Question - 1
Who was the inventor of the first neurocomputer?
Dr. John Hecht-Nielsen
Dr. Robert Hecht-Nielsen
Dr. Alex Hecht-Nielsen
Dr. Steve Hecht-Nielsen
Answer- B
Question - 2
How many types of Artificial Neural Networks?
Answer- A
Question - 3
In which ANN, loops are allowed?
FeedForward ANN
FeedBack ANN
Both A and B
None of the above
Answer- B
Question - 4
What is an auto-associative network?
a neural network that contains no loops
a neural network that contains feedback
a neural network that has only one loop
a single layer feed-forward neural network with pre-processing
Answer- B
Question - 5
Neural Networks are complex ______________ with many parameters.
Linear Functions
Nonlinear Functions
Discrete Functions
Exponential Functions
Answer- A
Question - 6
The output at each node is called_____.
node value
Weight
neurons
axons
Answer- A
Question - 7
In FeedForward ANN, information flow is _________.
unidirectional
bidirectional
multidirectional
All of the above
Answer- A
Question - 8
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:
Answer- C
Question - 9
Which of the following neural networks uses supervised learning?
Multilayer perceptron
Self organizing feature map
Hopfield network
All of the above
Answer- A
Question - 10
In Delta Rule for error minimization:
weights are adjusted w.r.to change in the output
weights are adjusted w.r.to difference between desired output and actual output
weights are adjusted w.r.to difference between input and output
None of these
Answer- B
Question - 11
Which of the following can be used for clustering of data?
Single layer perception
Multilayer perception
Self organizing map
Radial basis function
Answer- C
Question - 12
Backpropagation is a learning technique that adjusts weights in the neural network by propagating weight changes:
Forward from source to sink
Backward from sink to source
Forward from source to hidden nodes
Backward from sink to hidden nodes
Answer- B
Question - 13
Identify the following activation function:
phi(V) = Z + (1/ 1 + exp (-x * V + Y) ),
Z, X, Y are parameters
Gaussian function
Sigmoid function
Ramp function
Step function
Answer- B
Question - 14
Which of the following model has the ability to learn?
pitts model
rosenblatt perceptron model
both rosenblatt and pitts model
neither rosenblatt nor pitts
Answer- B
Question - 15
What was the 2nd stage in the perceptron model called?
sensory units
summing unit
association unit
output unit
Answer- C
Question - 16
What is the delta (error) in the perceptron model of neurons?
error due to environmental condition
difference between desired & target output
can be both due to difference in target output or environmental condition
none of the mentioned
Answer- A
Question - 17
What is Adaline in neural networks?
automatic linear element
adaptive line element
adaptive linear element
None of the mentioned
Answer- C
Question - 18
The operation of instar can be viewed as:
content addressing the memory
memory addressing the content
either content addressing or memory addressing
both content & memory addressing
Answer- A
Question - 19
What's the other name of Widrow & Hoff learning law:
Hebb
LMS
MMS
None of these
Answer- B
Question - 20
The other name for instar learning law:
looser take it all
winner give it all
winner take it all
looser give it all
Answer- C
Practice more set questions
