SMART WONDERS SCHOOL

Class 10 (Artificial Intelligence)

1. Define AI Modelling. What are its types?

AI modelling is like teaching a computer to think and make decisions like humans do. Just like we learn from
examples and experiences, AI models learn from data.
There are mainly three types of AI modelling:

1. Supervised Learning: In this, the computer is given labelled data (input and output pairs), and it learns to make
predictions or decisions based on that data. It’s like a teacher guiding the students.

2. Unsupervised Learning: Here, the computer explores data without being told what to look for. It tries to find
patterns or groupings in the data on its own. It's like discovering new things without a guide.

3. Reinforcement Learning: It is used to train the AI model using trial and error method. The model gets rewards
for good actions and penalties for bad ones. Later, it learns to take actions that will lead to the best possible
outcomes and maximize rewards.

2. Define a Neural network.

A neural network is a subfield of AI. It teaches computers to process data in a way that is inspired by the human
brain. It is a type of machine learning process, called deep learning. It uses interconnected nodes or neurons in a
layered structure that resembles the human brain.

3. List some advantages of Neural Networks.

 Can perform parallel processing
 Can learn from training data
 Can effectively learn from incomplete, unorganized data and still give accurate results
 Can adapt to new environments.

4. What’s the purpose of Hidden Layers in a Neural Network?

Between the input and the output layer, there is a set of layers known as Hidden Layers which are not visible to
users. In these layers, computations are performed which lead to generating an output. There can be more or less
hidden layers depending on the complexity of the network.

5. What happens in the Output Layer of a Neural Network?

The inputs given to the Input Layer go through a series of processing in hidden layers that finally results in the
output which is delivered via Output layer. This layer doesn’t process the data. It acts like a user interface with
which the user interacts.

6. Akhil wants to learn how to scope the problem for an AI Project. Explain him the following:
(a) 4W Problem Canvas (b) Problem Statement Template 4 Marks (CBSE Board 2023)
The 4Ws Problem canvas helps in identifying the key elements related to the problem. The 4Ws are Who, What,
Where and Why.
 The “Who” block helps in analyzing the people getting affected directly or indirectly due to the problem.
 The “What” block helps us to determine the nature of the problem.
 The “Where” block helps us to look into the situation in which the problem arises, the context of it, and the
locations where it is prominent.
 The “Why” block suggests to us the benefits which the stakeholders would get from the solution and how it will
benefit them as well as the society.
 SMART WONDERS SCHOOL
Class 10 (Artificial Intelligence)

7. Your grandmother watches you use AI applications. She wants to understand more about it. Help her
understand the term artificial intelligence by giving the right definition and explain to her with an example
how machines become artificially intelligent. 4 Marks (CBSE Board 2023)

When a machine possesses the ability to mimic human traits, i.e., make decisions, predict the future, learn and
improve on its own, it is said to have artificial intelligence. In other words, you can say that a machine is artificially
intelligent when it can accomplish tasks by itself - collect data, understand it, analyse it, learn from it, and improve
it.

Machines become intelligent once they are trained with some data which helps them achieve their tasks. AI
machines also keep updating their knowledge to optimise their output. For example, Netflix gives us
recommendations on the basis of what we like. Whenever we start liking a new genre, it updates and gives better
suggestions.

8. Identify and explain the types of the learning-based approaches in the figures given below.
4 Marks (CBSE Board 2023)
 SMART WONDERS SCHOOL
Class 10 (Artificial Intelligence)

Figure 1: It is a supervised learning model where the dataset which is fed to the machine is labelled. In other
words, we can say that the dataset is known to the person who is training the machine only then he/she is able to
label the data. A label is some information which can be used as a tag for data. Here, labelled images of dog and
cat are fed into the model and trained. So, the model correctly identifies the given input as a dog.

Figure 2: It is an unsupervised learning model that works on an unlabelled dataset. This means that the data which
is fed to the machine is random and there is a possibility that the person who is training the model does not have
any information regarding it. The unsupervised learning models are used to identify relationships, patterns and
trends out of the data which is fed into it. It helps the user in understanding what the data is about and what are the
major features identified by the machine in it. Here, images of a set of animals are fed into the AI model and the
model clusters them based on similar features.

9. Suhana works for a company wherein she was assigned the task of developing a project using AI project
cycle. She knew that the first stage was scoping the problem. Help her list the remaining stages that she
must go through to develop the project. 2 Marks (CBSE Board 2022)

Steps of AI project life cycle:

1. Data Acquisition
2. Data Exploration
3. Modelling
4. Evaluation

10. People of a village are totally dependent on the farmers for their daily food items. Farmers grow new
seeds by checking the weather conditions every year. An AI model is being deployed in the village which
predicts the chances of heavy rain to alert farmers which helps them in doing the farming at the right time.
Which evaluation parameter out of precision, recall and F1 Score is best to evaluate the performance of
this AI model? Explain. 2 marks (CBSE Board 2022)

Let us take each of the factor into consideration at once,

If precision is considered, FN (False Negative) cases will not be taken into account, so it will be of great loss as if
the machine will predict there will be no heavy rain, but if the rain occurred, it will be a big monetary loss due to
damage to crops.
If only recall is considered, then FP (false Positive) cases will not be taken into account. This situation will also
cause a big amount of loss, as all people of the village are dependent on farmers for food, and if the model predicts
there will be heavy rain and the farmers may not grow crops, it will affect the basic needs of the people.

Hence F1 Score is the best suited parameter to test this AI model, which is the balance between Precision and
Recall.

11. “Automatic summarization is used in NLP applications”. Is the given statement correct? Justify your
answer with an example. 2 marks (CBSE Board 2021)
Yes, the given statement is correct. Automatic summarization is relevant not only for summarizing the meaning of
documents and information, but also to understand the emotional meanings within the information, avoid
redundancy (duplicacy) from multiple sources and enhance the diversity of content obtained.
 SMART WONDERS SCHOOL
Class 10 (Artificial Intelligence)

12. What is F1 Score in Evaluation? 2 marks (CBSE Board 2020)

Ans: F1 score can be defined as the measure of balance between precision and recall.

13. Categorize the following under Data Sciences, Machine Learning, Computer Vision and NLP:

The latest technological advancements have made our lives convenient. Google Home, Alexa and Siri have been a
huge help to non-tech savvy people. Features like Facial recognition and Facelock have added additional security
to our gadgets. These advancements have also contributed in making our needs more approachable and
convenient. Now you can even check the prices with Price comparison websites and order groceries online with
chatbots. Did you know that you can even find how you are going to look when you grow old? Faceapps and
Snapchat filters have made this possible!

Alexa, Siri-NLP,
Facial Recognition - Computer Vision
Facelock - Computer Vision
Price comparison websites - Data Sciences
Chatbots - NLP
Faceapps -NLP
Snapchat Filters - Machine Learning