Thursday, 25 August 2022

Intro to Soft Computing Objective Questions

 

Question Statement        Solution with step wise marking

"Select a 4-input neuron weighs 1, 2, 3, 4. The transfer function here is linear, and the constant of proportionality is equivalent to 2. Also, the inputs here are 4, 10, 5, 20, respectively. Thus, the output would be:            a. 119

b. 123

c. 238

d. 76"    c 238

"Every connection link present in ANN gets linked to the ________ that consists of various statics about an input signal.

a. Activation function

b. Neurons

c. Bias

d. Weights

"             (d) Weights

"Neural network can be Classified with computing as

A. mimics human behaviour

B. information processing paradigm

C. both a and b

D. none of the above

"             both a and b

"While interpretation of Artificial neural network, one can say it is used for

A. pattern recognition

B. classification

C. clustering

D. all of the above

 

"             all of the above

"Classify the issues on which biological networks proves to be superior than AI networks?

a) robustness & fault tolerance

b) flexibility

c) collective computation

d) all of the mentioned

"             "Answer: d

Explanation: AI network should be all of the above mentioned."

"While inferring the neural network concept, Signal transmission at synapse is a?

a) physical process

b) chemical process

c) physical & chemical both

d) none of the mentioned

"             "Answer: b

Explanation: Since chemicals are involved at synapse, so its an chemical process."

"Classifying the fundamental function of dendrites in neural network Skelton ?

a) receptors

b) transmitter

c) both receptor & transmitter

d) none of the mentioned

"             Answer: a Explanation: Dendrites are tree like projections whose function is only to receive impulse.

"Inferring basic architecture of ANN, which is true for neural networks?

a)            It has set of nodes and connections

b)            Each node computes it’s weighted input

c)            Node could be in excited state or non-excited state

d)            All of the above

"             Answer: All of the above

"Compare and explain, what is plasticity in neural networks?

a)            input pattern has become static

b)            input pattern keeps on changing

c)            output pattern keeps on changing

d)            none of the above

"             ans: input pattern keeps on changing

"

Which application out of these of robots can be made of single layer feedforward network?

a) wall climbing

b) rotating arm and legs

c) gesture control

d) wall following

 

"             Answer: d Explanation: Wall folloing is a simple task and doesn’t require any feedback.

"What is objective of linear autoassociative feedforward networks?

a) to associate a given pattern with itself

b) to associate a given pattern with others

c) to associate output with input

d) none of the mentioned

"             "Answer: a

Explanation: The objective of linear autoassociative feedforward networks is to associate a given pattern with itself."

"What property should a feedback network have, to make it useful for storing information?

a) accretive behaviour

b) interpolative behaviour

c) both accretive and interpolative behaviour

d) none of the mentioned

"             "Answer: a

Explanation: During recall accretive behaviour make it possible for system to store information."

"Linear neurons can be useful for application such as interpolation, is it true?

a) yes

b) no

"             "Answer: a

Explanation: This means for input vector x, output vector y is produced and for input a.x, output will be a.y."

"Why do we need biological neural networks?

To make smart human interactive & user friendly system

To apply heuristic search methods to find solutions of problem

To solve tasks like machine vision & natural language processing

All of the above

 

"             "Answer : D

Explanation: To make smart human interactive & user friendly system, to apply heuristic search methods to find solutions of problem, to solve tasks like machine vision & natural language processing are the basic aims that a neural network achieve."

"Compare and explain, what A Neural Network can answer?

a)            For Loop questions

b)            what-if questions

c)            IF-The-Else Analysis Questions

d)            None of the mentioned

"             "Answer : B

Explanation: A Neural Network can answer what-if questions. So, option B is correct."

"Explain, Which of the following is true for neural networks?

a)            It has a set of nodes and connections

b)            A node could be in an excited state or non-excited state

c)            Each node computes it’s weighted input

d)            All of the above

"             "Answer : D

Explanation: Neural networks has a set of nodes and connections where each node computes it’s weighted input and a node could be in an excited state or non-excited state. So all of the above is correct."

"As compare to ANN, which of the following is an example of unsupervised neural network?

a)            Back-propagation network

b)            Hebb network

c)            Associative memory network

d)            Self-organizing feature map

"             Ans: Self organizing feature map

"During illustrating the active functions in ANN, Positive sign of weight indicates?

a) excitatory input

b) inhibitory input

c) can be either excitatory or inhibitory as such

d) none of the mentioned

"             "Answer: a

Explanation: Sign convention of neuron."

"The amount of output of one unit received by another unit depends on what?

a) output unit

b) input unit

c) activation value

d) weight

"             "Answer: d

Explanation: Activation is sum of wieghted sum of inputs, which gives desired output..hence output depends on weights."

"In neural network, how can connections between different layers be achieved?

a) interlayer

b) intralayer

c) both interlayer and intralayer

d) either interlayer or intralayer

"             "Answer: c

Explanation: Connections between layers can be made to one unit to another and within the units of a layer"

"A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant of proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. The output will be:

A. 238

B. 76

C. 119

D. 123

"             Ans: A. 238

"A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value, it outputs a 1, otherwise it just outputs a 0.

A. true

B. false

C. sometimes – it can also output intermediate values as well

D. can’t say

"             Ans: A. true

"A perceptron is: The perceptron is a single layer feed-forward neural network. It is not an autoassociative network because it has no feedback and is not a multiple layer neural network because the preprocessing stage is not made of neurons.

(a) a single layer feed-forward neural network with preprocessing

(b) an autoassociative neural network

(c) a double layer autoassociative neural network

     "        The answer is (a).

"What are the issues on which biological networks proves to be superior than AI networks?

a) robustness & fault tolerance

b) flexibility

c) collective computation

d) all of the mentioned" d) all of the mentioned

"Explain and classify, which of the following is true for neural networks?

(i) The training time depends on the size of the network.

(ii) Neural networks can be simulated on a conventional computer.

(iii)Artificial neurons are identical in operation to biological ones.

(a) all of them are true.

(b) (ii) is true.

(c) (i) and (ii) are true.

"             "The answer is (c).

The training time depends on the size of the network; the number of neuron is greater and therefore the the number of possible 'states' is increased. Neural networks can be simulated on a conventional computer but the main advantage of neural networks - parallel execution - is lost. Artificial neurons are not identical in operation to the biological ones. We don't know yet what the real neurons do in detail."

"In artificial Intelligence (AI), an environment is uncertain if it is ___

a)            Not fully observable and not deterministic

b)            Not fully observable or not deterministic

c)            Fully observable but not deterministic

d)            Not fully observable but deterministic

"             "Ans: Option (B) is correct.

Explanation : We say an environment is uncertain if it is not fully observable or not deterministic [Russell Pg. 43]."

"Which of the following is/are Common uses of RNNs?

A. Businesses Help securities traders to generate analytic reports

B. Detect fraudulent credit-card transaction

C. Provide a caption for images

D. All of the above

"             "Ans : D

Explanation: All of the above are Common uses of RNNs."

"CNN is mostly used when there is an?

 

A. structured data

B. unstructured data

C. Both A and B

D. None of the above

 

 

"             "Ans : B

Explanation: CNN is mostly used when there is an unstructured data set (e.g., images) and the practitioners need to extract information from it."

"Which neural network has only one hidden layer between the input and output?

 

A. Shallow neural network

B. Deep neural network

C. Feed-forward neural networks

D. Recurrent neural networks

 

 

"             "Ans : A

Explanation: Shallow neural network: The Shallow neural network has only one hidden layer between the input and output."

"Which is the following is true about neurons?

 A. A neuron has a single input and only single output

 B. A neuron has multiple inputs and multiple outputs

 C. A neuron has a single input and multiple outputs

 D. All of the above

"             Ans: D

"Which of the following statement is not correct?

 A. Neural networks mimic the human brain

 B. It can only work for a single input and a single output

 C. It can be used in image processing

 D. None

"             Ans: B

"Which of the following steps can be taken to prevent overfitting in a neural network?

 A. Dropout of neurons

 B. Early stopping

 C. Batch normalization

 D. All of the above

 

"             Ans: D

"Locate and classify, Neural networks can be used in-

 A. Regression problems

 B. Classification problems

 C. Clustering problems

 D. All of the above

"             Ans: D

"In a classification problem, which of the following activation function is most widely used in the output layer of neural networks?

 A. Sigmoid function

 B. Hyperbolic function

 C. Rectifier function

 D. All of the above

"             Ans: A

"Which of the following is true about bias?

 A. Bias is inherent in any predictive model

 B. Bias impacts the output of the neurons

 C. Both A and B

 D. None

"             Ans: C

"Which of the following is a loss function?

 A. Sigmoid function

 B. Cross entropy

 C. ReLu

 D. All of the above

"             Ans: B

"Suppose you have a dataset from where you have to predict three classes. Then which of the following configuration you should use in the output layer?

 A. Activation function = softmax, loss function = cross entropy

 B. Activation function = sigmoid, loss function = cross entropy

 C. Activation function = softmax, loss function = mean squared error

 D. Activation function = sigmoid, loss function = mean squared error

"             Ans: A

"Which of the following activation function can not be used in the output layer of an image classification model?

 A. ReLu

 B. Softmax

 C. Sigmoid

 D. None

"             Ans: A

"For a binary classification problem, which of the following activation function is used?

 A. ReLu

 B. Softmax

 C. Sigmoid

 D. None

"             Ans: C

"Which of the following makes a neural network non-linear?

 A. Convolution function

 B. Batch gradient descent

 C. Rectified linear unit

 D. All of the above

"             Ans: C

"In a neural network, which of the following causes the loss not to decrease faster?

 A. Stuck at a local minima

 B. High regularization parameter

 C. Slow learning rate

 D. All of the above

"             Ans: D

"Suppose the number of nodes in the input layer is 5 and the hidden layer is 10. The maximum number of connections from the input layer to the hidden layer would be-

 A. More than 50

 B. Less than 50

 C. 50

 D. None

"             Ans: C

"Report and recognize, Which of the following neural network model has a shared weight structure?

 A. Recurrent Neural Network

 B. Convolution Neural Network

 C. Both A and B

 D. None

"             Ans: C

"What is adaline in neural networks?

a)            adaptive line element

b)            adaptive linear element

c)            automatic linear element

d)            none of the mentioned

"             Ans: b

"Analyze and locate, which is true for neural networks?

a)            It has set of nodes and connections

b)            Each node computes it’s weighted input

c)            Node could be in excited state or non-excited state

d)            All of the above

"             Answer: All of the above

"Identify the models in neural networks?

a)            representation of biological neural networks

b)            mathematical representation of our understanding

c)            both first & second

d)            none of the above

"             Answer: both first & second

"Operations in the neural networks can perform what kind of operations?

a)            parallel

b)            serial

c)            both parallel & serial

d)            none of the above

"             Answer: both parallel & serial

"Report and recognize, Neural networks can be used in different fields. such as -

a)            Classification

b)            Data processing

c)            Compression.

d)            All of the above

"             Answer: All of the above.

"Which of the following option is not the disadvantage of Recurrent Neural Network?

a)            Training an RNN is quite a challenging task

b)            Inputs of any length can be processed in this model.

c)            Exploding and gradient vanishing is common in this model.

d)            It cannot process very long sequences if using 'tanh' or 'relu' as an activation function

"             Answer: Inputs of any length can be processed in this model.

"Report and recognize, a perceptron is:

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

 

B. an auto-associative neural network

 

C. a double layer auto-associative neural network

 

D. a neural network that contains feedback

 

 

"             A.a single layer feed-forward neural network with pre-processing

"Which of the following is not the promise of artificial neural network?

A. it can explain result

 

B. it can survive the failure of some nodes

 

C. it has inherent parallelism

 

D. it can handle noise

 

"             A.it can explain result

"Report and recognize, A Neural Network can answer

 

A.          

For Loop questions

 

B.          

what-if questions

 

C.          

IF-The-Else Analysis Questions

 

D.          

None of these"  "B.         

what-if questions"

"What is the name of the network, which includes backward links from the output to the inputs as well as the hidden layers?

 

Perceptron

Self-organizing maps

Multi-layered perceptron

Recurrent neural network"          D. Recurrent neural network

"Which of the following is true for unsupervised learning?

 

Some specific output values are disclosed

Some specific output values aren't disclosed

No relevant inputs value is specified

Both inputs as well outputs are specified"             Both inputs as well outputs are specified

"What is the feature of ANNs due to which they can deal with noisy, fuzzy, inconsistent data?

a) associative nature of networks

b) distributive nature of networks

c) both associative & distributive

d) none of the mentioned

"             "

Answer: c

Explanation: General characteristics of ANNs."

"What was the name of the first model which can perform wieghted sum of inputs?

a) McCulloch-pitts neuron model

b) Marvin Minsky neuron model

c) Hopfield model of neuron

d) none of the mentioned

"             "

Answer: a

Explanation: McCulloch-pitts neuron model can perform weighted sum of inputs followed by threshold logic operation."

"The amount of output of one unit received by another unit depends on what?

a) output unit

b) input unit

c) activation value

d) weight

"             "

Answer: d

Explanation: Activation is sum of wieghted sum of inputs, which gives desired output..hence output depends on weights."

"What is delta (error) in perceptron model of neuron?

a) error due to environmental condition

b) difference between desired & target output

c) can be both due to difference in target output or environmental condition

d) none of the mentioned

"             "

Answer: a

Explanation: All other parameters are assumed to be null while calculatin the error in perceptron model & only difference between desired & target output is taken into account."

"What was the main point of difference between the adaline & perceptron model?

a) weights are compared with output

b) sensory units result is compared with output

c) analog activation value is compared with output

d) all of the mentioned

"             "

Answer: c

Explanation: Analog activation value comparison with output,instead of desired output as in perceptron model was the main point of difference between the adaline & perceptron model."

"what is the another name of weight update rule in adaline model based on its functionality?

a) LMS error learning law

b) gradient descent algorithm

c) both LMS error & gradient descent learning law

d) none of the mentioned

"             "

Answer: c

"

"Connections across the layers in standard topologies & among the units within a layer can be organised?

a) in feedforward manner

b) in feedback manner

c) both feedforward & feedback

d) either feedforward & feedback

"             "

Answer: d

Explanation: Connections across the layers in standard topologies can be in feedforward manner or in feedback manner but not both."

"Locate and classify, What is perceptron?

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

A neural network that contains feedback

A double layer auto-associative neural network

An auto-associative neural network

"             Correct option is A

"Neural Networks are complex         functions with many parameter

Linear

Non linear

Discreate

Exponential

"             Correct option is A

"The network that involves backward links from output to the input and hidden layers is known as

Recurrent neural network

Self organizing maps

Perceptrons

Single layered perceptron

"             Correct option is A

"When a Network is ______, it loses the ability to generalize between similar input-output patterns.

Over trained

Curve-trained

Cost fitting

Above ALL"         A

"The ____ curve decreases monotonically to a minimum, it then start to increase as the training continues.

Early stopping point

training sample

validation learning

None"   C. validation learning

"Neurons are connected in__________

Series

Parallel

A complex

Individual"           ans: B

"Locate and classify, Axons are____________

Parts of the cell body

Connections between dendrites

Neuron outputs

Neuron inputs"  Ans: C

"Locate and classify, Neural Networks are complex ______________ with many parameters.

Linear Functions

Nonlinear Functions

Discrete Functions

Exponential Functions

"             Answer: A

"Activation functions play an important role in many ANN's

Networking

Communication

Neural Network

Internet connection

"             Answer: C

"Why is the XOR problem exceptionally interesting to neural network researchers?

A. because it can be expressed in a way that allows you to use a neural network

B. because it is complex binary operation that cannot be solved using neural networks

C. because it can be solved by a single layer perceptron

D. because it is the simplest linearly inseparable problem that exists.

"             Ans: D.because it is the simplest linearly inseparable problem that exists.

"Why are linearly separable problems of interest of neural network researchers?

A. because they are the only class of problem that network can solve successfully

B. because they are the only class of problem that perceptron can solve successfully

C. because they are the only mathematical functions that are continue

D. because they are the only mathematical functions you can draw

"             Ans: B. because they are the only class of problem that perceptron can solve successfully

"Select the correct option, which is true for neural networks?

A. it has set of nodes and connections

 

B. each node computes it’s weighted input

 

C. node could be in excited state or non-excited state

 

D. all of the mentioned

 

 

"             D.all of the mentioned

"Outline, out the following option, artificial neural network used for

 

A.          

Pattern Recognition

 

B.          

Classification

 

C.          

Clustering

 

D.          

All of these"        "D.        

All of these"

"Locate and classify, A Neural Network can answer

 

A.          

For Loop questions

 

B.          

what-if questions

 

C.          

IF-The-Else Analysis Questions

 

D.          

None of these"  "B.         

what-if questions"

"Which of the following is correct for the neural network?

 

I. The training time is dependent on the size of the network

 

II. Neural networks can be simulated on the conventional computers

 

III. Artificial neurons are identical in operation to a biological one

 

All of the above

(ii) is true

(i) and (ii) are true

None of the above

 

"             Answer: c) (i) and (ii) are true

"Which of the following is not the promise of an artificial neural network?

 

It can survive the failure of some nodes

It can handle noise

It can explain the result

It has inherent parallelism"          It can explain the result

"What is the name of the network, which includes backward links from the output to the inputs as well as the hidden layers?

 

Perceptron

Self-organizing maps

Multi-layered perceptron

Recurrent neural network"          D. Recurrent neural network

"A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant of proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. The output will be:

(a) 238

 (b) 76

(c) 119

(d) 52

"             "The answer is (b).

The output is found by multipling the weights with their respective inputs, summing the results and multipling with the trasfer function. Therefore: Output = 2 * (1*4 + 2*10 + 3*5 + 4*20) = 238"

"Why is the XOR problem exceptionally interesting to neural network researchers?

A. because it can be expressed in a way that allows you to use a neural network

B. because it is complex binary operation that cannot be solved using neural networks

C. because it can be solved by a single layer perceptron

D. because it is the simplest linearly inseparable problem that exists.

"             Ans: D.because it is the simplest linearly inseparable problem that exists.

"Illustrate and explain the back propagation best definition?

A. it is another name given to the curvy function in the perceptron

B. it is the transmission of error back through the network to adjust the inputs

C. it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

D. none of the mentioned

"             Ans: C.it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

"Comparing the basic structure of Neural Network with human body, when the cell is said to be fired?

a) if potential of body reaches a steady threshold values

b) if there is impulse reaction

c) during upbeat of heart

d) none of the mentioned

 

"             "Answer: a

Explanation: Cell is said to be fired if & only if potential of body reaches a certain steady threshold values."

"As compare to ANN architecture, what is equilibrium in neural systems?

a) deviation in present state, when small perturbations occur

b) settlement of network, when small perturbations occur

c) change in state, when small perturbations occur

d) none of the mentioned

Answer

"             "Answer: b

Explanation: Follows from basic definition of equilibrium."

"How is pattern storage task generally accomplished?

a) by a feedback network consisting of processing units with non linear output functions

b) by a feedback network consisting of processing units with linear output functions

c) by a feedforward network consisting of processing units with non linear output functions

d) by a feedforward network consisting of processing units with linear output functions

"             "Answer: b

Explanation: Pattern storage task generally accomplished by a feedback network consisting of processing units with non linear output functions."

"How can false minima be reduced in case of error in recall in feedback neural networks?

a) by providing additional units

b) by using probabilistic update

c) can be either probabilistic update or using additional units

d) none of the mentioned

"             "Answer: b

Explanation: Hard problem can be solved by additional units not the false minima."

"A far as different ANN networks are concerned, loops are allowed in?

a)            FeedForward ANN

b)            ForwardFeed ANN

c)            FeedBack ANN

d)            None of the above

 

"             "Answer : C

Explanation: In FeedBack ANN, loops are allowed. They are used in content addressable memories. So, option C is correct."

"Interpreted the concept of Neuron theory, what is Neuro software?

A. A software used to analyze neurons

B. It is powerful and easy neural network

C. Designed to aid experts in real world

D. It is software used by Neurosurgeon

 

"             "Ans : B

Explanation: Neuro software is powerful and easy neural network."

"Which of the following is not the promise of artificial neural network?

 

A. It can explain result

B. It can survive the failure of some nodes

C. It has inherent parallelism

D. It can handle noise

View Answer

 

"             "Ans : A

Explanation: The artificial Neural Network (ANN) cannot explain result."

"ln neural network, the network capacity is defined as:

a)            The traffic (tarry capacity of the network

b)            The total number of nodes in the network

c)            The number of patterns that can be stored and recalled in a network

d)            None of the above

 

"             Ans: The number of patterns that can be stored and recalled in a network

"Which of the following can be an application of neural network?

 

 

a)            Sales forecasting

b)            Data validation

c)            Risk management

d)            All of the above

"             Ans: All of the above

"Supervised learning and unsupervised learning are two board category of

a)            Data warehouse

b)            DBMS

c)            DBMS

d)            Neural Network

 

"             Ans: C

"_________ type of model, the algorithm learns from a dataset which is labelled, and the algorithm uses the answer keys to evaluate its accuracy on the training data.

a)            Supervised learning

b)            UnSupervised learning

c)            Reinforcement learning

d)            None of these

 

"             Ans: Supervised learning

"Which of the following is a representation learning algorithm?

A) Neural network

B) Random Forest

C) k-Nearest neighbor

D) None of the above

"             "Solution: (A)

Neural network converts data in such a form that it would be better to solve the desired problem. This is called representation learning.

"

"A neuron with 3 inputs has the weight vector [0.2  -0.1  0.1]^T and a bias θ = 0. If the input vector is X = [0.2  0.4  0.2]^T then the total input to the neuron is:

a. 0.20

b. 1.0

c. 0.02

d. -1.0 

"             "Answer:  (c).0.02

 

 

"

"How does the transmission/pulse acknowledged?

a) by lowering electric potential of neuron body

b) by raising electric potential of neuron body

c) both by lowering & raising electric potential

d) none of the mentioned 

"             Answer: c

"The cell body of neuron can be analogous to what mathematical operation?

a) summing

b) differentiator

c) integrator

d) none of the mentioned

"             "Answer: a

Explanation: Because adding of potential (due to neural fluid) at different parts of neuron is the reason of its firing"

"Which action is faster pattern classification or adjustment of weights in neural nets?

a) pattern classification

b) adjustment of weights

c) equal

d) either of them can be fast, depending on conditions

"             "Answer: a

Explanation: Memory is addressable, so thus pattern can be easily classified."

"What is the feature of ANNs due to which they can deal with noisy, fuzzy, inconsistent data?

a) associative nature of networks

b) distributive nature of networks

c) both associative & distributive

d) none of the mentioned

"             "Answer: c

Explanation: General characteristics of ANNs."

"What is asynchronous update in neural netwks?

a) output units are updated sequentially

b) output units are updated in parallel fashion

c) can be either sequentially or in parallel fashion

d) none of the mentioned

"             "Answer: a

Explanation: Output are updated at different time in the networks"

"If two layers coincide & weights are symmetric(wij=wji), then what is that structure called?

a) instar

b) outstar

c) autoassociative memory

d) heteroassociative memory

"             "Answer: c

Explanation: In autoassociative memory each unit is connected to every other unit & to itself."

"Why are linearly separable problems of interest of neural network researchers?

A. because they are the only class of problem that network can solve successfully

B. because they are the only class of problem that perceptron can solve successfully

C. because they are the only mathematical functions that are continue

D. because they are the only mathematical functions you can draw

"             Ans: B. because they are the only class of problem that perceptron can solve successfully

"Analyze and locate,  What are the Advantages of Neural Networks?

a)            It can be performed without any problem

b)            It can be implemented in any application.

c)            A neural network learns and reprogramming is not necessary

d)            All of the above

"             Answer: All of the above

"Analyze and locate, artificial Neural Network is based on which approach?

a)            Weak Artificial Intelligence approach

b)            Cognitive Artificial Intelligence approach

c)            Strong Artificial Intelligence approach

d)            Applied Artificial Intelligence approach

"             "View Answer: B

Explanation: Artificial Neural Network is based on Cognitive Artificial Intelligence approach. So, option B is correct."

"Which of the following is true for neural networks?

a)            It has a set of nodes and connections

b)            A node could be in an excited state or non-excited state

c)            Each node computes it’s weighted input

d)            All of the above

"             "Answer : D

Explanation: Neural networks has a set of nodes and connections where each node computes it’s weighted input and a node could be in an excited state or non-excited state. So all of the above is correct."

"Backpropagation is a learning technique that adjusts weights in the neural network by propagating weight changes

a)            Backward from sink to source

b)            Forward from source to sink

c)            Backward from sink to hidden nodes

d)            Forward from source to hidden nodes

"             "Answer : A

Explanation: Backward from sink to source."

"Analyze and locate, The fundamental unit of the neural network is

a)            Neuron

b)            Brain

c)            Nucleus

d)            Dendrites

"             "Answer : A

Explanation: Neurons are the fundamental units of the neural network."

"Which of the following techniques perform similar operations as dropout in a neural network?

a)            Bagging

b)            Boosting

c)            Stacking

d)            None of the above

"             "Answer : A

Explanation: The correct answer is bagging as dropout can be seen as an extreme form of bagging in which each model is trained on a single case, and each parameter of the model is very strongly regularized by sharing it with the corresponding parameter in all the other models. So, option A is correct."

"What is Neuro software?

a)            A software used to analyze neurons

b)            It is powerful and easy neural network

c)            It is software used by Neurosurgeon

d)            Designed to aid experts in real world

"             "Answer : B

Explanation: Neuro software is a powerful and easy neural network."

"What is perceptron?

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

b)            A neural network that contains feedback

c)            A double layer auto-associative neural network

d)            An auto-associative neural network

"             Correct option is A

"Which of the following is true for neural networks?

i.             The training time depends on the size of the

ii.            Neural networks can be simulated on a conventional

iii.           Artificial neurons are identical in operation to biological

a)            All

b)            Only (ii)

c)            (i) and (ii)

d)            None

"             Correct option is C

"Neural Networks are complex functions with many parameter

a)            Linear

b)            Non linear

c)            Discreate

d)            Exponential

"             Correct option is A

"Which of the following is true about model capacity (where model capacity means the ability of neural network to approximate complex functions)?

 A) As number of hidden layers increase, model capacity increases

 B) As dropout ratio increases, model capacity increases

 C) As learning rate increases, model capacity increases

 D) None of these

"             Ans: (A)

"Identify the following activation function :

φ(V) = Z + (1/ 1 + exp (– x * V + Y) ),

Z, X, Y are parameters

a.            Step function

b.            Ramp function

c.            Sigmoid function

d.            Gaussian function

  "           Answer: (c). Sigmoid function

"A neuron with 3 inputs has the weight vector [0.2 -0.1 0.1]^T and a bias θ = 0. If the input vector is X = [0.2 0.4 0.2]^T then the total input to the neuron is:

a.            0.20

b.            1.0

c.            0.02

d.            -1.0

   "          "Answer: (c).

0.02"

"Which of the following can be used for clustering of data ?

a.            Single layer perception

b.            Multilayer perception

c.            Self organizing map

d.            Radial basis function

"             "Answer: (c).

Self organizing map"

"Which of the following is true for neural networks?

(A). It has a set of nodes and connections

(B). Each node computes it’s weighted input

(C). A node could be in an excited state or non-excited state

(D). All of these

 

 

"             MCQ Answer: d

"Which of the following option is not the disadvantage of recurrent neural network?

a)            Inputs of any length can be processed in this model

b)            Exploding and gradient vanishing is common in this model

c)            Training an RNN is quite a challenging task

d)            It cannot process very long sequences if using ‘tanh’ or ‘relu’ as an activation function

"             Answer: Inputs of any length can be processed in this model

"The neural network can be used in different field. such as

a)            Data processing

b)            Classification

c)            Compression

d)            All of the above

"             Answer: All of the above

"What is auto association task in neural network?

a)            input pattern keeps on changing

b)            output pattern keeps on changing

c)            input pattern has become static

d)            None

"             Answer: input pattern keeps on changing

"A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value, it outputs a 1, otherwise it just outputs a 0.

A. true

 

B. false

 

C. sometimes – it can also output intermediate values as well

 

D. can’t say

 

 

"             A.true

"Which of the following is the component of learning system?

A. goal

 

B. model

 

C. learning rules

 

D. all of the mentioned

 

 

"             D.all of the mentioned

"Artificial neural network used for

 

A.          

Pattern Recognition

 

B.          

Classification

 

C.          

Clustering

 

D.          

All of these"        "D.        

All of these"

"Backpropagation can be defined as _________

 

It is another name given to the curvy function in the perceptron.

It is the transmission of errors back through the network to adjust the inputs.

It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

None of the above"         C. It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

"Which of the following is not the promise of an artificial neural network?

 

It can survive the failure of some nodes

It can handle noise

It can explain the result

It has inherent parallelism"          It can explain the result

"What are the issues on which biological networks proves to be superior than AI networks?

a) robustness & fault tolerance

b) flexibility

c) collective computation

d) all of the mentioned" d) all of the mentioned

" What is hebb’s rule of learning

a) the system learns from its past mistakes

b) the system recalls previous reference inputs & respective ideal outputs

c) the strength of neural connection get modified accordingly

d) none of the mentioned

"             "

Answer:c

Explanation: The strength of neuron to fire in future increases, if it is fired repeatedly."

"Operations in the neural networks can perform what kind of operations?

a) serial

b) parallel

c) serial or parallel

d) none of the mentioned

 

"             "Answer: c

Explanation: General characteristics of neural networks."

"Which action is faster pattern classification or adjustment of weights in neural nets?

a) pattern classification

b) adjustment of weights

c) equal

d) either of them can be fast, depending on conditions

 

"             "Answer: a

Explanation: Memory is addressable, so thus pattern can be easily classified."

"Classify and select from the given option, what is an activation value?

a) weighted sum of inputs

b) threshold value

c) main input to neuron

d) none of the mentioned

"             "

Answer: a

Explanation: It is definition of activation value & is basic q&a."

"Predict and select, Positive sign of weight indicates?

a) excitatory input

b) inhibitory input

c) can be either excitatory or inhibitory as such

d) none of the mentioned

"             "

Answer: a

Explanation: Sign convention of neuron."

"Explain, Negative sign of weight indicates?

a) excitatory input

b) inhibitory input

c) excitatory output

d) inhibitory output

"             "

Answer: b

Explanation: Sign convention of neuron."

"The process of adjusting the weight is known as?

a) activation

b) synchronisation

c) learning

d) none of the mentioned

"             "

Answer: c

Explanation: Basic definition of learning in neural nets ."

"The procedure to incrementally update each of weights in neural is referred to as?

a) synchronisation

b) learning law

c) learning algorithm

d) both learning algorithm & law

"             "

Answer: d

Explanation: Basic definition of learning law in neural."

"Classify and select from the given option, how can output be updated in neural network?

a) synchronously

b) asynchronously

c) both synchronously & asynchronously

d) none of the mentioned

"             "

Answer: c

Explanation: Output can be updated at same time or at different time in the networks."

"What is asynchronous update in neural netwks?

a) output units are updated sequentially

b) output units are updated in parallel fashion

c) can be either sequentially or in parallel fashion

d) none of the mentioned

"             "

Answer: a

Explanation: Output are updated at different time in the networks."

"What was the 2nd stage in perceptron model called?

a) sensory units

b) summing unit

c) association unit

d) output unit

"             "

Answer: c

Explanation: This was the very speciality of the perceptron model, that is performs association mapping on outputs of he sensory units."

"What is adaline in neural networks?

a) adaptive linear element

b) automatic linear element

c) adaptive line element

d) none of the mentioned

"             "

Answer: a

Explanation: adaptive linear element is the full form of adaline neural model."

"In neural how can connectons between different layers be achieved?

a) interlayer

b) intralayer

c) both interlayer and intralayer

d) either interlayer or intralayer

"             "

Answer: c

Explanation: Connections between layers can be made to one unit to another and within the units of a layer."

"What is STM in neural network?

a) short topology memory

b) stimulated topology memory

c) short term memory

d) none of the mentioned

"             "

Answer: c

Explanation: Full form of STM."

"State whether Hebb’s law is supervised learning or of unsupervised type?

a) supervised

b) unsupervised

c) either supervised or unsupervised

d) can be both supervised & unsupervised

"             "

Answer: b

Explanation: No desired output is required for it’s implementation."

"Classify and select from the given option, What is the objective of backpropagation algorithm?

To develop learning algorithm for multilayer feedforward neural network, so that network can be trained to capture the mapping implicitly

To develop learning algorithm for multilayer feedforward neural network

To develop learning algorithm for single layer feedforward neural network

All of the above

"             Correct option is A

"What is true regarding backpropagation rule?

Error in output is propagated backwards only to determine weight updates

There is no feedback of signal at nay stage

It is also called generalized delta rule

All of the above

"             Correct option is D

"The general limitations of back propagation rule is/are

Scaling

Slow convergence

Local minima problem

All of the above

"             Correct option is D

"In backpropagation rule, how to stop the learning process?

No heuristic criteria exist

On basis of average gradient value

There is convergence involved

None of these

"             Correct option is B

"Hessian Matrix is will support to study of neural networks specially for _____

Pruning

Second order

Optimization

Above ALL"         D

"The Learning process may be viewed as a ______ problem.

Curve-cutting

Curve-Fitting

Over-Fitting

Over Training"    B. Curve-Fitting

"A neural network with minimum size is likely to learn _____

Idiosyncrasies

noise in the trained data

Generalize better to new data

Above ALL"         Ans: D

"In _____, the winning neuron determines the spatial location of a topological neighbourhood of exited neurons.

Competition

Synaptic adaptation

Cooperation

Above ALL"         Ans: C

"In order to study of neuro dynamics, we need a _____ model.

Computational

Mathematical

Scientific

Above ALL"         Ans: B

"Classify and select from the given option, Perceptions are suitable for

Single layer only

Multi-layer only

Single and multi layer

Single neuron only

"             Answer: B

"Outline, out the following option, stochastic neural networks is a_________

Back Propagation Algorithm

Security Algorithm

NN Algorithm

Feed forward Algorithm

"             Answer: A

"For what purpose Feedback neural networks are primarily used?

 

a) classification

 

b) feature mapping

 

c) pattern mapping

 

d) none of the mentioned"           Ans: a

"A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value, it outputs a 1, otherwise it just outputs a 0.

A. true

B. false

C. sometimes – it can also output intermediate values as well

D. can’t say

"             Ans: A. true

"A perceptron is: The perceptron is a single layer feed-forward neural network. It is not an autoassociative network because it has no feedback and is not a multiple layer neural network because the preprocessing stage is not made of neurons.

(a) a single layer feed-forward neural network with preprocessing

(b) an autoassociative neural network

(c) a double layer autoassociative neural network

     "        The answer is (a).

"Which of the following is not the promise of artificial neural network?

A. it can explain result

 

B. it can survive the failure of some nodes

 

C. it has inherent parallelism

 

D. it can handle noise

 

"             A.it can explain result

"A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value, it outputs a 1, otherwise it just outputs a 0.

A. true

 

B. false

 

C. sometimes – it can also output intermediate values as well

 

D. can’t say

 

 

"             A.true

"Explain in terms of Neural Network architecture, where do the chemical reactions take place in neuron?

a) dendrites

b) axon

c) synapses

d) nucleus

"             "Answer: c

Explanation: It is a simple biological fact."

"Which of the following option is not the disadvantage of Recurrent Neural Network?

a)            Training an RNN is quite a challenging task

b)            Inputs of any length can be processed in this model.

c)            Exploding and gradient vanishing is common in this model.

d)            It cannot process very long sequences if using 'tanh' or 'relu' as an activation function

"             Answer: Inputs of any length can be processed in this model.

"Illustrate and compare, what are pros of neural networks over computers?

a) they have ability to learn b examples

b) they have real time high computational rates

c) they have more tolerance

d) all of the mentioned

 

"             "Answer: d

Explanation: Because of their parallel structure, they have high computational rates than conventional computers, so all are true."

"1.          Backpropagation is a learning technique that adjusts weights in the neural network by propagating weight changes

a)            Backward from sink to source

b)            Forward from source to sink

c)            Backward from sink to hidden nodes

d)            Forward from source to hidden nodes

"             "Answer : A

Explanation: Backward from sink to source."

"Back propagation is a learning technique that adjusts weights in the neural network by propagating weight changes.

a.            Forward from source to sink

b.            Backward from sink to source

c.            Forward from source to hidden nodes

d.            Backward from sink to hidden nodes

"             Ans: b

"Back propagation is a learning technique that adjusts weights in the neural network by propagating weight changes.

 

 

  (A) Forward from source to sink

 (B) Backward from sink to source

 (C) Forward from source to hidden

(D) Backward from since to hidden nodes"            Ans: B

"Analyze and locate, which of the following is an unsupervised neural network?

a)            RBS

b)            Hopfield

c)            Back propagation

d)            Kohonen

 

 

"             Ans: Kohonen

"The most suitable activation function for hidden layer

a)            Sigmoid

b)            Softmax

c)            ReLu

d)            Tanh

"             Ans: ReLU

"Exemplifying the human neuron structure,  what are dendrites?

a) fibers of nerves

b) nuclear projections

c) other name for nucleus

d) none of the mentioned 

"             Answer: a

"The membrane which allows neural liquid to flow will?

a) never be imperturbable to neural liquid

b) regenerate & retain its original capacity

c) only the certain part get affected, while rest becomes imperturbable again

d) none of the mentioned

"             "Answer: b

Explanation: Each cell of human body(internal) has regenerative capacity"

"Why can’t we design a perfect neural network?

a) full operation is still not known of biological neurons

b) number of neuron is itself not precisely known

c) number of interconnection is very large & is very complex

d) all of the mentioned

"             "Answer: d

Explanation: These are all fundamental reasons, why can’t we design a perfect neural network"

"Illustrate and explain, what is learning signal in this equation ∆wij= µf(wi a)aj?

a) µ

b) wi a

c) aj

d) f(wi a)

"             "Answer: d

Explanation: This the non linear representation of output of the network."

"Which of the following is NOT true in problem solving in artificial intelligence?

a)            Implements heuristic search technique

b)            Solution steps are not explicit

c)            Knowledge is imprecise

d)            It works on or implements repetition mechanism

 

"            

"Which of the following is well suited for perceptual tasks?

A. Feed-forward neural networks

B. Recurrent neural networks

C. Convolutional neural networks

D. Reinforcement Learning

 

"             "Ans : C

Explanation: CNN is a multi-layered neural network with a unique architecture designed to extract increasingly complex features of the data at each layer to determine the output. CNNs are well suited for perceptual tasks."

"What is the purpose of a loss function?

 A. Calculate the error value of the forward network

 B. Optimize the error values according to the error rate

 C. Both A and B

 D. None

"             Ans: C

"In which type of neural network, the data is grouped based on its distance from a center point?

a)            Convolution Neural Network

b)            Recurrent Neural Network

c)            Modular Neural Network

d)            Radial Basis Functions Neural Network

"             Answer: Radial Basis Functions Neural Network

"Assume that your machine has a large enough RAM dedicated to training neural networks. Compared to using stochastic gradient descent for your optimization, choosing a batch size that fits your RAM will lead to::

A)           a more precise but slower update.

B)           a less precise but faster update.

C)           a less precise and slower update.

D)           a more precise and faster update.

"             Correct Answer : Option (A) :   a more precise but slower update.

"Recognize, why do we need biological neural networks?

a)            To make smart human interactive & user friendly system

b)            To apply heuristic search methods to find solutions of problem

c)            To solve tasks like machine vision & natural language processing

d)            All of the above

"             "Answer: D

Explanation: To make smart human interactive & user friendly system, to apply heuristic search methods to find solutions of problem, to solve tasks like machine vision & natural language processing are the basic aims that a neural network achieve."

"An auto-associative neural network is:

a)            A neural network that contains no loops

b)            A neural network that contains feedback

c)            A neural network that has only one loop

d)            A single layer feed-forward neural network with pre-processing

"             "Answer : B

Explanation: An auto-associative neural network is a neural network that contains feedback."

"Which of the factors affect the performance of the learner system does not include?

a)            Good data structures

b)            Representation scheme used

c)            Training scenario

d)            Type of feedback

"             Correct option is A

"In general, to have a well-defined learning problem, we must identity which of the following

a)            The class of tasks

b)            The measure of performance to be improved

c)            The source of experience

d)            All of the above

"             Correct option is D

"Report and recognize, which of the following does not include different learning methods

a)            Analogy

b)            Introduction

c)            Memorization

d)            Deduction

"             Correct option is B

"Concept learning inferred a valued function from training examples of its input and output.

a)            Decimal

b)            Hexadecimal

c)            Boolean

d)            All of the above

"             Correct option is C

"Real-Time decisions, Game AI, Learning Tasks, Skill Aquisition, and Robot Navigation are applications of which of the folowing

a)            Supervised Learning: Classification

b)            Reinforcement Learning

c)            Unsupervised Learning: Clustering

d)            Unsupervised Learning: Regression

"             Correct option is B

"Targetted marketing, Recommended Systems, and Customer Segmentation are applications in which of the following

a)            Supervised Learning: Classification

b)            Unsupervised Learning: Clustering

c)            Unsupervised Learning: Regression

d)            Reinforcement Learning

"             Correct option is B

"Applications of NN (Neural Network)

A)           Risk management

B)           Data validation

C)           Sales forecasting

D)           All of the above

"             Correct option is D

"Match the following knowledge representation techniques with their applications:

List – I List – II

(a) Frames (i) Pictorial representation of objects, their attributes and relationships

(b) Conceptual dependencies (ii) To describe real world stereotype events

(c) Associative networks (iii) Record like structures for grouping closely related knowledge

(d) Scripts (iv) Structures and primitives to represent sentences

code:

a b c d

a.            (iii) (iv) (i) (ii)

b.            (iii) (iv) (ii) (i)

c.            (iv) (iii) (i) (ii)

d.            (iv) (iii) (ii) (i)

 

"             "Answer: (a).

(iii) (iv) (i) (ii)"

"Which of the following neural networks uses supervised learning?

 

(A) Multilayer perceptron

(B) Self organizing feature map

(C) Hopfield network

a.            (A) only

b.            (B) only

c.            (A) and (B) only

d.            (A) and (C) only

   "          "Answer: (a).

(A)          only"

"Which is true for neural networks?

A. it has set of nodes and connections

 

B. each node computes it’s weighted input

 

C. node could be in excited state or non-excited state

 

D. all of the mentioned

 

 

"             D.all of the mentioned

"Which of the following is correct for the neural network?

 

I. The training time is dependent on the size of the network

 

II. Neural networks can be simulated on the conventional computers

 

III. Artificial neurons are identical in operation to a biological one

 

All of the above

(ii) is true

(i) and (ii) are true

None of the above

 

"             Answer: c) (i) and (ii) are true

"Computational benefit of back propagation learning is/are ______

Sensitivity analysis

Efficiency

Robustness

Above ALL"         Ans: D

"Classify, what is back propagation?

It is another name given to the curvy function in the perceptron

It is the transmission of error back through the network to adjust the inputs

It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn

None of the mentioned

"             Answer: C

"Illustrate and explain the back propagation best definition?

A. it is another name given to the curvy function in the perceptron

B. it is the transmission of error back through the network to adjust the inputs

C. it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

D. none of the mentioned

"             Ans: C.it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

"Which of the following is the component of learning system?

A. goal

 

B. model

 

C. learning rules

 

D. all of the mentioned

 

 

"             D.all of the mentioned

"Backpropagation can be defined as _________

 

It is another name given to the curvy function in the perceptron.

It is the transmission of errors back through the network to adjust the inputs.

It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

None of the above"         C. It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

"Outline out the following option, which of the following is true for unsupervised learning?

 

Some specific output values are disclosed

Some specific output values aren't disclosed

No relevant inputs value is specified

Both inputs as well outputs are specified"             Both inputs as well outputs are specified

              

GATE Notes

Intro to Soft Computing Objective Questions

  Question Statement         Solution with step wise marking "Select a 4-input neuron weighs 1, 2, 3, 4. The transfer function here...