Scribd
Upload
860 views1 page

Revision Worksheet-Assignment - I (Term Ii) Class - Ix Subect - Artificial Intelligence

The document is a revision worksheet for an Artificial Intelligence class assignment. It contains 10 questions defining and explaining key concepts in artificial neural networks, including: 1) supervised and unsupervised learning, activation functions, input/hidden/output layers; 2) applications of neural networks; 3) backpropagation and its benefits; 4) calculating the output of a simple neural model. It asks students to define additional concepts like perceptrons and loss functions, and explain features like activation functions, linearly separable values, and the role of data features in artificial neural networks.

Uploaded by

Atharva Varshney
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
860 views1 page

Revision Worksheet-Assignment - I (Term Ii) Class - Ix Subect - Artificial Intelligence

The document is a revision worksheet for an Artificial Intelligence class assignment. It contains 10 questions defining and explaining key concepts in artificial neural networks, including: 1) supervised and unsupervised learning, activation functions, input/hidden/output layers; 2) applications of neural networks; 3) backpropagation and its benefits; 4) calculating the output of a simple neural model. It asks students to define additional concepts like perceptrons and loss functions, and explain features like activation functions, linearly separable values, and the role of data features in artificial neural networks.

Uploaded by

Atharva Varshney
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

REVISION WORKSHEET- ASSIGNMENT – I ( TERM II)

CLASS – IX

SUBECT – ARTIFICIAL INTELLIGENCE

Q1. Define the following :

1. Supervised Learning

2. Unsupervised Learning

3. Reinforcement Learning

4. Activation function
this is a value decided by the
5. Summation Function user according to the complexity
of the user. It can be in the form
6. Threshold value of decimals.

7. Input, hidden and output layer

8. Conventional Computing It is a type of computing we use now a days it


is different from ANN as it is deterministic in
9. Artificial Neural Network nature
10. Weight

Q2. Mention few applications of Neural Network in daily life.

Q3. Define Backpropagation and its benefits.

Q4. Assume a simple Neural Model with 3 neurons having weights 4,2 and 6. The inputs are
1,2 and 3 respectively. Assume the Activation Function is a linear constant value of 5.
What will be the output?

Q5. The number of nodes in an Input layer are 6 and hidden layer is 8 . Find out the
maximum number of connections from the input layer to the hidden layer.

Q6. Define the term perceptron and limitation of it.

Q7. What is the significance of Loss Function in ANN.

Q8. Name some Activation Functions used in ANN. Tanh function


maxout functions
Q9. Explain the term Linearly Separable Values in reference to an ANN model.

Q10. What is the role of data features in an ANN.

You might also like