Probability & Statistics (PCCAIML 501)

Choose a study mode

Play Quiz
Study Flashcards
Spaced Repetition
Chat to Lesson

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

What is a defining characteristic of a microkernel operating system?

  • It only supports one application at a time.
  • It includes most services in the kernel space.
  • It is designed for real-time processing exclusively.
  • It minimizes the functions in the kernel space. (correct)

Which scheduling algorithm is characterized as pre-emptive?

  • Shortest Remaining Time First (SRTF) (correct)
  • Shortest Job First (SJF)
  • Round Robin (RR) (correct)
  • First-Come, First-Served (FCFS)

In process management, what is a Process Control Block (PCB) primarily used for?

  • To track memory allocation.
  • To store data permanently.
  • To manage the CPU state.
  • To maintain information about processes. (correct)

Which of the following is not a criterion for scheduling algorithms?

<p>Memory allocation (C)</p> Signup and view all the answers

Which concept refers to a situation where multiple processes access a shared resource and manipulate it simultaneously, leading to data inconsistency?

<p>Race condition (C)</p> Signup and view all the answers

What is the primary function of semaphores in inter-process communication?

<p>To control access to shared resources. (A)</p> Signup and view all the answers

Which operating system structure is most rigid and lacks modularity?

<p>Monolithic Operating System (C)</p> Signup and view all the answers

In context switching, what happens to the current process?

<p>Its state is saved into the PCB. (D)</p> Signup and view all the answers

Which of the following correctly describes a zombie process?

<p>A process that has completed execution but still has an entry in the process table. (A)</p> Signup and view all the answers

Which semaphore functions are commonly used for signaling between processes?

<p>semaphore_wait and semaphore_signal (C)</p> Signup and view all the answers

What is the purpose of the pthread_join function in POSIX Threads?

<p>To wait for a thread to finish execution. (D)</p> Signup and view all the answers

Which of the following describes message passing in inter-process communication?

<p>Data is transferred between processes through queues or buffers. (A)</p> Signup and view all the answers

In object-oriented programming, what defines encapsulation?

<p>The process of hiding the internal state of an object. (A)</p> Signup and view all the answers

Which programming function is used to create a pipe for inter-process communication?

<p>pipe (A)</p> Signup and view all the answers

What key feature distinguishes polymorphism in object-oriented programming?

<p>The ability of different objects to be accessed through the same interface. (C)</p> Signup and view all the answers

What is the primary purpose of implementing Bagging using Random Forests?

<p>To improve accuracy by combining multiple base learners. (D)</p> Signup and view all the answers

Which of the following statements is NOT a feature of object-oriented programming?

<p>Global variables (C)</p> Signup and view all the answers

K-means clustering is best used for which of the following tasks?

<p>Identifying natural patterns in numerical data. (B)</p> Signup and view all the answers

Which statement accurately describes Gaussian Mixture Model (GMM)?

<p>GMM assumes that the data comes from a mixture of several Gaussian distributions. (B)</p> Signup and view all the answers

What is the main advantage of using Association Rule Mining with FP Growth?

<p>It generates frequent itemsets without candidate generation. (A)</p> Signup and view all the answers

When comparing machine learning algorithms, which factor is crucial?

<p>The algorithm's performance on balanced and unbalanced datasets. (A)</p> Signup and view all the answers

What is the role of the k-nearest neighbor algorithm in machine learning?

<p>To classify data points based on proximity to labeled examples. (A)</p> Signup and view all the answers

Which clustering method is best suited for categorical data?

<p>K-mode clustering. (C)</p> Signup and view all the answers

What is a key characteristic of evaluating ML algorithms with unbalanced datasets?

<p>It can lead to skewed performance metrics. (A)</p> Signup and view all the answers

What are the six stages of the lifecycle management of cloud services?

<p>Planning, Deployment, Monitoring, Maintenance, Scaling, Retirement (D)</p> Signup and view all the answers

Which aspect is NOT a concern related to cloud security?

<p>Financial audits of cloud services (C)</p> Signup and view all the answers

What does Service Oriented Architecture (SOA) primarily utilize for transactions?

<p>Message-based transactions (D)</p> Signup and view all the answers

Which of the following options correctly describes cloud storage?

<p>Storage defined by manned and unmanned options (B)</p> Signup and view all the answers

What is one of the key features of cloud management systems?

<p>Monitoring of entire cloud computing deployment stacks (A)</p> Signup and view all the answers

Which protocol stack is involved in an Event-driven Service Oriented Architecture?

<p>SOAP, REST, and WebSockets (C)</p> Signup and view all the answers

Which one of the following is a characteristic of cloud APIs?

<p>Facilitates cross-platform integrations (A)</p> Signup and view all the answers

What is the function of syndication services in webmail?

<p>Aggregating content from various feeds (D)</p> Signup and view all the answers

What is a primary focus of non-metric methods in pattern classification?

<p>Nominal data handling (D)</p> Signup and view all the answers

Which of the following is NOT an algorithm used for clustering?

<p>Decision Trees (A)</p> Signup and view all the answers

What does unsupervised learning primarily involve?

<p>Finding hidden patterns in unlabelled data (B)</p> Signup and view all the answers

What is the objective of learning about vertex coloring in graph theory?

<p>Assigning colors to vertices such that no two adjacent vertices share the same color (A)</p> Signup and view all the answers

Which of the following concepts is NOT covered under the basics of graph theory?

<p>Grouping algorithms (A)</p> Signup and view all the answers

In the context of clustering, what do criterion functions do?

<p>Measure the quality of different clustering techniques (B)</p> Signup and view all the answers

What is the primary purpose of set covering in graph theory?

<p>To cover all elements in a set with the least number of subsets (B)</p> Signup and view all the answers

What is the relation between K-means clustering and the properties of the data?

<p>K-means is sensitive to the initial placement of centroids (B)</p> Signup and view all the answers

What does the chromatic number of a graph represent?

<p>The minimum number of colors needed to color the graph such that no two adjacent vertices share the same color (B)</p> Signup and view all the answers

Which theorem pertains to the coloring of chordal graphs?

<p>Brooks' theorem (C)</p> Signup and view all the answers

In which type of graph is edge-coloring specifically relevant?

<p>Bipartite graphs (B)</p> Signup and view all the answers

What characteristic distinguishes Class-1 graphs from Class-2 graphs?

<p>Class-1 has a chromatic index equal to its maximum degree (A)</p> Signup and view all the answers

What does the Greedy coloring algorithm aim to achieve?

<p>Minimizes the total number of colors used for coloring (A)</p> Signup and view all the answers

Which kind of networks does Maarten van Steen's book focus on?

<p>Complex networks (C)</p> Signup and view all the answers

What is the primary focus of the Gupta-Vizing theorem?

<p>Classifying edge-coloring in bipartite graphs (D)</p> Signup and view all the answers

What can Mycielski's theorem help to construct?

<p>New graphs with higher chromatic numbers from existing graphs (D)</p> Signup and view all the answers

Flashcards

System Calls

The basic building blocks of an operating system, these routines provide access to system resources like memory, files, and peripherals.

Context switching

A way to run multiple programs or tasks concurrently on a single processor. It gives the illusion of multitasking by quickly switching between different processes.

Mutual Exclusion

A fundamental principle of operating systems that prevents multiple processes from interfering with each other's critical data. It ensures that shared data is accessed and modified in a controlled manner.

Dining Philosophers Problem

A classic problem used to illustrate the complexities of inter-process communication, where multiple philosophers try to eat from bowls of noodles but need to share chopsticks to do so.

Signup and view all the flashcards

Semaphores

A common approach to handling concurrent access to shared resources. It provides a mechanism to protect critical sections and ensure that only one process can enter at a time.

Signup and view all the flashcards

Layered Operating System

A type of operating system structure where components are organized in layers, with each layer building upon the one below. This modular approach promotes maintainability and code reuse.

Signup and view all the flashcards

Threads

A mechanism that allows a single process to appear as multiple independent processes. It helps improve efficiency by utilizing the CPU more effectively.

Signup and view all the flashcards

Process States

The various states a process can be in, including running, waiting, ready, and terminated. Transitions between these states are governed by the operating system.

Signup and view all the flashcards

Abstract Data Type (ADT)

Represents a collection of data elements in a logical and structured manner, allowing for efficient manipulation and access.

Signup and view all the flashcards

Encapsulation

The ability to hide implementation details of an object, exposing only essential functionalities.

Signup and view all the flashcards

Polymorphism

The ability of an object to take on multiple forms or behaviors based on the context.

Signup and view all the flashcards

Inheritance

The mechanism for creating new classes based on existing ones, inheriting properties and methods.

Signup and view all the flashcards

Design Patterns

Reusable solutions to common design problems, promoting code reusability and consistency.

Signup and view all the flashcards

Object Identity

The capacity for an object to be uniquely identified, even if its state might be the same as another object.

Signup and view all the flashcards

Concrete Invariant

A function that governs the state of an object, ensuring it remains valid within its defined constraints.

Signup and view all the flashcards

Abstraction Function

A function that maps an object's abstract representation to its concrete implementation.

Signup and view all the flashcards

System Concept

A structured way of organizing and representing information, with a focus on relationships between elements. It includes components, boundaries, and interactions within a system.

Signup and view all the flashcards

Management Definition

A set of actions designed to achieve a specific goal, usually involving planning, organizing, leading, and controlling resources.

Signup and view all the flashcards

Management Functions

The functions of management include setting goals, analyzing situations, making decisions, implementing plans, and monitoring progress.

Signup and view all the flashcards

Bagging

Bagging (Bootstrap Aggregating) is a machine learning technique that combines multiple decision trees to improve prediction accuracy. It reduces variance and overfitting by averaging individual tree predictions.

Signup and view all the flashcards

K-Means Clustering

An unsupervised learning algorithm used for grouping data points into clusters based on their similarities. It identifies 'natural patterns' in data by minimizing the distance between points within a cluster and maximizing the distance between clusters.

Signup and view all the flashcards

Hierarchical Clustering

A hierarchical clustering method that builds a dendrogram by iteratively merging clusters based on their similarity. It uses a distance metric to determine the closeness of clusters.

Signup and view all the flashcards

K-Modes Clustering

A clustering technique specifically designed for categorical data. It uses the concept of frequency of categorical values to form clusters. K-Modes is similar to K-Means but for categorical variables.

Signup and view all the flashcards

Association Rule Mining using FP-Growth

A technique for discovering association rules (relationships) within data. It uses the FP-Growth algorithm to efficiently find frequent itemsets and their associated patterns.

Signup and view all the flashcards

Cloud Computing

A way of managing and delivering IT services, such as storage, computing power, and networking, over the internet instead of on physical hardware.

Signup and view all the flashcards

Cloud Management

A collection of technologies and services that enable businesses to manage their cloud infrastructure effectively. It involves tasks like resource allocation, security, monitoring, and cost optimization.

Signup and view all the flashcards

Service Oriented Architecture (SOA)

A type of program architecture where services are broken down into smaller components that communicate with each other through messages. It allows for faster development and easier maintenance.

Signup and view all the flashcards

Enterprise Service Bus (ESB)

A platform that helps connect different services and applications within an SOA. It provides a central bus for messages and communication.

Signup and view all the flashcards

Cloud-based Storage

A type of cloud storage where data can be accessed and stored online, without the need for physical servers. It is typically managed by a third-party provider.

Signup and view all the flashcards

Manned Cloud storage

A type of storage where data is stored and managed physically within a data center, requiring human intervention for its maintenance.

Signup and view all the flashcards

Unmanned cloud storage

A type of storage where data is stored and managed automatically by machines without human intervention. This allows for greater efficiency and scalability.

Signup and view all the flashcards

Cloud Mail Services

Email services that are hosted online and accessible from anywhere with an internet connection, such as Gmail, Hotmail, and Yahoo Mail.

Signup and view all the flashcards

Non-numeric data

Data that doesn't have numerical values, like categories or labels. Think of it like descriptive information.

Signup and view all the flashcards

Decision trees

A flowchart-like structure used to make decisions based on data. It helps predict an outcome by asking a series of yes/no questions.

Signup and view all the flashcards

Unsupervised learning

Finding patterns and grouping similar data without any pre-defined labels. It's like sorting objects into piles based on their similarities.

Signup and view all the flashcards

Criterion functions for clustering

A function that measures how good a cluster is based on how similar items within a cluster are. It's like a scorecard for cluster quality.

Signup and view all the flashcards

Algorithms for clustering

Popular algorithms used for unsupervised learning. K-means divides data into K clusters, while hierarchical methods create a tree-like structure of clusters.

Signup and view all the flashcards

Graph theory

The study of graphs (networks of nodes and edges) with applications in various fields like computer science, social networks, and logistics.

Signup and view all the flashcards

Cycle in a graph

A sequence of nodes in a graph that visits each node exactly once, creating a closed loop.

Signup and view all the flashcards

Shortest path problem

Finding the shortest path between two points in a graph, like finding the most efficient route on a map.

Signup and view all the flashcards

Chromatic Number

The minimum number of colors needed to color the vertices of a graph so that no two adjacent vertices have the same color.

Signup and view all the flashcards

Clique

A complete subgraph within a larger graph.

Signup and view all the flashcards

Chordal Graph

A graph where every cycle has an edge connecting non-adjacent vertices within the cycle.

Signup and view all the flashcards

Greedy Coloring Algorithm

A graph coloring algorithm where each vertex is assigned the lowest available color, starting from an arbitrary vertex.

Signup and view all the flashcards

Brooks' Theorem

A theorem stating that the chromatic number of a graph is at most one more than the maximum degree of any vertex in the graph, except for complete graphs and odd cycles.

Signup and view all the flashcards

Edge Colorings

An assignment of colors to the edges of a graph so that no two adjacent edges have the same color.

Signup and view all the flashcards

Gupta-Vizing Theorem

A theorem stating that the chromatic index of a graph (minimum number of colors for edges) is either equal to the maximum degree of any vertex or one more than the maximum degree.

Signup and view all the flashcards

Class-1 Graph

A graph where the maximum degree of any vertex is equal to the chromatic index (minimum number of colors for edges).

Signup and view all the flashcards

Study Notes

Probability & Statistics (PCCAIML 501)

  • Course Semester: V
  • Maximum Marks: 100
  • Examination Scheme:
    • End Semester Exam: 70 marks
    • Attendance: 5 marks
    • Continuous Assessment: 25 marks
  • Teaching Scheme: 3 hours/week theory
  • Course Aim: Equip students with standard concepts and tools in probability and statistics to tackle problems in the discipline.
  • Course Objective: Familiarize students with statistical techniques. Students should demonstrate understanding of probability & statistics by learning:
    • Probability and random variables (discrete and continuous) and their properties
    • Basic ideas of statistics (central tendency, correlation, regression)
    • Statistical methods for studying data samples

Object Oriented Programming (PCC-CS503)

  • Semester: V
  • Maximum Marks: 100
  • Examination Scheme:
    • Mid Semester Exam: 15 marks
    • Assignment and Quiz: 10 marks
    • Attendance: 5 marks
    • End Semester Exam: 70 marks

Object Oriented Programming Lab (PCC-CS592)

  • Semester: V
  • Maximum Marks: 100
  • Credit Points: 2
  • Teaching Scheme: 4 hours/week

Introduction to Machine Learning (PCCAIML 502)

  • Semester: V
  • Maximum Marks: 100
  • Credit Points: 3
  • L: 3, T: 0, P: 0, C: 3
  • Course Objectives: Students will comprehend supervised and unsupervised techniques, differentiate regression/classification/clustering, analyze the performance of various machine learning techniques and select appropriate features.
  • Module 1: Introduction to Machine Learning, Feature Engineering, Learning Paradigm, Generalization of Hypothesis, VC Dimension, PAC Learning, Applications of ML.
  • Module 2: Data Handling and ANN, Feature Selection Mechanisms, Imbalanced Data, Outlier Detection. Artificial Neural Network details including backpropagation.
  • Module 3: ML Models and Evaluation, Regression (Multi-variable Regression, Model evaluation, Least squares regression, Regularization, LASSO), Classification (KNN, Naive Bayes, SVM, Decision Tree). Training and testing classifier models, Cross-validation, Model evaluation (precision, recall, F1-mesure, accuracy, area under curve), Statistical decision theory (discriminant functions, decision surfaces). Models assessment and inference.
  • Module 4: Model Assessment and Inference,Model assessment and Selection Ensemble Learning (Boosting, Bagging). Bayesian Theory, EM Algorithm.
  • Module 5: Hidden Markov Models
  • Module 6: Association Rules
  • Pre-requisites: NIL

Machine Learning Lab (PCCAIML 592)

  • Semester: V
  • Maximum Marks: 100
  • Credit Points: 2
  • Lab Experiments: Implement Decision Tree learning, Logistic Regression, Classification using Multilayer perceptron, Classification using SVM, Implement Adaboost, Implement Bagging(Random forests), Implement K-means Clustering, Implement Hierarchical Clustering, Implement K-mode clustering, Implement Association Rule Mining using FP Growth, Classification based on association rules, Implement Gaussian Mixture Model using the EM algorithm, Evaluating ML algorithm with balanced and unbalanced datasets, Comparison of machine learning algorithms. Implement K-nearest neighbour algorithms.
  • Total Lecture hours: 30 hours

Graph Theory (PECAIML501C)

  • Semester: V
  • Credit Points: 3
  • Teaching Scheme: 3 hours theory/week
  • Aim: Understanding graph theory, paths, walks and cycles, set covering, matching problem, vertex coloring.
  • Module details: 1. Introduction, 2. Connected Graphs & shortest paths, 3. Trees, 4. Independent sets & coverings, 5.Vertex Colouring.

Pattern Recognition (PECAIML501B)

  • Semester: V
  • Credit Points: 3
  • Teaching scheme: 3 hours theory/week
  • Aim: Understand Bayesian decision theory, classifiers, discriminant functions, normal/density/discriminant functions.
  • Module details: basics of pattern recognition, Bayesian decision theory, parameter estimation methods, Hidden Markov Models, dimension reduction methods, non-parametric techniques, linear discriminant function based classifier (Perceptron, Support Vector Machines).

Introduction to Industrial Management (HSMC-501)

  • Semester: V
  • Credit Points: 3
  • Teaching Scheme: 2 hours theory/week
  • Course Objectives: Students should acquire knowledge of the basic principles of industrial management and organizational structure. Topics include definition, types and factors in organization structures, and the concept of division of labor.
  • Module Details: Introduction to Industrial Management; Concepts; types, parameters, variables and behaviour; Management definitions; organizational structure, definitions, goals, factors considered in formulating structure; Types of organizations; Advantages/Disadvantages/Applications; Division of labour, span of control, delegation; Organizational culture and climate; Moral factors; Job satisfaction; Factory acts and labour la

Cloud Computing (PECAIML501A)

  • Semester: V
  • Credit Points: 3
  • Teaching Scheme: 3 hrs./week theory
  • Unit 1: Definition of Cloud computing and its basics (cloud types, deployment types, service models- IaaS, PaaS, SaaS). Cloud Reference Model, Infrastructure, Platforms, Virtual Appliances, Communication Protocols, Application development; Usage of PaaS; Application frameworks; Google applications portfolio.
  • Unit 2: Use of platforms in Cloud computing (Mobility patterns, Load balancing, Application Delivery Controllers and Networks, Hypervisors); Porting of applications into the Cloud;Concepts of Platform as a Service, PaaS, and Distinction between SaaS and PaaS (examples of Salesforce.com and Force.com);
  • Unit 3: Cloud Management: Overview of network management, Lifecycle Management of Cloud services; Concept of Security concerns, Security mapping, data security, storage, and identity management; Cloud Transactions; functionality mapping.
  • Unit 4: Cloud infrastructure; Cloud Management; Concepts of services and applications-Service Oriented Architecture.

Studying That Suits You

Use AI to generate personalized quizzes and flashcards to suit your learning preferences.

Quiz Team

Related Documents

More Like This

Use Quizgecko on...
Browser
Browser