# BE Computer Engineering Curriculum Scheme: Rev 2016 Exa

Download BE Computer Engineering Curriculum Scheme: Rev 2016 Exa

## Preview text

University of Mumbai Examination 2020 under cluster 4 (PCE)

Time: 1 hour

Program: BE Computer Engineering Curriculum Scheme: Rev 2016 Examination: Final Year Semester VII Course Code: CSC703 and Course Name: AISC

Max. Marks: 50

Ability to learn how to do tasks based on the data given

Q

for training or initial experience is called?

M

A

Self Organization

0

A

Adaptive Learning

1

A

Fault tolerance

0

A

Robustness

0

Q

Core of soft Computing is?

M

A

Fuzzy Networks and Artificial Intelligence

0

A

Fuzzy Computing, Neural Computing, Genetic Algorithms

1

A

Artificial Intelligence and Neural Science

0

A

Neural Science and Genetic Science

0

Q

Which search comes under Local search ?

M

A

A* search

0

A

BFS

0

A

Hill Climbing Search

1

A

DFS

0

Q

State space landscape is a term used in

M

A

Local Search algorithm

1

A

Informed search algorithm

0

A

Uninformed search algorithm

0

A

Blind search algorithm

0

Memory space requirement in hill climbing algorithm is

Q

_____

M

A

Less

1

A

More

0

A

very high

0

A

Zero

0

______ are the curves in the search space that leads to

Q

sequence of local maxima

M

A

Plateau

0

A

Ridges

1

A

Peak

0

A

Mount

0

Q

Which of the mentioned rules are valid Inference rules? M

A

Modus Ponens

1

A

addition

0

A

multiplication

0

A

subdivision

0

Which of the mentioned point correctly defines a

Q

quantifier in AI?

M

A

Quantifiers are numbers ranging from 0-9.

0

A

Quantifiers are the quantity defining terms which are used with the predica1tes.

A

Quantifiers quantize the term between 0 and 1.

0

A

Quantifiers quantize the term between 10 and 100.

0

Q

What are not present in finish actions?

M

A

Preconditions

0

A

Effect

1

A

Finish

0

A

Cause

0

Q

Which is not Familiar Connectives in First Order Logic? M

A

and

0

A

iff

1

A

or

0

A

not

0

Three main basic features involved in characterizing

Q

membership function are

M

A

Core, Support , Boundary

1

A

Fuzzy Algorithm, Neural network, Genetic Algorithm

0

A

Intution, Inference, Rank Ordering

0

A

Weighted Average, center of Sums, Median

0

Q

Fuzzy Logic is ____

M

A

Multi Valued Logic

1

A

Binary Logic

0

A

Crisp set Logic

0

A

Two level logic

0

Given U = {1, 2, 3, 4, 5, 6, 7} A = {(3, 0.3), (5, 0.4), (6,

Q

1)} then ~A(Complement of A) is

M

A

{(2,1),(3,0.3),(4,1),(5,0.6),(7,1)

0

A

{(1,1),(2,1),(3,0.7),(4,1),(5,0.6),(7,1)}

1

A

{(1,1)(2,1),(3,0.7),(4,0.4),(5,0.6),(6,1),(7,1)

0

A

{(3,0.7),(5,0.6)(6,1),(7,1)}

0

Q

the points of fuzzy set A at which µA(x)=0.5 are called M

A

Boundary

0

A

core

0

A

crossover points

1

A

Support

0

Q

Fuzzy relation R is symmetric if _______

M

A

μR(xi,xj)=μR(xj,xi)

1

A

μR(xi,xi)=1

0

A

μR(xj,xi)=μR(xj,xi)

0

A

μR(xi,xi)=μR(xj,xj)

0

Intersection Operation of two fuzzy set is given

Q

by__________ operation

M

A

max

0

A

abs

0

A

min

1

A

average

0

Q

Complement of Fuzzy set A is given by

M

A

1+μA(x)

0

A

1/μA(x)

0

A

2*μA(x)

0

A

1-μA(x)

1

__________ are designed to solve complex problems by

reasoning about knowledge, represented primarily as if–then rules rather than through conventional procedural

Q

code.

M

A

neural network

0

A

Perceptrons

0

A

Expert systems

1

A

Quantization

0

________ is used for topology optimization i.e. to select

number of hidden layers, number of hidden nodes and

Q

interconnection pattern for ANN.

M

A

Neuro-fuzzy system

0

A

Forward neural network

0

A

Neural network

0

A

Genetic algorithm

1

Q

What Perceptron is?

M

A

a single layer feed-forward neural network with pre-processing

1

A

an auto-associative neural network

0

A

a double layer auto-associative neural network

0

A

a neural network that contains feedback

0

Q

Signal transmission at synapse is a

M

A

Physical process

0

A

Chemical Procees

1

A

Biological process

0

A

Activation

0

Backpropogation is applied for which type of network

Q

architecture

M

A

Single layer feed forward

0

A

Single layer feedback network

0

A

Multilayer feedback network

0

A

Multilayer feed forward network

1

Why is the XOR problem exceptionally interesting to

Q

neural network researchers

M

A

Because it can be expressed in a way that allows you to use a neural netwo0rk

A

Because it is complex binary operation that cannot be solved using neural n0etworks

A

Because it can be solved by a single layer perceptron

0

A

Because it is the simplest linearly inseparable problem that exists.

1

Q

The process of adjusting the weight is known as?

M

A

Activation

0

A

Synchronisation

0

A

Learning

1

A

Classification

0

Q

What is an activation value?

M

A

Weighted sum of inputs

1

A

Threshold value

0

A

Main input to neuron

0

A

Function

0

Time: 1 hour

Program: BE Computer Engineering Curriculum Scheme: Rev 2016 Examination: Final Year Semester VII Course Code: CSC703 and Course Name: AISC

Max. Marks: 50

Ability to learn how to do tasks based on the data given

Q

for training or initial experience is called?

M

A

Self Organization

0

A

Adaptive Learning

1

A

Fault tolerance

0

A

Robustness

0

Q

Core of soft Computing is?

M

A

Fuzzy Networks and Artificial Intelligence

0

A

Fuzzy Computing, Neural Computing, Genetic Algorithms

1

A

Artificial Intelligence and Neural Science

0

A

Neural Science and Genetic Science

0

Q

Which search comes under Local search ?

M

A

A* search

0

A

BFS

0

A

Hill Climbing Search

1

A

DFS

0

Q

State space landscape is a term used in

M

A

Local Search algorithm

1

A

Informed search algorithm

0

A

Uninformed search algorithm

0

A

Blind search algorithm

0

Memory space requirement in hill climbing algorithm is

Q

_____

M

A

Less

1

A

More

0

A

very high

0

A

Zero

0

______ are the curves in the search space that leads to

Q

sequence of local maxima

M

A

Plateau

0

A

Ridges

1

A

Peak

0

A

Mount

0

Q

Which of the mentioned rules are valid Inference rules? M

A

Modus Ponens

1

A

addition

0

A

multiplication

0

A

subdivision

0

Which of the mentioned point correctly defines a

Q

quantifier in AI?

M

A

Quantifiers are numbers ranging from 0-9.

0

A

Quantifiers are the quantity defining terms which are used with the predica1tes.

A

Quantifiers quantize the term between 0 and 1.

0

A

Quantifiers quantize the term between 10 and 100.

0

Q

What are not present in finish actions?

M

A

Preconditions

0

A

Effect

1

A

Finish

0

A

Cause

0

Q

Which is not Familiar Connectives in First Order Logic? M

A

and

0

A

iff

1

A

or

0

A

not

0

Three main basic features involved in characterizing

Q

membership function are

M

A

Core, Support , Boundary

1

A

Fuzzy Algorithm, Neural network, Genetic Algorithm

0

A

Intution, Inference, Rank Ordering

0

A

Weighted Average, center of Sums, Median

0

Q

Fuzzy Logic is ____

M

A

Multi Valued Logic

1

A

Binary Logic

0

A

Crisp set Logic

0

A

Two level logic

0

Given U = {1, 2, 3, 4, 5, 6, 7} A = {(3, 0.3), (5, 0.4), (6,

Q

1)} then ~A(Complement of A) is

M

A

{(2,1),(3,0.3),(4,1),(5,0.6),(7,1)

0

A

{(1,1),(2,1),(3,0.7),(4,1),(5,0.6),(7,1)}

1

A

{(1,1)(2,1),(3,0.7),(4,0.4),(5,0.6),(6,1),(7,1)

0

A

{(3,0.7),(5,0.6)(6,1),(7,1)}

0

Q

the points of fuzzy set A at which µA(x)=0.5 are called M

A

Boundary

0

A

core

0

A

crossover points

1

A

Support

0

Q

Fuzzy relation R is symmetric if _______

M

A

μR(xi,xj)=μR(xj,xi)

1

A

μR(xi,xi)=1

0

A

μR(xj,xi)=μR(xj,xi)

0

A

μR(xi,xi)=μR(xj,xj)

0

Intersection Operation of two fuzzy set is given

Q

by__________ operation

M

A

max

0

A

abs

0

A

min

1

A

average

0

Q

Complement of Fuzzy set A is given by

M

A

1+μA(x)

0

A

1/μA(x)

0

A

2*μA(x)

0

A

1-μA(x)

1

__________ are designed to solve complex problems by

reasoning about knowledge, represented primarily as if–then rules rather than through conventional procedural

Q

code.

M

A

neural network

0

A

Perceptrons

0

A

Expert systems

1

A

Quantization

0

________ is used for topology optimization i.e. to select

number of hidden layers, number of hidden nodes and

Q

interconnection pattern for ANN.

M

A

Neuro-fuzzy system

0

A

Forward neural network

0

A

Neural network

0

A

Genetic algorithm

1

Q

What Perceptron is?

M

A

a single layer feed-forward neural network with pre-processing

1

A

an auto-associative neural network

0

A

a double layer auto-associative neural network

0

A

a neural network that contains feedback

0

Q

Signal transmission at synapse is a

M

A

Physical process

0

A

Chemical Procees

1

A

Biological process

0

A

Activation

0

Backpropogation is applied for which type of network

Q

architecture

M

A

Single layer feed forward

0

A

Single layer feedback network

0

A

Multilayer feedback network

0

A

Multilayer feed forward network

1

Why is the XOR problem exceptionally interesting to

Q

neural network researchers

M

A

Because it can be expressed in a way that allows you to use a neural netwo0rk

A

Because it is complex binary operation that cannot be solved using neural n0etworks

A

Because it can be solved by a single layer perceptron

0

A

Because it is the simplest linearly inseparable problem that exists.

1

Q

The process of adjusting the weight is known as?

M

A

Activation

0

A

Synchronisation

0

A

Learning

1

A

Classification

0

Q

What is an activation value?

M

A

Weighted sum of inputs

1

A

Threshold value

0

A

Main input to neuron

0

A

Function

0

## Categories

## You my also like

### BPL Annual Report Final Single Page

2 MB23.6K10.8K### Generalized quantifiers and modal logic

2.2 MB22.1K4.9K### Chapter 10: The Logic of Quantifiers

48 KB79.4K21.4K### A Contrastive Analysis of Bangla and English Determiners

189.9 KB57.2K13.2K### The Open Logic Text

4 MB20K8.2K### Expanding the universe of categorical syllogisms: A challenge

436.4 KB5.5K2.2K### Quantifier Worksheet (1)

330.7 KB4K1.2K### Chapter 6 The Landscape of Greek Quantifiers

631.2 KB1.5K565### Contrastive Analysis Of Arabic And English: The Quantifiers

211.5 KB5.6K1.8K