Set – 1

Q.1. Explain the different types of Artificial Intelligence (Reactive Machines, Limited Memory, Theory of Mind, and Self-aware AI). Analyse their capabilities and limitations with suitable examples.

Ans 1.

Types of Artificial Intelligence

Artificial Intelligence Systems are classified as four different types based upon their abilities to think and to understand or think about their environment.

Reactive Machines

Reactive Machines represent the most basic type of AI. These systems process current inputs and create outputs using predetermined rules. They do not have any memory of past interactions.

MUJ

Its Half solved only

Buy Complete assignment from us

Price – 190/  assignment

MUJ Manipal University Complete SolvedAssignments  JAN- FEB  2026

buy cheap assignment help online from us easily

we are here to help you with the best and cheap help

Contact No – 8791514139 (WhatsApp)

OR

Mail us-  bestassignment247@gmail.com

Our website – https://muj.assignmentsupport.in/

JAN-FEB 2026

Q.2. Give the architecture and working of TensorFlow and PyTorch frameworks. Discuss their associated cloud-based deployment tools and their role in scalable model serving.

Ans 2.

TensorFlow: Architecture and Working

TensorFlow is an open source machine-learning framework created by Google Brain and released publicly in the year 2015. The architecture of the framework is built on computational graphs. Nodes represent mathematical operations and edges represent the multidimensional data arrays referred to tensors moving between each other. In TensorFlow 2.x the eager execution

Q.3. Compare and contrast supervised, unsupervised, and reinforcement learning paradigms. Illustrate each with suitable real-world examples and highlight their key differences.

Ans 3.

Supervised Learning

Supervised learning is the process of training models on data labeled and each example of training is paired with a corresponding accurate output. It learns how to convert the inputs into outputs by decreasing the variance between its forecasts and the actual labels. The two main tasks are classification and regression. two main duties. Image classification systems that identify the presence of a pet or a cat are built on millions of labels images. Spam email filters learn from

Set – 2

Q.4. Analyse the role of cloud-based computer vision services in modern applications. How do object detection and image classification techniques improve automation and decision-making?

Ans 4.

Cloud-Based Computer Vision Services

Cloud-based computer vision solutions provide the ability to use ready-to-use AI capabilities to understand visual information using easy API calls. This eliminates the requirement for companies to develop and train their own deep-learning models completely from scratch. Cloud providers that are leading in their field, such as AWS Rekognition, Google Cloud Vision API, and Azure Computer Vision offer a extensive array of computer vision capabilities in managed

Q.5. What are cloud-based Natural Language Processing (NLP) services? Discuss key NLP tasks such as sentiment analysis, named entity recognition, and machine translation, along with their real-world applications.

Ans 5.

Cloud-Based NLP Services

Cloud-based Natural Language Processing (NLP) services are controlled AI products that help applications to understand, interpret and translate human speech via API-based access to pretrained large models of language. The major cloud platforms, including AWS Comprehend, Google Cloud Natural Language API, Azure Cognitive Services Text Analytics, and OpenAI

Q.6. How cloud-based AI pipelines enable efficient development and deployment of machine learning models? Explain each stage of the pipeline with suitable examples.

Ans 6.

Cloud-Based AI Pipelines

Cloud-based AI pipelines are automated end-to-end processes that simplify every step of developing, training reviewing, and deploying model-based learning at a scale. They abstract infrastructure management, ensure reproducibility, enable collaboration among teams, and help speed the transition of raw data into production-ready models. Major cloud providers offer managed pipeline services including Google Vertex AI Pipelines, AWS SageMaker Pipelines,

SET – 1

Q.1(a). Discuss the role of unsupervised learning in modern AI systems. Explain how it contributes to data preprocessing, representation learning, foundation models, reinforcement learning, and autonomous systems. (5 Marks)

Q.1(b). Elaborate on the importance of probability models such as Bayesian inference and Maximum Likelihood Estimation (MLE) in unsupervised learning. (5 Marks)

Ans 1a.

Unsupervised learning is a branch of machine-learning that identifies patterns and patterns in information without the need for specific examples. It is now a fundamental element of modern AI and is contributing to several crucial areas of system development and design.

Contributions to Modern AI

When data processing non-supervised methods like clustering and dimensionality reduction can

MUJ

Its Half solved only

Buy Complete assignment from us

Price – 190/  assignment

MUJ Manipal University Complete SolvedAssignments  JAN- FEB  2026

buy cheap assignment help online from us easily

we are here to help you with the best and cheap help

Contact No – 8791514139 (WhatsApp)

OR

Mail us-  bestassignment247@gmail.com

Our website – https://muj.assignmentsupport.in/

JAN-FEB 2026

Q.2. Compare K-Means, DBSCAN, and Agglomerative Clustering in terms of working principle, assumptions, strengths, and limitations. (10 Marks)

Ans 2.

The task of clustering involves connecting similar data points without the use of predefined labels. In the array of algorithms for clustering developed, K-Means, DBSCAN, and Agglomerative Clustering are among the most widely used. Each operates according to a distinct

Q.3. Explain the concept of density-based clustering and justify why it is suitable for datasets containing noise and outliers. (10 Marks)

Ans 3.

Density-based clustering is a method to grouping data points that describes clusters as zones of high data point density that are separated from areas with lower density. As opposed to other methods that use centroids such as K-Means and other density-based algorithms, these don’t require clusters to have a defined dimension or shape. The most representative algorithm in this class is DBSCAN, which stands for Density-Based Spatial Clustering of Applications with

SET – 2

Q.4. Explain the concept of matrix factorisation and discuss its importance in unsupervised learning. (10 Marks)

Matrix factorisation is an algorithmic technique which breaks down a massive matrix into two or smaller matrices, whose products are similar to the initial. This technique reveals the pattern of the data in a concise and readable shape. In unsupervised learning, the matrix factorization is frequently used to aid in the reduction of dimensionality, feature extraction and

Q.5. Explain the challenges associated with high-dimensional data in unsupervised learning. Discuss techniques such as Dimensionality Reduction (PCA, SVD) and their role in improving clustering performance. Illustrate with suitable examples. (10 Marks)

The term “high-dimensional” refers to data sets where every observation is defined by an enormous number of characteristics or variables. The data naturally arises in text analysis, genomics imaging, as well as sensor networks. While having more features may be appealing, a higher degree of dimensionality creates well-studied problems that significantly impact the performance of unsupervised learning algorithms, particularly clustering.

Challenges of High-Dimensional Data

The root of the issue is known as the curse of dimensions. The more dimensions grows, the size

Q.6. Explain the role of unsupervised learning in cybersecurity and healthcare. Illustrate how anomaly detection and pattern discovery are used for intrusion detection and disease diagnosis. Support your answer with relevant real-world examples and discuss challenges faced in these domains. (10 Marks)

Ans 6.

Unsupervised learning is particularly valuable in areas where labeled data is hard to come by, cost prohibitive to obtain, or where the pattern of interest is continually changing. Healthcare and cybersecurity are two examples of such areas. Both fields are supervised, and unsupervised learning powers anomaly detection and pattern detection that allows the early detection of threats

Assignment Set – 1

Q1. A hospital wants to predict whether a patient will develop diabetes. Identify which type of Machine Learning should be used and justify your answer.

Ans 1.

Identifying the Type of Machine Learning

If a hospital wants to determine whether the patient is likely to develop diabetes or not, Supervised Learning is the best kind of machine learning that they can employ. Particularly, it is an issue of binary classification, which means that the model has to predict either or the patient is likely to develop the disease (positive classification) or the patient will not be diagnosed with the

MUJ

Its Half solved only

Buy Complete assignment from us

Price – 190/  assignment

MUJ Manipal University Complete SolvedAssignments  JAN- FEB  2026

buy cheap assignment help online from us easily

we are here to help you with the best and cheap help

Contact No – 8791514139 (WhatsApp)

OR

Mail us-  bestassignment247@gmail.com

Our website – https://muj.assignmentsupport.in/

JAN-FEB 2026

Q2. An email system needs to classify emails as spam or not spam. Which supervised learning technique would you use and why?

Ans 2.

Problem Overview

The classification of emails as spam or not is an old binary classification issue in machine learning supervised. Email systems already have an extensive collection of email which were previously classified as spam or not by administrators or users. The fact that these historical emails have been labeled makes the decision to use supervised learning a natural one. It is the

Q3. In a cancer detection system, explain why Recall is more important than Accuracy. Support your answer with an example.

Ans 3.

Understanding Accuracy and Recall

Accuracy refers to the percentage of predictions total that are accurate. This can be misleading if the distribution of classes is not balanced which is often the case when it comes to cancer detection data in which healthy people outnumber cancer patients.

Recall, sometimes referred to as sensitive or the true positive rate, is the percentage of positive

Assignment Set – 2

Q4. A company wants to analyze customer reviews from its website. Explain the preprocessing steps required before applying ML.

Ans 4.

Introduction

Reviews of customers are not structured information. Before any machine-learning algorithm is able to analyze sentiment, identify topics, or categorize opinions, the unstructured text has to be cleansed and converted into a structured numeral format. The process of transformation is known

Q5. Explain how an OTT platform recommends movies to users using collaborative filtering. Compare content-based and hybrid recommendation systems using an example

Ans 5.

Collaborative Filtering on OTT Platforms

A OTT (Over-The-Top) service such as Netflix as well as Amazon Prime uses collaborative filtering to suggest movies to users. Collaboration-based filtering is based on the assumption that those who reached an agreement on preferences or ratings previously are more likely to be able to reach a consensus in the near future. The system does not rely on any details about the films themselves (such such as director, genre or casting) however it relies on patterns in user behavior

Q6. A company processes millions of transactions daily. Explain why traditional ML techniques may fail and how Big Data tools help.

Ans 6.

An organization that handles thousands of transactions every day generates an enormous, constant flow of information. Although traditional ML techniques are suitable for smaller to medium-sized data sets that can are able to fit into the memory of one machine however, they are severely limited in big datasets. Knowing these limitations and the ways big data-related tools

Set – 1

Q.1. Explain the evolution and history of Mobile Operating Systems. Discuss the resource constraints in mobile devices and explain how mobile OS manages CPU, memory, and power.

Ans 1.

Evolution and History of Mobile Operating Systems

The story of mobile operating systems starts in the early 1990s when the first personal digital assistants appeared. These early devices ran proprietary software with very limited capabilities. The Nokia communicator model was released in 1996 and is one of the first attempts at creating the smartphone’s look and function featuring a multi-function operating system. Palm OS, launched in 1996, was one of the first popular mobile operating system systems, created

MUJ

Its Half solved only

Buy Complete assignment from us

Price – 190/  assignment

MUJ Manipal University Complete SolvedAssignments  JAN- FEB  2026

buy cheap assignment help online from us easily

we are here to help you with the best and cheap help

Contact No – 8791514139 (WhatsApp)

OR

Mail us-  bestassignment247@gmail.com

Our website – https://muj.assignmentsupport.in/

JAN-FEB 2026

Q.2. Explain the core principles of microkernel architecture. How do these principles enhance system reliability, security, and maintainability?

Ans 2.

Core Principles of Microkernel Architecture

Microkernel architecture is a approach to operating systems that puts the core operations in the kernel. running everything else in user space as separate functions. A microkernel’s fundamentals contains only hardware abstraction the basic scheduling of processes, inter-process communication, and memory protection. File systems, device drivers as well as network stacks

Q.3. Explain the Android Activity Lifecycle. Describe each lifecycle state and callback method with a suitable diagram and its significance in mobile application development.

Ans 3.

Android Activity Lifecycle

The Android Activity Lifecycle is the fundamental idea within Android application development that defines the conditions an Activity goes through from creation to destruction. The understanding of this process will allow developers to create applications that behave correctly, conserve the system’s resources and offer users with a seamless experience during interruptions

Set – 2

Q.4. Explain Role of Layouts in Android UI Design. Discuss the significance of Layout Hierarchy and View Group concepts.

Ans 4.

Role of Layouts in Android UI Design

Layouts form the primary element that form the basis of Android user interface design. Layouts establish the design of an UI screen, by arranging views elements like buttons, text fields pictures, and more widgets in a ViewGroup container. Layouts decide how these elements are positioned, sized and displayed in relation to one another in the screens. If layout management is

Q.5. Explain the intents and broadcasts in IPC of Mobile Communication.

Ans 5.

Inter-Process Communication in Android

Inter-process communication within Android is primarily achieved through Intents and Broadcasts, which provide a flexible and loosely coupled messaging system allowing different application components as well as separate apps to exchange messages using direct method calls

Q.6. Explain Quantum Cryptography. What are Future Prospects of Quantum Cryptography?

Ans 6.

Quantum Cryptography

Quantum cryptography is a technique of protecting communication, which utilizes the basic principles of quantum mechanics to provide theoretically secure encryption. Unlike classical cryptography, which is based on the computational complexity of mathematical problems such as taking large numbers into account quantum cryptography gets its protection by physical laws

Assignment Set – 1

Q.1. (a) Define Artificial Intelligence. Explain its major goals and real-world applications. (b) What are intelligent agents? Classify different types of agents and explain their working with practical examples.

Ans 1.

(a) Artificial Intelligence: Definition, Goals, and Applications

Artificial Intelligence is the branch of computer science concerned with making systems that are able to perform the tasks that usually need human brains. These tasks include reasoning through experience, learning, comprehending language, seeing patterns and making choices. The term was coined by John McCarthy in 1956 at the Dartmouth Conference, and since it was coined, AI

Q.2. (a) Differentiate between propositional logic and first-order logic. Provide suitable problem-based examples. (b) Compare supervised, unsupervised, and reinforcement learning in terms of working principles, use-cases, and limitations.

Ans 2.

(a) Propositional Logic vs First-Order Logic

Propositional logic, also known as zeroth-order logical reasoning, deals with the propositions and statements that can be either true or not. It uses logical connectives like AND, OR, NOT or IF in order to transform simple sentences into complicated ones. As an example, the sentence “It’s

Q.3. (a) What is Natural Language Processing? Explain the roles of syntax, semantics, and pragmatics in NLP. (b) Describe fuzzy sets and fuzzy inference systems. Demonstrate their application using a real-life scenario.

Ans 3.

 (a) Natural Language Processing: Syntax, Semantics, and Pragmatics

Natural Language Processing is a branch of AI that enables computers to understand, interpret, and create human languages. NLP can bridge the gaps between human language and machine understanding. It is a combination of linguistics, computer science, and machine understanding

Assignment Set – 2

Q.4. (a) Explain feature extraction in computer vision. How does it impact model performance? Illustrate with an example. (b) What are heuristic search techniques? Compare any two algorithms based on efficiency and application.

Ans 4.

(a) Feature Extraction in Computer Vision

A process called feature extraction is of extracting and separating the most pertinent information of raw image data, so that a machine learning model can learn patterns effectively. Raw images contain many millions of pixels. Processing them directly is costly computationally and usually

Q.5. (a) Describe the role of sensors and actuators in robotics. (b) Explain Q-learning. How is it used in reinforcement learning?

Ans 5.

(a) Sensors and Actuators in Robotics

The robot communicates with its surroundings through two essential components: sensors, which collect information about the surroundings, and actuators, which let the robot take action in that environment. Together, they make up the perception-action loop that can enable intelligent

Q.6. (a) Discuss major AI applications in business and industry with examples. (b) Discuss ethical challenges in AI systems with respect to bias, fairness, transparency, and privacy.

Ans 6.

(a) AI Applications in Business and Industry

Artificial Intelligence has transformed how companies operate in virtually all industries. For e-commerce and retail, recommendations engines study browsing histories purchases, patterns of purchase, as well as demographic data to suggest products. Amazon’s recommendation engine is