These Class 12 AI Important Questions Chapter 1 Capstone Project Class 12 Important Questions and Answers NCERT Solutions Pdf help in building a strong foundation in artificial intelligence.
Capstone Project Class 12 Important Questions
Class 12 AI Capstone Project Important Questions
Important Questions of Capstone Project Class 12 – Class 12 Capstone Project Important Questions
Capstone Project Class 12 Very Short Answer Type Questions
Question 1.
What is capstope project?
Answer:
It is a project made by students by researching a real life topic/problem and to find it solution independently with a deep understanding of the subject matter. In this project student integrate all their learning’s or knowledge and demonstrate in the form of comprehensive project.
Question 2.
Give Examples of capstone project in AI
Answer:
- Some of the capstone project ideas are:
- Stock prices predictor
- Develop a sentiment analyzer
- Fraud detection using machine learning
- Brain tumor detection
- Students results predictor
Question 3.
What are the questions category that are asked under the umbrella of predictive analysis?
Answer:
- Which category? (classification)
- How much or how many? (Regression)
- Which group? (Clustering)
- Is this unusual? (Anomaly detection)
- Which option should be taken? (Recommendation)
Question 4.
What is designing thinking
Answer:
It is a design methodology that provides a solution based approach to solve problems.
Question 5.
Write the stages involved in design thinking?
Answer:
Design thinking involves five stages.
Empathize-Conduct research (interviews, polls, etc) to better understand your users.
Define-Define the challenges, use your research to observe users current problems. Create a point of view.
Ideate-Brainstq̣m to arrive at various creative solutions.
Prototype-Build representations (charts, models) of one or more ideas.
Test- Test your model(s) and gain user feedback.
Question 6.
Given below a Airline passengers dataset describing the total number of passengers over a period of time, in a CSV format. Write the python code to a draw a line plot or a linear trend for this airline passenger’s dataset.
Answer:
The python code is :
from pandas import read_csv
from matplotlib import pyplot
series.plot()
pyplot.show()
Question 7.
What is train test split evaluation?
Answer:
The train test validation method measures the performance of machine algorithms when they need to make predictions on data that was not used to train the model.
Question 8.
What is cross validation procesudure?
Answer:
It is a re-sampling technique to evaluate the machine learning model on the basis of a small sample of data. This process includes only one parameter that specifies the number of groups into which a given data samples should be divided.
Question 9.
What is the ratio of data in training set and test set.
Answer:
Usually the split percentage of the training set and test data set is 80-20%.
Question 10.
What is the difference between train test split and cross validation method.
Answer:
Train test split:
- For large data set a simple train test split is helpful. It works faster
- Train test split procedure relies on only one train-test split.
Cross validation:
- For small data set it is useful
- It allows the model to be trained on multiple train- test split also it performs well on the unseen data.
Question 11.
What is classification?
Answer:
In classification the output predicted is from a set up of finite categorical values.
Examples : A large set of photograph when numbers were handwritten on them, as these numbers can be categorized into one of 0-9 digits so it is a example of classification.
Question 12.
What is regression?
Answer:
Regression is linked with a continuous value for example number of rooms, room size, number of pupil, predicting the price of house.
Question 13.
What is loss function.
Answer:
A loss function is a method used by machine to learn. It also determines the performance of the model. Depending on the type of learning we dealt with loss function is divided into two types. Regression losses and classification losses.
Question 14.
What is (Mean square Error)
Answer: It is the widely used loss function. Mostly used to calculate the models prediction difference and the actual value, square it, and average it across the entire dataset to get the value of MSE. MSE is given by the equation:
Question 15.
Write the formula of Mean Squared Error
Answer:
Question 16.
What is RMSE?
Answer:
It is a method that determines how well a regression lines fits the data points. It can also be considered as the standard deviation in the predicted value and observed value in the regression line.
Question 17.
What is the formula for RMSE?
Answer:
Question 18.
What is cross validation?
Answer:
Machine learning is an iterative process. Cross validation is a Cross-validation is a statistical method used to estimate the performance (or accuracy) of machine learning models.
Question 19.
What is train -test split?
Answer:
The train-test split is a technique for evaluating the performance of a machine learning algorithm. It can be used for classification or regression problems and can be used for any supervised learning algorithm.
Capstone Project Class 12 Short Answer Type Questions
Question 1.
What is (Mean square Error)
Answer:
It is the widely used loss function. Mostly used to calculate the models prediction difference and the actual value, square it, and average it across the entire dataset to get the value of MSE. MSE is given by the equation:
Advantages of MSE: It is useful for ensuring that our trained model does not have any outlier predictions with significant errors because MSE places a higher weight on these errors due to the squaring element of the function.
Disadvantage: If our model makes a single particularly incorrect forecast, the squaring part of the function multiplies the error.
Question 2.
Write the names of sum regression loss function.
Answer:
- Mean Square Error/Quadratic Loss
- Mean Absolute Error
- Huber Loss/ Smooth Mean Absolute Error
- Log Cash Loss
- Quantile Loss
Question 3.
Write the names of sum classification function.
Answer:
- Log Loss
- Focal Loss
- KL divergence/Relative Entropy
- Exponential Loss
- Hinge Loss
Question 4.
What is meant by feedback of model effectiveness?
Answer:
By compiling data from the deployed model, the organisation gets feedback on the model’s efficacy and effect on the environment in which it was deployed. Data scientists analyse the feedback to increase the model’s usefulness and accuracy. To expedite the model refresh procedure and enhance outcomes, they can automate any or all of the feedback gathering, model assessment, refining, and redeployment steps.
Question 5.
Differentiate between training set and test set.
Answer:
A training set is a set of historical data in which the outcomes are already known. Train Dataset: Used to fit the machine learning model. Test Dataset: Used to evaluate the fit machine learning model.
Question 6.
What is training data set?
Answer:
The procedure involves taking a dataset and dividing it into two subsets. The first subset is used to fit the model and is referred to as the training dataset. The second subset is not used to train the model; instead, the input element of the dataset is provided to the model, then predictions are made and compared to the expected values. This second dataset is referred to as the test dataset.
Capstone Project Class 12 Long Answer Type Questions
Question 1.
Given below four graphs pick analytical approach based on the type of questions asked
A-Which of the graph is used for statistical analysis?
B-Which of the graph is showing current status?
C-Which of the graph is used for predictive forecasting?
D- Which of the graph is used for probability of the action?
Answer:
A-The second graph shows statistical analysis that is what happened, why is this happening?
B-The first graph shows the current status or descriptive status of a question.
C-The third graph shows predictive forecasting that is what will happen next or what if the trend will continue type of questions.
D-The four graph is used to determine the probability of action for this the predictive model might be used.
Question 2.
Consider the following data
Regression Equation: 0.7 x+17.8
Calculate the RMSE (Root means Square Error) for the above data.
Answer:
Let’s calculate the predicted value of y first, using the regression equation.
Regression Equation: 0.7 x+17.8
Thus, the answer of RMSE is 3.836
Question 3.
Explain the cross-validation procedure.
Answer:
A resampling approach called cross-validation is used to assess machine learning models on a small sample of data. The technique only has one parameter, k, which determines how many groups should be formed from a given data sample. It is a common approach because it is simple to understand and generates a less biassed or optimistic assessment of model competency than other approaches, including a plain train/test split. The general process is as follows.
- Randomly shuffle the dataset.
- Organize the data into k groups.
- For each district group:
- As a test data set, take a group.
- For training data set, use the remaining groupings.
- Fit the model to the training set and evaluate it against the test set.
- Keep the evaluation score but toss out the model.
- Using the sample of model evaluation scores, summarise the model’s ability
Question 4.
Find the MSE of the following data, if the regression equation is:o. 8 x+18.9 :
Calculate the RMSE(Root means Square Error) for the above data.
Answer:
Considering the above data, first calculate its predicted value,predicted-observe5d value.
Regression Equation: 0.8x + 18.9
Here, the formula of RMSE is
Putting the values on the above formula, we get RMSE
= \(\sqrt{\frac{248.05}{5}}\) = 7.043
Question 5.
Consider the given data points: (1,1),(2,1),(3,2),(4,2),(5,4) and Regression line equation is: Y=0.7 X – o.1. Calculate its RMSE value, write the Python program for doing so, also draw its graph.
Answer:
Regression line equation: Y=0.7 X-0.1
MSE=1.14/5=0.2
Python Program
from sklearn.metrics import mean_squared_error
# Given values
Y_true = [1,1,2,2,4] # Y_true = Y (original values)
X_true=[1,2,3,4,5] #X_true=X(original values)
# calculated values
for i in range(0,5):
Y_pred[i]=0.7*X_ _true[i]-0.1
print(Y_pred[i])
# Calculation of Mean Squared Error (MSE)
print(“MSE value is”)
print(mean_squared_error(Y_true,Y_pred))
import matplotlib.pyplot as plt
plt.scatter(X_true, Y_true, Y_pred) # Plot the chart
plt.show() # display
Output:
Graph
Question 4.
Explain the Cross Validation Procedure? In which situation is it better than a Train Test Split?
Answer:
We use cross-validation to obtain numerous metrics of model quality by running our modelling procedure on various subsets of the data.
The original dataset is evenly divided into k subparts or folds for k -fold cross-validation. For each iteration, one group from the k -folds is chosen as the test data, and the remaining (k-1 ) groups are chosen as the training data. K times of this process are carried out. By using the mean accuracy, the model’s final accuracy is calculated.
Cross-validation should be used when the dataset is smaller for greater accuracy.
Question 5.
Find the MSE of the following data, if the regression equation is: 0.8 x+18.9 :
Calculate the RMSE(Root means Square Error) for the above data.
Answer:
Considering the above data, first calculate its predicted value, predicted-observe value.
Regression Equation: 0.8 x + 18.9
Here, the formula of RMSE is
Putting the values on the above formula, we get RMSE
= \(\sqrt{\frac{248.05}{5}}\) = 7.043
Thus answer is 7.043
Competency based questions
The post Capstone Project Class 12 Questions and Answers appeared first on Learn CBSE.