OCS351QuestionBANK-Artificial Intelligence and Machine Learning fundamentals

UNIT1

SYLLABUS:INTELLIGENTAGENTANDUNINFORMEDSEARCH
Introduction - Foundations of AI - History of AI - The state of the art - Risks and Benefits of AI - Intelligent
Agents - Nature of Environment - Structure of Agent - Problem Solving Agents - Formulating Problems -
UninformedSearch-BreadthFirstSearch-Dijkstra'salgorithmoruniform-costsearch-DepthFirstSearch- Depth
Limited Search

PART-A
Q.No Questions Mark

WhatisArtificialIntelligence?APR/MAY2023 2M
1.
Whatisanagent? 2M
2.
Whatarethe differenttypesofagents? 2M
3.

Definerationalagent 2M
4.
Listdownthecharacteristicsofintelligentagent 2M
5.
WhatarevariousapplicationsofAI? or What can AI do today? 2M
6.

Are reflex actions (such as flinching from a hot stove) rational? Are theyintelligent 2M
7.
IsAIascience,orisitengineering?Orneitherorboth? Explain 2M
8.
Whatarethevariousagentprogramsinintelligentsystems? 2M
9.

Definetheproblemsolving agent. 2M
10.
Definethetermsgoalformulationandproblem formulation 2M
11.
Listthestepsinvolvedinsimpleproblemsolvingagent 2M
12.
Whatarethecomponentsofwell-definedproblems? (or) 2M
13. Whatare thefourcomponentsto define a problem?
 Definethem?

Differentiatetoyproblemsandrealworld roblems? 2M
14. pp

ListtheapplicationsofAI. 2M
15.
How will you measure the problem-solving performance? 2M
16.

DefineBFS. 2M
17.

Whatistheapplication ofBFS? 2M
18.
Stateonwhichbasissearchalgorithmsarechosen? 2M
19.
Evaluateperformanceofproblem-solvingmethod based on depth-first 2M
20. searchalgorithm?

Listsome oftheuninformed search techniques. 2M

21.

Evaluateperformanceofproblem-solvingmethodbased uninformed search techniques. 2M

22.

WhatisDFS? 2M
23.
WhatisDLS? 2M
24.
WhatisUCS? 2M
25.
DefineAI,enumerate thecharacteristicsofAI. 6M
1.
WhatareIntelligentAgentsanditscharacteristicsand describe the architecture of the 7M
2. Intelligent Agents.
InterpretthetypesofEnvironment. 13M
3.

Explainindetail thedifferent forms/typesof Agents? 13M

4.

EnumeratePEASenvironmentforaproduction environment. B 6M
5. T
 L
-
2
ExplainProblemsolvingapproachindetailwitha traveler map example. 7M
6.
ExplainProblemsolvingagentindetailwithadiagram. 13M
7.
InterpretanythreeUninformedSearch Strategies 13M
8.
Enumerate Classical “Water jug Problem”. Describe the state space for this 6M
9. problemandalso give the solution.

ExplainDijkstra’salgorithmwithasuitable example. 7M
10.
PART–C
Definethefollowingproblems.Whattypesofcontrol strategy is used in the following problem. 14M
1. i.TheTowerofHanoi ii.Crypto-arithmetic
iii.TheMissionariesandcannibals’problems iv.8-puzzle problem

Consider a Water Jug Problem : You are given two jugs,a4-gallononeanda3- 14M
2. gallonone.Neitherhasany measuring markers on it. There is a pump that can be used to fill
the jugs with water. How can you get exactly 2 gallons of water into the 4-gallon jug ?
Explicit Assumptions: A jug can be filled from the pump, water can be poured out of a
jug onto the ground, water can be poured from one jug to another
andthattherearenoothermeasuringdevicesavailable.

ExplaintheworkingofAlexa/SiriandwhatpartofAI techniques are used, 14M

3.

HowisAIassociatedwithmanufacturingindustryand its future explain the techniques in 14M

4. detail.
WhatisCHATGPTandelaboratetheusesofitand how is AI associated with it? 14M
5.
 UNIT2
SYLLABUS:PROBLEMSOLVINGWITHSEARCHTECHNIQUES
InformedSearch-GreedyBestFirst-A*algorithm-AdversarialGameandSearch-Gametheory-
Optimal decisions in game - Min Max Search algorithm - Alpha-beta pruning - Constraint
SatisfactionProblems (CSP) - Examples - Map Coloring - Job Scheduling - Backtracking Search for CSP
PART-A
Q.No Questions Mark

WhatisInformedSearch? 2M
1.
DefineGreedyBestFirstSearch. 2M
2.
Whatisthepowerofheuristicsearch?(or) Why does one go for 2M
3. heuristicssearch?

Whataretheadvantages ofheuristicfunction? 2M
4.
Statethereasonwhenhillclimbingoftengets stuck? 2M
5.
Whenaheuristicfunctionhissaidtobeadmissible? Give an admissibleheuristic 2M
6. function for TSP?

Whatdoyoumeanbylocalmaximawithrespecttosearch technique? 2M
7.

Howcanweavoidridgeandplateauinhill climbing? 2M
8.
DifferentiateBlindSearchandHeuristic Search 2M
9.
WhatisCSP? 2M
10.
Howcanminimaxalsobeextendedforgameofchance? 2M
11.

DefineA*search. 2M
12.
Whatisonlinelocalsearch. 2M
13.
WhatislearningrealtimeA*? 2M
14.
Whenistheclassofproblem saidto be interactable? 2M
15.
Whatisadversarialsearch?NOV/DEC2023 2M
16.
17 WhatisGame Theory? 2M

DefineMini-Max algorithm. 2M
18.
Definealphacutoffandbeta cutoff 2M
19.
DefineStochastic games. 2M
20.
WhatisBacktracking? 2M
21.
DefineJobScheduling. 2M
22.
Statethetechniques ofCSP. 2M
23.
Whatispruning? 2M
24.
WhatisLocalSearch? 2M
25.
PART-B
ExplainGametheory. 7M
1.
ExplaintheA*searchandgivetheproofofoptimalityofA* 13M
2.
ExplainAO*algorithmwithasuitableexample. State the limitations in 7M
3.
the algorithm?

Explainthetechniquesfordecisionmakingingames. 6M
4.

ExplainStochasticgames. 6M
5.
Discussaboutconstraintsatisfactionproblemwitha algorithm for solving a 13M
6. crypt arithmetic Problem
Explainalpha-betapruningalgorithmwithan example 13M
7.
ExplainJob-Schedulingindetailwithan example. 6M
8.
WhatisMin-Maxalgorithmexplainwithan example. 7M
9.
ExplainthebacktrackingtechniquesinCSP. 6M
10.

PART–C(Ifapplicable)
1.SolvethefollowingCryptarithmetic 14M
1. problemusingconstraintssatisfaction
search procedure.
 CROSS
+ROADS DANGER

Solve thegiven problem. Describe the operatorsinvolved in it. 14M

2. Consider a water jug problem: You are given two jugs, a 4-gallon one and a
3-gallon one.Neither have any measuring Markers on it. There is a pump
that can beusedtofillthejugwithwater.Howcanyougetexactly
2 gallons of water into the 4 gallon jug? Explicit Assumptions: A jug can be
filled from the pump, water can be poured out of a jug onto the ground,
water can be poured from one jug to another and that there are noother
measuring devices available.

ExplainA*searchwithanexample.Provetheoptimality, consistency and triangle 14M

3. inequality theorems.
ExplainLocalSearchandOptimization problem 14M
4.
DiscussaboutConstraintSatisfactionProblemandthe solution for Map 14M
5. coloring problem.

UNIT-3
SYLLABUS:LEARNING :Machine Learning: Definitions–Classification - Regression -
approaches of machine learning models - Types of learning - Probability - Basics - Linear
Algebra – Hypothesis space and inductive bias, Evaluation. Training and test sets, cross validation,
Concept of over fitting, under fitting, Bias and Variance -Regression: Linear Regression -
Logistic Regression

PART-A
Mark
Q.N Questions
o
WhatisMachineLearning? 2M
1.
MentionthedifferencebetweenDataMiningand Machine learning? 2M
2.

Whatis‘Overfitting’and‘Underfitting’inMachine learning? 2M
3.

DefineLogistic regression. 2M
4.
Whyoverfittinghappens? 2M
5.
2M
6. Howcanyouavoid overfitting?

WhatarethefivepopularalgorithmsofMachine Learning? 2M
7.

WhatarethedifferentAlgorithmtechniquesinMachine Learning? 2M
8.

What arethethreestagestobuild thehypothesesor modelin machine learning? 2M

9.

Whatisthestandard approachtosupervised learning? 2M

10.
Whatis‘Trainingset’ and‘Testset’? 2M
11.
Whatisthedifferencebetweenartificiallearningand machine learning? 2M
12.
 WhatisBiasandwhatare thetypesofBias? 2M
13.
What is the main key difference between supervised and unsupervised machine 2M
14. learning?

WhatisaLinearRegression? 2M
15.
Whatarethedisadvantagesofthelinearregression model? 2M
16.

Whatisthedifferencebetweenclassificationand regression? 2M
17.

Whatiscross validation? 2M
18.
Outlinedifferencebetweensupervisedlearningand unsupervised learning? 2M
19. APR/MAY 2023
WhatIsBayesianLinearRegressionandstateits advantages? 2M
20.

WhatisvarianceinMachineLearning? 2M
21.
DefineInductiveBias. 2M
22.
Whatisprobabilisticdiscriminativemodel? 2M
23.
DefineLinearAlgebraanditsapplicationinMachine Learning? 2M
24.
WhatisHypothesis? 2M
25.

PART–B
 Explainthefollowing 13M
1. • Linear regression

• LogisticRegression

WhatisMachineLearning?Explainindetailthevarious types of Machine Learning with 13M

2. examples.
WhatisProbability?ExplainPropositionsand Conditional Probabilities with an 6M
3. example.

WhatisCross-Validation. 7M
4. ExplainthevariousmethodsofCross-Validation?
WhatisLogisticRegressionexplainwithan example. 7M
5.
ExplainLinearAlgebraandAnalyticalGeometryof Machine Learning with real time 13M
6. examples.
WhatisHypothesisTesting?Explainwithdifferent techniques. 7M
7.
ExplainOverfittingandUnderfittingwithappropriate data set examples. 6M
8.
WhatisBiasandVarianceexplainwithsuitable examples. 6M
9.
ExplainBayestheoremandconditionalprobability. 13M
10.
Assumeadiseasesorarethatitisseeninonlyoneperson outof every million. Assume also that 14M
1. we have a test
thatiseffectiveinthatifapersonhasthedisease,thereis a 99 percent chance that the test
result will be positive; however, the test is not perfect, and there is a one in a thousand
chance that the test result will be positive on a
healthyperson.Assumethatanewpatientarrivesandthe test result is positive. What is the
probability that the patient has the disease?

Defineuncertainknowledge,PriorProbabilityand Conditional Probability. 14M

2. StateBayestheorem.Howusefulitisformaking Decisions.
 WhatisRegressionAnalysisexplainindetail. 14M
3.
FindthelinearRegressionequationforthefollowing two sets of data

Explaintheevaluationtechniquesfortheclassification based algorithms. 14M

4.
Givenasensordatafromamanufacturingindustryhow can we classify and what are the 14M
5. steps to get useful results from the sensor data for the future prediction explain with
any classification technique in detail and tool used.
 UNIT4

SYLLABUS:SUPERVISEDLEARNING-NeuralNetwork: Introduction, Perceptron

Networks– Adaline – Back propagation networks –DecisionTree: Entropy – Information gain –
Gini Impurity – classification algorithm – Rule based Classification –
NaïveBayesianclassification –SupportVectorMachines (SVM)

PART–A
Q.No Questions Mark

WhatisSupervised Learning? 2M
1.
Whatarethetypesofsupervisedlearning? 2M
2.
WhataretheadvantagesofNaiveBayes? 2M
3.

WhatisClassification? 2M
4.
WhatisError? 2M
5.
Whataretypesofclassificationmodels? 2M
6.
DefineActivationfunction. 2M
7.
WhatareweightsinNeural Networks? 2M
8.
Givethe componentsofa neural network. 2M
9.
WhatarethetypesofActivationfunctions? 2M
10.
WhatisID3? 2M
11.
DefineAdaline. 2M
12.
WhytouseBackpropagation technique? 2M
13.
WhatareDecisionTrees? 2M
14.
 WhatisSVM? 2M
15.
Whatare Hyperplanes? 2M
16.
DefineInformation gainwith formula. 2M
17.
WhatisEntropy? 2M
18.
WhatisGini Index? 2M
19.
WhatisCART? 2M
20.
DefineGiniImpurity witha formula. 2M
21.
WhatarethetypesofSVM? 2M
22.
WhatisRuleBased Algorithm? 2M
23.
GivetheformulaforNavieBasedclassificationwithrelevant explanation. 2M
24.
Givetherealtimeapplicationof (i)SVM 2M
25. (ii)NaïveBayes

PART–B
Draw the architecture of a single layer perceptron (SLP) and explainits operation. 6M
1. Mention its advantages and disadvantages.

Describebackpropagationand featuresofbackpropagation. 7M
2.
ExplainNaïveBayesClassifierwithanExample 13M
3.

ExplainSVMAlgorithmin Detail 7M
4.
ExplainDecisionTreeClassificationalgorithmwithanexampleand illustrate Gini 13M
5. Impurity
ExplainID3Algorithmwithan example. 13M
6.
ExplainAdalinein detail. 7M
7.
 Draw the architecture of a Multilayer perceptron(MLP) and explain its operation. 13M
8. Mention its advantages and disadvantages.
GiventheClass:C1:Play=‘yes’C2:Play=‘no’DatasampleX= (Outlook=Sunny, 6M
9. Temperature=Hot, Humidity=high, Windy=False)
Findoutwhichclass Xbelongstogiventhe table

ExplainCARTalgorithmin detail. 7M
10.
PART–C(Ifapplicable)
DevelopaBackpropagationalgorithmforMultilayerFeedforward neural network 14M
1. consisting of one input layer, one hidden layer and output layer from first principles

Listthefactorsthataffecttheperformanceofmultilayerfeed- forward neural network. 14M

2.

Explaindeeplearningindetail withan example. 14M

3.

Givenadatasethowcanitbeclassifiedusingrulebasedalgorithm what are the techniques 14M

4. available explain in detail.
Givenadatasetwithtextandimagehowcanitbeclassifiedand drawn conclusions explain 14M
5. in detail.
 UNIT5

SYLLABUS:UNSUPERVISEDLEARNING
UnsupervisedLearning – Principle Component Analysis –NeuralNetwork:
FixedWeight Competitive Nets – Kohonen Self-Organizing Feature Maps –
Clustering: Definition–TypesofClustering–Hierarchicalclusteringalgorithms–k-
means algorithm
PART–A

Q.No Questions Mark

WhatisUnsupervisedLearning? 2M
1.
WhatarethetypesofUnsupervisedLearning? 2M
2.
WhatareArtificial NeuralNetworks? 2M
3.

DefinePCA. 2M
4.
WhatisClustering? 2M
5.
WhatarethealgorithmsofClusteringtechnique? 2M
6.
WhatistherealtimeapplicationofPCA? 2M
7.
WhatisK-meansalgorithm? 2M
8.
WhatisFixedWeightCompetitiveNets? 2M
9.
WhatarethetypesofFixedWeightCompetitiveNets? 2M
10.
DefineMaxnet. 2M
11.
DefineSubnet. 2M
12.
 WhatisHammingNetwork? 2M
13.
Howmanylayers arethereinperceptron? 2M
14.
WhatisSOM? 2M
15.
WhatareKohonenSelf-OrganizingFeatureMaps? 2M
16.
What is the difference between a regular neural network and Kohonen Self-Organizing 2M
17. Feature Maps?
State the advantages of Kohonen Self-Organizing Feature Maps. 2M
18.
WhatareHierarchicalclustering algorithms? 2M
19.
WhatarethetypesofHierarchical clustering algorithms? 2M
20.

HowtheAgglomerativeHierarchicalclusteringWork? 2M
21.
Whatare dendrograms? 2M
22.
WhataretheadvantagesofHierarchicalclustering technique? 2M
23.
State the differences between Kohonen Self-Organizing Feature Maps and Fixed 2M
24. Weight Competitive Net.
DrawthearchitectureofMultilayer Perceptron. 2M
25. NOV/DEC2023
PART–B
WhatisUnsupervisedLearning?Explain2techniques of Unsupervised Learning in detail. 13M
1.
Explaintheconceptsofclusteringapproaches.Howit differ from classification. 7M
2.
List the applications of clustering and identify advantages and disadvantages of 6M
3. clustering algorithm

ExplaintheHierarchicalclusteringalgorithmswitha neat sketch. 7M

4.
 ExplainKohonenSelf-OrganizingFeatureMapsin detail. 13M
5.
ExplainFixedWeightCompetitiveNetsindetail. 13M
6.
WhatisPCA?Explain withthealgorithm. 6M
7.
Explaink-meansalgorithmwithanexampleand algorithm. 13M
8.
ExplainthetypesofFixedWeightCompetitiveNets. 6M
9.
List the applications of clustering and identify advantages and disadvantages 7M
10. ofKohonen Self- Organizing Feature Maps.

PART–C(Ifapplicable)
Using K-means Euclidean Distance Algorithm method find clusters for the following 14M
1.
A B C D
x 1 2 4 5
y 1 1 3 4
Whatisdimensionalityreductionexplainindetailwith an algorithm. 14M
2.
Givenadatasetjustifythereasonstogoforclustering what are the advantages and 14M
3. disadvantages.

Explainthedetailedstepsforsolvingaproblemusing SOM with suitable example. 14M

4.
How canneuralnetworksbeusedinmanufacturing industry explain the steps in detail. 14M
5.

SUBJECT INCHARGE HOD