NNFS Short Questions
Uploaded by
Megha AryaNNFS Short Questions
Uploaded by
Megha AryaNeural Networks and Fuzzy Systems
Short Types Question Bank
Questions:
a Define Artificial Intelligence. List various applications of Artificial Intelligence.
b Explain McCulloch-Pitts Neuron Model.
c Demonstrate neural network to implement AND gate.
d Define learning rate. What is the use of learning rate?
e Explain why neural network is called as parallel distributed processing.
f Explain perceptron learning rule.
g Explain the characteristics of neural networks.
h Explain Gradient descent learning.
i Explain linear and non-linear problems.
j Explain some application areas of Back Propagation Neural Network.
Answers:
Questions:
a Explain why neural networks are also called as Parallel Distributed Processing?
b Draw 3-4-3-2 feed forward neural network.
c Write the applications of artificial neural network.
d If the net input to an output neuron is 0.64, compute its output when the activation function
is binary sigmoidal.
e Differentiate crisp and fuzzy set.
f Draw fuzzy membership function to describe young, middle and old age.
g Compute cardinality and compliment of fuzzy set defined as:
A = {(x, 0.2), (y, 0.9), (z, 0.7)}
h Compute the Height of following fuzzy set A = {(x1, 0.2), (x2, 0.7), (x3, 0.4)}
i Define the L-R type Fuzzy numbers.
j Define fuzzy neurons.
Answers:
Q1. Write the range of application of artificial neural network?
Artificial neural networks are used for a range of applications, including image recognition, speech
recognition, machine translation, and medical diagnosis. The fact that ANN learns from sample data
sets is a significant advantage. The most typical application of ANN is for random function
approximation.
Q2. What is meant by backpropagation?
Backpropagation, or backward propagation of errors, is an algorithm that is designed to test for
errors working back from output nodes to input nodes. It is an important mathematical tool for
improving the accuracy of predictions in data mining and machine learning.
Q3. What do you mean by activation function?
An activation function is a function used in artificial neural networks which outputs a small value
for small inputs, and a larger value if its inputs exceed a threshold. If the inputs are large enough,
the activation function "fires", otherwise it does nothing.
Q4. What are the tuning parameters for neural network?
The hyper parameters to tune are the number of neurons, activation function, optimizer, learning
rate, batch size, and epochs. The second step is to tune the number of layers. This is what other
conventional algorithms do not have. Different layers can affect the accuracy.
Q5. Why supervised learning is used?
Supervised learning allows collecting data and produces data output from previous experiences.
Helps to optimize performance criteria with the help of experience. Supervised machine learning
helps to solve various types of real-world computation problems.
Q6. What is difference between supervised and unsupervised learning?
In supervised learning, input data is provided to the model along with the output. In unsupervised
learning, only input data is provided to the model. The goal of supervised learning is to train the
model so that it can predict the output when it is given new data.
Q7. What is auto-associative and hetero associative memory?
The difference between auto associative and heteroassociative memories lies in the retrieved
pattern. An auto associative memory retrieves the same pattern Y given an input pattern X, i.e., Y =
X. On the other hand, a heteroassociative memory retrieves the stored pattern Y given an input
pattern X such that Y ¹X
Q8. What is application of fuzzy set?
Applications of fuzzy technology can be found in artificial intelligence, computer science, control
engineering, decision theory, expert systems, logic, management science, operations research,
robotics, and others.
Q9. What is universal set in fuzzy set?
An universal set X is defined in the universe of discourse and it includes all possible elements
related with the given problem. If we define a set A in the universal set X, we see the following
relationships A X. In this case, we say a set A is included in the universal set X.
Q10. Which of the following is linguistic variable?
Linguistic variables are variables with a value made up of linguistic concepts (also known as linguistic
words) rather than numbers, such as child, young, and so on.
Q11. Why is fuzzy logic used?
Fuzzy logic allows for the inclusion of vague human assessments in computing problems. Also, it
provides an effective means for conflict resolution of multiple criteria and better assessment of
options.
Q12. Describe the difference between fuzzy and crisp set.
Crisp set defines the value is either 0 or 1. It is also called a classical set.
Fuzzy set defines the value between 0 and 1 including both 0 and 1. It specifies the degree to
which something is true
Q13. What is Fuzzy Inference System and How it works?
Fuzzy inference system is key component of any fuzzy logic system. It uses fuzzy set theory, IF-
THEN rules and fuzzy reasoning process to find the output corresponding to crisp inputs.
Predicates in IF-THEN rules are connected using and or logical connectives.
Q14. What is crisp and fuzzy relation?
A Crisp relation represents presence or absence of association, interaction or interconnection
between elements of ≥ 2 sets. This concept can be generalized to various degrees or strengths of
association or interaction between elements. A fuzzy relation generalizes these degrees to
membership grades.
Q15. What is alpha cut and strong alpha cut?
Q16.
what does fuzzy controller explain with example.
Almost all the consumer products have fuzzy control. Some of the examples include controlling your
room temperature with the help of air-conditioner, anti-braking system used in vehicles, control
on traffic lights, washing machines, large economic systems, etc.
Q17. Q18.