Class 10 - Artificial Intelligence (417)

AI Project Cycle Test - 04

1. In which rule-based approach, the relationship in the data is defined

a) Machine
b) Developer
c) Output layer network
d) Data set
2. A process has the following features:
i. It is the process of creating a model to predict continuous quantity.
ii. It predicts ordered data.
iii. It may be evaluated using root mean square error.
The process is:
a) Regression
b) Classification
c) Decision tree
d) System map
3. In the Rule-Based Approach, who defines the relationships in patterns or data?
a) Computer Owner
b) Buddy
c) User
d) Coder/Programmer
4. is not included in sustainable development.
a. Recycling and reuse of waste products/materials,
b. Promoting deforestation
c. Promoting green grassy patches between concrete buildings,
d. Scientific management of renewable resources, especially bio-resources,
5. How many AI systems we have in different AI models.
a) 4
b) 3
c) 2
d) 9
6. Name the 4Ws of problem canvases under the problem-scoping stage of the AI Project Cycle.
7. Define data analysis.
8. How many stages are there in an Al-project cycle?
9. What are the other names given for web scraping?
10. What is data cleaning? Why is it required?
11. Explain Reinforced Learning.
12. Mention two precautions to be taken while acquiring data for developing an AI Project.
13. Explain the Learning-based Approach with the help of a suitable example.
14. Explain the AI Project Cycle with details.
15. Explain Supervised Learning with a suitable example.

1/3
 Class 10 - Artificial Intelligence (417)
AI Project Cycle Test - 04

Solution

1. (b) Developer
Explanation: Developer
2. (a) Regression
Explanation: Regression
3. (d) Coder/Programmer
Explanation: Coder/Programmer
4. (b) Promoting deforestation
Explanation: Promoting deforestation
5. (b) 3
Explanation: 3
6. i. Who
ii. What
iii. Where
iv. Why
7. Data analysis means a process of cleaning, transforming, and modelling data to discover useful information for business
decision-making.
8. Five stages.
9. Web data extraction, web harvesting and Screen Scraping.
10. Data cleaning or data cleansing and data scrubbing is the process of removing incorrect, corrupted, incorrectly formatted,
duplicate, or incomplete data within a dataset. This is required to create a culture around quality data decision-making.
11. In reinforcement learning, the ability of an agent to interact with the environment is checked to find out the best outcome.
Reinforcement learning is defined as Machine Learning that is associated with how software agents should take actions in an
environment. It is a part of the deep learning method. It is a kind of hit and trial method, where the agent is rewarded or
penalised with a point for a correct or a wrong answer; on the basis of the positive reward points gained, the model trains
itself. After the training, it gets ready to predict the new data fed into the machine.
12. i. It should be from an authentic source and accurate.
ii. Look for redundant and irrelevant data parameters that do not take part in prediction.
13. In the Learning-based Approach, the AI model gets trained on the data fed to it, and then a model is designed, which is
adaptive to the change in data. Thus, when the model is trained with X type of data, and the machine designs the algorithm
around it, then the model would modify itself according to the changes which occur in the data to handle all the exceptions
in this case.
Example: Suppose we have a dataset comprising 200 images of pineapples and mangoes each. These images depict
pineapples and mangoes in various shapes and sizes. These images are then labeled as either apple or banana so that all
apple images are labeled pineapple,' and all the mango images have 'mango' as their label. Then, the AI model is trained
with this Dataset and the model is programmed in such a way so that it can distinguish between a pineapple image and a
mango image according to their features. And it can predict the label of any image which is fed to it as pineapple or mango.
After training, when the machine is fed with testing data, then the testing data might not have similar images to the ones on
which the model has been trained. Hence, the model adapts to the features on which it has been trained and accordingly, it
predicts if the image is of pineapple or mango. In this way, the machine learns by itself by adapting to the new data which is

2/3
 flowing in. This is the learning-based Approach introducing the dynamicity in the model. The learning-based approach can
further be divided into three parts: Supervised Learning, Unsupervised Learning and Reinforced Learning.
14. The steps involved in the AI project cycle are as given:
The first step is to Scope the Problem by which we set the goal for our AI project by stating the problem which we wish to
solve with it. Under problem scoping, we should look at various parameters which may affect the problem to be solved.
The next step is to acquire data that will become the base of your project as it will help you in understanding the parameters
that are related to problem scoping.
Next, we go for data acquisition by collecting data from various reliable and authentic sources. Since the data we collect
would be in large quantities, we can try to give it a visual image using different types of representations like graphs,
databases, flow charts, maps, etc. This makes it easier for us to interpret the patterns in which our acquired data follows.
After exploring the patterns, we can decide upon the type of model we would build to achieve the goal. For this, we can
research online and select various models which give a suitable output.
We can test the selected models to find out the most efficient one.
The most efficient model is now the base of our AI project, and you can develop your algorithm around it.
Once the modelling is complete, we need to test the model on some newly fetched data. Tie results will help us in evaluating
the model and hence improving it. Finally, after Evaluation, the project cycle is complete and we get our AI project.
15. In a normal classroom, supervised Learning occurs in the presence of a supervisor like a teacher. But in the case of a
machine, supervised Learning is a learning in which the machine is trained by using data that is well labeled. It means that
some data is already labeled with the correct answer. Later for training purposes, the machine is provided with a new dataset
so that the supervised learning algorithm can analyze the training data and produces a correct outcome from labeled data.
Therefore, in a supervised learning model, the Dataset which is fed to the machine is labeled. A label is some information
that can be used as a tag for data.
Example: students get grades as per the marks secured in the examinations. These grades are labels that categorise the
students according to their marks. There are two types of Supervised Learning models:
a. Classification: In Classification, the data is classified according to the labels. Classification is defined as the process of
finding/ discovering a model (function), which helps in separating the data into multiple categories/classes. In
Classification, the data is categorised under different labels according to some parameters and then, the labels are
predicted for the data. This model works on a discrete dataset. It means the data fed in the machine need not be
continuous. A classification problem will be when the output variable is a category, such as "Green or "Red," "disease"
and "no disease," "spam" or "no-spam" in email, etc. Example: In the grading system, the students are classified based
on the grades they obtain with respect to their marks in the annual examination.
b. Regression: Regression is defined as the process of finding a model/function for distinguishing the data into continuous
real values in place classes. Mathematically, one is trying to find the function approximation with the minimum error
deviation in a regression problem. In regression, the numeric data dependency is predicted to distinguish it.
The Regression analysis is the statistical model that is used to predict the numeric data instead of labels. Regression can
also identify the distribution movement depending on the available data or historical data. A regression problem will be
when the output variable is a real value, such as "dollars" or weight. Such models work on continuous data.
Consider this example: when we want to predict our next salary, then we have to put in the data of our previous
salaries, all increments, etc., and would train the model. Here, the continuous data which has been fed to the machine is
continuous.