V Semester Diploma Make-Up Examination, July 2024 Artificial Intelligence & Data Science PDF

Summary

This is an Artificial Intelligence and Data Science exam paper for a V Semester Diploma program, covering topics including machine learning, data preprocessing, and collaborative software development. The paper is designed for a 3-hour examination, featuring multiple sections of theoretical and practical problems.

Full Transcript

# V Semester Diploma Make-Up Examination, July 2024 ## ARTIFICIAL INTELLIGENCE & DATA SCIENCE **[Time: 3 Hours]** **[Max_Marks:100]** **Instructions:** (1) Answer one Full question from each Section. ## SECTION - I ### 1. a) Explain how Amazon, Microsoft and I...

# V Semester Diploma Make-Up Examination, July 2024 ## ARTIFICIAL INTELLIGENCE & DATA SCIENCE **[Time: 3 Hours]** **[Max_Marks:100]** **Instructions:** (1) Answer one Full question from each Section. ## SECTION - I ### 1. a) Explain how Amazon, Microsoft and IBM are leveraging artificial intelligence in their business strategies and provide an example of an AI-based application or service from each of these companies. 10 b) Describe the importance of Git branching and merging in collaborative software development and explain the steps to create a repository named "mini-project - 1" on GitHub and push it to the remote repository. 10 ### 2. a) Explain the concept of containers in cloud computing and their significance in modern software development. Describe the key components and advantages of containerization. Provide an example of how containers are used to deploy applications in a cloud environment. 10 b) Analyse different Cloud deployment Model. 10 ## SECTION - II ### 3. a) Create a scatter graph using matplotlib, identify people who as high BP heart rate and low BP heart rate by using data below. | High BP Heart rate | Low BP Heart rate | | --- | --- | | 1 | 1 | | 2.5 | 2 | | 3 | 3 | | 3.7 | 4 | | 4.5 | 2 | | 5 | 1 | | 6.5 | 3 | | 7 | 4 | | 9 | 3 | | 9.5 | 4 | | 10 | 4.5 | | 10.5 | 5 | | 11 | 5.2 | | | | b) Machine learning models can be resource heavy. They require good amount of processing power to predict, validate and recalibrate, millions of times over. How can containerisation of ML model solve this problem? 10 ### 4. a) Given two fair dices thrown, what is the probability that two dices thrown sum is 8? When the first dice is 3? 10 b) If A and B are two events, such that P(A)=1/4, P(A/B)=1/2, P(B|A)=2/3. Find the value of P(B)? 10 ## SECTION - III ### 5. a) Write a python program to find eigen value and eigen vector and how it works. 10 b) Justify and explain briefly Linear Algebra Using Python? 10 ### 6. a) Justify data preprocessing takes place and what are the comman data preprocessing method. 10 b) Describe the steps involved in implementing a Multiple Linear Regression model for predictive analysis. Discuss the assumptions made in Multiple Linear Regression and how to evaluate the model's performance. 10 ## SECTION - IV ### 7. a) Describe the key metrics and techniques used to evaluate a multiple linear regression model. In a practical context, discuss how these metrics can be applied to assess the effectiveness of a real-time housing price prediction model. 10 b) Explain why cross-validation is necessary in the context of machine learning. Provide a code example in Python demonstrating how to perform k-fold cross-validation for model evaluation. 10 ### 8. a) Confusion matrix of a logistic regression is given below, what is the Accuracy, Recall, Precision, Error rate of the model according to the confusion matrix? 10 b) Explain the concept of Decision Trees in machine learning. What are the key characteristics and advantages of using Decision Trees as a predictive modeling technique? Provide a real-world example of a problem where Decision Trees can be applied. 10 ## SECTION - V ### 9. a) NLP is one of the most popular tools in the field of AI. NLP uses Sentiment Analysis, state some advantages and disadvantages of Sentiment Analysis. 10 b) Suppose there is a dataset that contains multiple fruit images. The dataset is divided into subsets and given to each decision tree. During the training phase, each decision tree produces a prediction result, and when a new data point occurs, then based on the produces a prediction result, and when a new data point occurs, then based on the majority of results, model will predict the output. Describe step you will follow to build this model. 10 ### 10. a) How Principal Component Analysis (PCA) is used for Dimensionality Reduction? 10 b) Explain the concept of MLOps in machine learning and its significance in the development and deployment of machine learning models. What are some key components of an MLOps pipeline and how do they contribute to the lifecycle management of machine learning models? Provide an example scenario where MLOps practices can streamline model deployment concept of MLOps. 10

Use Quizgecko on...
Browser
Browser