – 1,2 PPT
10 Discussion on topics taught 1,2 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
2 30 What is artificial intelligence 1,2,3 PPT
10 Discussion on topics taught 1,2 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
3 30 Foundations of artificial Intelligence 1,2,3 PPT
10 Discussion on topics taught 1,2,3 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
4 30 Contributions from different fields 1,2,3 PPT
10 Discussion on topics taught 1,2,3 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
5 30 History of artificial intelligence 1,2,3 PPT
10 Discussion on topics taught 1,2,3 PPT/NPTEL
10 Attendance and Discussion of previous topics 1,2 Talk
6 30 History of artificial intelligence 1,2,3 PPT
10 Discussion on topics taught 1,2 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
7 30 Intelligent Agents 1,2,3 PPT
10 Discussion on topics taught 1,2 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
8 30 Agents and environments 1,2,3 PPT
10 Discussion on topics taught 1,2 PPT
10 Attendance and Discussion of previous topics 1,2 Talk
9 30 The concept of rationality 1,2,3 PPT
10 Discussion on topics taught 1,2 Talk
10 Attendance and Discussion of previous topics 1,2 Talk
10 30 The nature of environments 1,2 PPT
10 Discussion on topics taught 1,2 PPT
PART - A
Course
Q. No. Question BTL
Outcome
UNIT - 1
1 Generalize what is a rational agent? 1 CO1
2 Define Artificial Intelligence? 1 CO1
3 What are the applications of AI? 1 CO1
4 Define an agent? Give example. 1 CO1
5 List the agent types. 1 CO1
6 Write the limitations of AI. 3 CO1
7 Access what is meant by Turing Test? 1 CO1
8 What is specialty of Total Turing Test? 1 CO1
9 Analyze how to measure the performance of an agent? 1 CO1
10 List he properties of environments. 1 CO1
UNIT - 2
1 State the advantages of Breadth First Search. 1 CO2
Define the following terms:
2 1 CO2
1)Goal test 2) Path 3) Successor function 4) Abstraction
3 What is search? What are the steps for problem solving? 1 CO2
4 Define 1) Initial state 2) state space 3) Path cost 1 CO2
5 Compare BFS and DFS. 3 CO2
6 List the properties of DFS. 1 CO2
7 Give examples for Real World and Toy problems. 1 CO2
8 Express the ways to formulate a problem. 1 CO2
9 List the uninformed search techniques. 1 CO2
10 Write about depth limited search. 3 CO2
UNIT - 3
1 What is Tautology? Give example. 1 CO3
2 List the elements of propositional logic. 1 CO3
3 Write about parts of knowledge-based agent. 3 CO3
PART - B
Q. Course
Question BTL
No. Outcome
UNIT - 1
1 Design a medical diagnosis system using PEAS factors. 6 CO1
2 Illustrate utility- based agent with an example. 3 CO1
3 Explain environment types with an example. 2 CO1
4 Describe the fundamental concepts of AI. 2 CO1
5 Explain the history of AI. 2 CO1
UNIT-I
For each possible percept sequence, a rational agent should select an action that is
expected to maximize its performance measure, given the evidence provided by the
percept sequence and whatever built-in knowledge the agent has.
• Human agent: eyes, ears, and other organs for sensors; hands,legs, mouth, and
other body parts for actuators.
• Cannot understand natural language robustly( read & understand News paper)
2) Path : Sequence of actions leading from one state in the state space to another.
1) Initial state: starting point from which the agent sets out
2) state space : set of all states reachable from the initial state by any sequence of actions
Data structure BFS uses Queue to find the DFS uses Stack to find the
2
shortest path. shortest path.
Suitablity for decision As BFS considers all DFS is more suitable for
tree neighbour so it is not decision tree. As with one
suitable for decision tree decision, we need to traverse
4
used in puzzle games. further to augment the
decision. If we reach the
conclusion, we won.
Advantages:
Disadvantages:
Simple sentences which are true or false are basic propositions. Larger and more
complex sentences are constructed from basic propositions by combining them
with connectives. Thus propositions and connectives are the basic elements of
propositional logic. Though there are many connectives, we are going to use the
following five basic connectives here:
NOT, AND, OR, IF_THEN (or IMPLY), IF_AND_ONLY_IF.
6. Express ‘I will visit my friend’s house if and only if she visits me’ in
propositional logic.
P: I will visit my friend’s house, Q: she visits me
Propositional logic : P↔Q
7. Define Semantic net. Give example.
A semantic network is a knowledge base that represents semantic relations
between concepts in a network. This is often used as a form of knowledge
representation. It is a directed or undirected graph consisting of vertices, which
represent concepts, and edges, which represent semantic relations between
concepts, mapping or connecting semantic fields.
Example: a graph database or a concept map.
9. Translate the sentence into proposition formulae: I spend money only when I buy
clothes or I buy vegetables.
Following are three operations which are performed by KBA in order to show the
intelligent behavior:
1. TELL: This operation tells the knowledge base what it perceives from the
environment.
2. ASK: This operation asks the knowledge base what action it should
perform.
3. Perform: It performs the selected action.
UNIT-IV
Application Description
Advising
Instructing and assisting human in decision making
Demonstrating
Deriving a solution
Diagnosing
Explaining
Interpreting input
Predicting results
Justifying the conclusion
Suggesting alternative options to a problem
8. How many phases in building expert systems? Justfy with one example.
Phase 3: Rapidprototyping
Phase 5: Implementation
Phase 6: Post-implementation
Ensuring that computer has all the knowledge needed to solve a problem.
Choosing one or more forms to represent the required knowledge.
Ensuring efficient usage of reasoning method by computer
Disadvantages:
Unit-V
Machine learning is an application of artificial intelligence (AI) that provides systems the
ability to automatically learn and improve from experience without being explicitly
programmed.
8.What is memorization
Regression is the process of finding a model or function for distinguishing the data into
continuous real values instead of using classes or discrete values.
10.What is learning?
UNIT-1
a. Second
b. Fourth
c. Fifth
d. Third
2. The characteristics of the computer system capable of thinking, reasoning and learning
is known is
a. machine intelligence
b. human intelligence
c. artificial intelligence
d. virtual intelligence
a. Discrete / Continuous
b. Static / Dynamic
c. Deterministic / Non-deterministic
d. No agent / Multiple agents
4. What among the following is/are not the example of the intelligent agents ?
a. Human
b. Robot
c. Autonomous spacecraft
d. Hardware
a. Discrete
b. Continuous
c. Episodic
d. Non-deterministic
a. Dartmouth
b. Harvard
c. New York
d. Stanford
a. Architecture
b. Agent Function
c. Perception Sequence
d. Architecture and Program
a. LISP
b. PROLOG
c. Python
d. Perl
a. Static
b. Dynamic
c. Semi Dynamic
d. None of the mentioned
a. BASIC
b. FORTRAN
c. IPL
d. LISP
a. Yes
b. No
a. Turing Test
b. Algorithm
c. Boolean Algebra
d. Logarithm
a. Problem
b. Solution
c. Agent
d. Observation
a. Behavior of Agent
b. Percept
c. Percept Sequence
d. Agent Function
20. In Artificial Intelligence (AI), which agent deals with happy and unhappy state?
21. Which were built in such a way that humans had to supply the inputs and interpret
the outputs?
a. Agents
b. AI system
c. Sensor
d. Actuators
22. In which year John McCarthy coined the term Artificial Intelligence?
a. TRUE
b. FALSE
c. AI is not associated with human intelligence
d. None of the Above
26. The conference that launched the AI revolution in 1956 was held at: *
a. Dartmouth
b. Harvard
c. New York
d. Stanford
a. Discrete
b. Continuous
c. Episodic
a. Episodic
b. Semi-Static
c. Single agent
d. Partially Observable
a. performance measures
b. Percept Sequence
c. reaction
d. actions
30. Which of the following areas can not contribute to build an intelligent system?
a. Neuron science
b. Maths
c. Computer Science
d. Geology
31. What among the following is/are not the example of the intelligent agents ?
a. Human
b. Robot
c. Autonomous spacecraft
d. Hardware
a. Sensors
b. Perceiver
c. Actuators
d. Data
34. If a robot is able to change its own trajectory as per the external conditions, then the
robot is considered as the__
a. Mobile
b. Non-Servo
c. Open Loop
d. Intelligent
a. Angle
b. Acid
c. Actuator
d. Agent
a. Intelligent robot
b. data security
c. social media
d. content mining
38. A technique that was developed to determine whether a machine could or could not
demonstrate the artificial intelligence known as the___
a. Boolean Algebra
b. Turing Test
c. Logarithm
d. Algorithm
a. social media
b. astronomy
c. science
d. none
a. John McCarthy
b. Marvin Minsky
c. Alan Turing
d. Allen Newell and Herbert Simon
UNIT-II
a. Depth-first search
b. Breadth-first search
c. Bidirectional search
d. Depth limited search
a. Depth-limited search
b. Depth-first search
c. Breadth-first search
d. Uniform cost search
4. Breadth-first search always expands the ______ node in the current fringe of the
search tree.
a. Stacks
b. Queues
c. Priority Queues
d. List
a. Heuristic search
b. Uniform-cost search
c. Blind search
d. Depth limited search
a. Yes, Yes
b. No, Yes
c. Yes, No
d. No, No
a. Simple-action rule.
b. Structured
c. Condition-action rule
d. No rule
11. The Process of deciding what actions and states to consider given a goal is called
a. Problem formulation
b. Goal formulation
c. Solution
d. Goal-seeking
12. In which search problem, to find the shortest path, each city must be visited once
only?
a. O(b)
b. O(bl)
c. O(m)
d. O(bm)
14. The process of looking for a sequence of actions that reaches the goal is called _____
a. assumption
b. Model
c. Learning
d. search
a. Optimal search
b. Breadth-First Search
a. 8X8 array
b. 16X16 array
c. 9X9 array
d. 10X10 array
a. Toy
b. Real-world
c. dummy
d. game
a. smell
b. symbols
c. touch
d. algorithms
a. Depth-limited search
b. Depth-first search
c. Iterative deepening search
d. Bidirectional search
20. LIFO is ______ where as FIFO is ________
a. Stack, Queue
b. Queue, Stack
c. Priority Queue, Stack
d. Stack. Priority Queue
21. Which of the following search algorithm searches forward from initial state and
backward from goal state till both meet to identify a common state?
a. Depth-limited search
b. Depth-first search
c. Iterative deepening search
d. Bidirectional search
a. 4X4
b. 3X3
c. 2X4
d. 8X8
26. Which is used to provide the feedback to the learning element?
a. Critic
b. Actuators
c. Sensor
d. Agent
27. Example for route-finding problems is _________ system.
a. Hybrid
b. Sliding-block
c. Relational
d. complete
29. There are ______ kind of formulation.
a. 3
b. 4
c. 2
d. 5
31. The _______ is a touring problem in which each city must be visited exactly once.
The aim is to find the shortest tour.
a. 3
b. 4
c. 5
d. 6
34. A search algorithm takes _________ as an input and returns ________ as an output.
a. Input, output
b. Problem, solution
c. Solution, problem
d. Parameters, sequence of actions
35. Depth-first search always expands the ______ node in the current fringe of the search
tree.
a. Shallowest
b. Child node
c. Deepest
d. Minimum cost
a. Problem Space
b. Problem Instance
c. Problem Space Graph
d. Admissibility
a. iterative
39. The process of removing detail from a given state representation is called ______
a. Extraction
b. Abstraction
c. Information Retrieval
d. Mining of data
a. informed
b. Semi-Static
c. iterative
d. Uninformed
UNIT-III
1. The central component of knowledge-based agent is ___.
a. logic
b. Knowledge-base
c. language
d. database
2. Instance and isa are two important attributes which supports property of ____
a) Inheritance
b) polymorphism
c) encapsulation
d) none
3. _____ is deriving new sentences from old.
a) results
b) phrases
c) pages
d) inference
4. A Semantic network is ______________.
a) A way of representing knowledge
a. Solid
b. Dotted
c. Dashed
d. simple
b. KL-one
c. SGML
d. lisp
UNIT-IV
1. Which of the following is not a Capabilities of Expert Systems?
a. Advising
b. Demonstrating
c. Explaining
d. Expanding
a. Knowledge Base
b. Inference Engine
c. User Interface
d. All of the above
A. Design Domain
B. Monitoring Systems
C. Knowledge Domain
D. Systems domain
A. Availability
B. Speed
C. Time
D. Less Error Rate
A. IF-THEN
B. IF-THEN-ELSE
C. IF-ELSE
D. All of the above
A. Understandable
B. Highly responsive
C. Unreliable
D. High performance
A. 2
B. 3
C. 4
D. 5
A. Tools
B. shell
C. Expert System
D. knowledge
11. Data, information, and past experience combined together are termed as __________.
a) Expert Systems
b) Gaming
c) Vision Systems
d) All of the above
14. Among the given options, which is not the required property of Knowledge
representation?
a. Inferential Efficiency
b. Inferential Adequacy
c. Representational Verification
d. Representational Adequacy
15. Which of the following is an advantage of using an expert system development tool?
a) imposed structure
b) knowledge engineering assistance
c) rapid prototyping
d) all of the mentioned
20. ------------- attempt to provide the same judgmental advice that human experts such as
doctors provide.
1. Expert System
2. AI
3. KBS
4. RAND
21. Expert system are part of the general area of research known as ------------
a. AI
b. ES
c. STUDENT
d. RAND
22. _____ system is used to diagnose bacterial infection.
a. Miner
b. MYCIN
c. EMYCIN
d. Puff
23. ____Phases are there in ES.
a. 4
b. 6
c. 5
d. 7
UNIT-5
2. Which of the factors affect the performance of the learner system does not include?
a) Representation scheme used
b) Training scenario
c) Type of feedback
b) Analogy
c) Deduction
d) Introduction
b) 2
c) 3
d) 4
b) Feedback
c) Problem
b) Unsupervised learning
c) Active learning
d) Reinforcement learning
c) Automated vehicle
8. In which of the following learning the teacher returns reward and punishment to learner?
a) Active learning
b) Reinforcement learning
c) Supervised learning
b) Model
c) Learning rules
b) Active learning
c) Unsupervised learning
d) Reinforcement learning
a) 1
b) 2
c) 3
d) 4
14.Which of the factors affect the performance of the learner system does not include?
a) Representation scheme used
c) Type of feedback
b) Analogy
c) Deduction
d) Introduction
b) 2
c) 3
d) 4
b) Feedback
c) Problem
b. 5
c. 7
d. 4
b. critic
c. manager
d. tester
20. In which of the following learning the teacher returns reward and punishment to
learner?
b) Reinforcement learning
c) Supervised learning
d) Unsupervised learning
b) Model
c) Learning rules
b) Active learning
c) Unsupervised learning
d) Reinforcement learning
b. 2
c. 3
d. 4
a. Rote
b. supervised
c. unsupervised
28. One of the most common uses of Machine Learning today is in the domain of _____.
A) Expert system
B) Unsupervised learning
D) Robotics
a. solution
b. problem
c. program
d. system
30. In regression the output is
A) Discrete.
B) Continuous and always lies in a finite range.
C) Continuous.
D) May be discrete or continuous.
31. What category of machine learning algorithm finds patterns in the data when the data
is not labeled?
a. three
b. four
c. two
d. five
34. In many programs, ____evaluation functions can be used to reduce search space.
a. static
b. dynamic
c. maths
d. engineering
a. learning
b. testing
c. outputs
d. middle nodes
36. There is no information available about the _____outputs in the unsupervised learning.
a. wrong
b. correct
c. no
d. more
b Tic-tac-toe
c. Checker
d. Go
38. In the ____model, the number of clusters can be varied according to the problem size.
a. SOM
b. Back-Prop
c. CNN
d. ART
a. goal
b. math
c. utility
d. sigmoid
a. pattern
b. task
c. goal
d. letter