no longer supports Internet Explorer.

To browse and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

  • We're Hiring!
  • Help Center

paper cover thumbnail

Thesis on Machine Learning Methods and Its Applications

Profile image of IJRASET Publication


In the 1950s, the concept of machine learning was discovered and developed as a subfield of artificial intelligence. However, there were no significant developments or research on it until this decade. Typically, this field of study has developed and expanded since the 1990s. It is a field that will continue to develop in the future due to the difficulty of analysing and processing data as the number of records and documents increases. Due to the increasing data, machine learning focuses on finding the best model for the new data that takes into account all the previous data. Therefore, machine learning research will continue in correlation with this increasing data. This research focuses on the history of machine learning, the methods of machine learning, its applications, and the research that has been conducted on this topic. Our study aims to give researchers a deeper understanding of machine learning, an area of research that is becoming much more popular today, and its applications.

Related Papers

Manisha More

Machine learning is the fastest growing areas of computer science. It has the ability to lets the computer to create the program. It is a subset of Artificial Intelligence (AI), and consists of the more advanced techniques and models that enable computers to figure things out from the data and deliver. It is a field of learning and broadly divided into supervised learning, unsupervised learning, and reinforcement learning. There are many fields where the Machine learning algorithms are used. The objective of the paper is to represent the ML objectives, explore the various ML techniques and algorithms with its applications in the various fields from published papers, workshop materials & material collected from books and material available online on the World Wide Web.

thesis on machine learning pdf

pankaj verma

The field of machine learning is introduced at a conceptual level. The main goal of machine learning is how computers automatically learn without any human invention or assistance so that they can adjust their action accordingly. We are discussing mainly three types of algorithms in machine learning and also discussed ML's features and applications in detail. Supervised ML, In this typeof algorithm, the machine applies what it has learned in its past to new data, in which they use labeled examples, so that they predict future events. Unsupervised ML studies how systems can infer a function, so that they can describe a hidden structure from unlabeled data. Reinforcement ML, is a type of learning method, which interacts with its environment, produces action, as well as discovers errors and rewards.

Journal of Advances in Mathematical & Computational Science. Vol 10, No.3. Pp 1 – 14.

Jerry Sarumi

Machine learning and associated algorithms occupies a pride of place in the execution of automation in the field of computing and its application to addressing contemporary and human-centred problems such as predictions, evaluations, deductions, analytics and analysis. This paper presents types of data and machine learning algorithms in a broader sense. We briefly discuss and explain different machine learning algorithms and real-world application areas based on machine learning. We highlight several research issues and potential future directions

IJESRT Journal

Machine learning [1], a branch of artificial intelligence, that gives computers the ability to learn without being explicitly programmed, means it gives system the ability to learn from data. There are two types of learning techniques: supervised learning and unsupervised learning [2]. This paper summarizes the recent trends of machine learning research.

International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Manish Kumar Singh

Machine learning has become one of the most envisaged areas of research and development field in modern times. But the area of research related to machine learning is not new. The term machine learning was coined by Arthur Samuel in 1952 and since then lots of developments have been made in this field. The data scientists and the machine learning enthusiasts have developed myriad algorithms from time to time to let the benefit of machine learning reach to each and every field of human endeavors. This paper is an effort to put light on some of the most prominent algorithms that have been used in machine learning field on frequent basis since the time of its inception. Further, we will analyze their area of applications.

International Journal of Advanced Technology and Engineering Exploration

Akash Badone

International Journal of Engineering Applied Sciences and Technology

vishal bari

Today, huge amounts of data are available everywhere. Therefore, analyzing this data is very important to derive useful information from it and develop an algorithm based on this analysis. This can be achieved through data mining and machine learning. Machine learning is an essential part of artificial intelligence used to design algorithms based on data trends and past relationships between data. Machine learning is used in a variety of areas such as bioinformatics, intrusion detection, information retrieval, games, marketing, malware detection, and image decoding. This paper shows the work of various authors in the field of machine learning in various application areas.

Ioannis Vlahavas

IJRASET Publication

This paper describes essential points of machine learning and its application. It seamlessly turns around and teach about the pros and cons of the ML. As well as it covers the real-life application where the machine learning is being used. Different types of machine learning and its algorithms. This paper is giving the detail knowledge about the different algorithms used in machine learning with their applications. There is brief explanation about the Weather Prediction application using the machine learning and also the comparison between various machine learning algorithms used by various researchers for weather prediction.

Sumeet Agarwal


Lancar Usahanya

Kathy Hayes

Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

Thrombosis and Haemostasis

Jonathan Costa

The Journal of Urology

juan david rios ramos

Journal of Biological Researches

Hening Swastikaningrum

Prof. Devanildo Braz da Silva


New Insight into Brucella Infection and Foodborne Diseases

Mashooq Dar


Chin-ling Chen

Maria do Céu Roldão

Computer Science and Communications Dictionary



DOAJ (DOAJ: Directory of Open Access Journals)

Roberto Kahlmeyer-Mertens

Journal of Separation Science



Neuropsychology (journal)

Lincoln Gray

Metabolic Brain Disease

Tally Lerman-Sagie

Jurnal Syntax Fusion

Novia Nanda


  •   We're Hiring!
  •   Help Center
  • Find new research papers in:
  • Health Sciences
  • Earth Sciences
  • Cognitive Science
  • Mathematics
  • Computer Science
  • Academia ©2024

Carnegie Mellon University

Efficient Lifelong Learning in Deep Neural Networks: Optimizing Architecture, Training, and Data

 The prevalent machine learning paradigm involves training a separate model for every new task given a static dataset. In contrast, humans accumulate knowledge over time, and the lifelong learning paradigm seeks to emulate this process by enabling systems to learn continuously from a stream of tasks, retaining past knowledge for efficient future learning. This paradigm also offers advantages such as avoiding periodic model training, potentially reducing computational and energy requirements, and promoting environmentally friendly Green AI. In modern machine learning, deep neural networks, while powerful, face challenges like catastrophic forgetting (losing knowledge from previous tasks during new task learning) and negative interference (previously learned knowledge hindering new task learning). These issues arise from the stability-plasticity dilemma , which necessitates finding the right balance between preserving past knowledge (stability) and acquiring new knowledge (plasticity). Efficient lifelong learning systems must address this dilemma, along with other considerations like supporting online data streams, utilizing small and fixed memory buffer capacity (if any), and learning from unlabeled data streams. 

In this thesis, we derive inspiration from the biological learning process and recent progress in deep learning to enable efficient lifelong learning systems . We propose injecting inductive biases into the three main components of data-driven machine learning: model (architecture & initialization), training (objective & optimization), and data. This thesis is structured into three parts, each corresponding to one of these components. In the first part, we explore the role of pre-trained initializations , revealing their implicit alleviation of forgetting compared to random ones. Next, we design a parameter-efficient expert architecture that dynamically expands learning capacity to address the stability-plasticity dilemma. In the second part, we demonstrate that explicit optimization for flat minima improves network stability and introduce a meta-learning objective for stability-plasticity balance. The third part delves into lifelong semi-supervised learning, addressing the stability-plasticity dilemma by rehearsing pseudo-labeled data . We conclude by examining pre-training from the perspective of lifelong learning, showcasing enhancements by applying the above-developed strategies to the (continual) pre-training of models 

Degree Type

  • Dissertation
  • Language Technologies Institute

Degree Name

  • Doctor of Philosophy (PhD)

Usage metrics

  • Natural Language Processing

Help | Advanced Search

Computer Science > Machine Learning

Title: data-driven stochastic ac-opf using gaussian processes.

Abstract: The thesis focuses on developing a data-driven algorithm, based on machine learning, to solve the stochastic alternating current (AC) chance-constrained (CC) Optimal Power Flow (OPF) problem. Although the AC CC-OPF problem has been successful in academic circles, it is highly nonlinear and computationally demanding, which limits its practical impact. The proposed approach aims to address this limitation and demonstrate its empirical efficiency through applications to multiple IEEE test cases. To solve the non-convex and computationally challenging CC AC-OPF problem, the proposed approach relies on a machine learning Gaussian process regression (GPR) model. The full Gaussian process (GP) approach is capable of learning a simple yet non-convex data-driven approximation to the AC power flow equations that can incorporate uncertain inputs. The proposed approach uses various approximations for GP-uncertainty propagation. The full GP CC-OPF approach exhibits highly competitive and promising results, outperforming the state-of-the-art sample-based chance constraint approaches. To further improve the robustness and complexity/accuracy trade-off of the full GP CC-OPF, a fast data-driven setup is proposed. This setup relies on the sparse and hybrid Gaussian processes (GP) framework to model the power flow equations with input uncertainty.

Submission history

Access paper:.

  • Download PDF
  • Other Formats

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

BibSonomy logo

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

  • Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .


  1. (PDF) Modern Applications of Machine Learning

    thesis on machine learning pdf

  2. Fundamentals of Machine Learning (True PDF)

    thesis on machine learning pdf

  3. (PDF) Thesis Dissertation: Machine Learning Techniques for Word Sense

    thesis on machine learning pdf

  4. (PDF) Machine Learning for Probabilistic Prediction (PhD thesis, VALERY

    thesis on machine learning pdf


    thesis on machine learning pdf

  6. (PDF) Comparative Study of Some Supervised Machine Learning Algorithms

    thesis on machine learning pdf


  1. The Academic Research Process

  2. Research Methodology part two

  3. Research Methodology : Lecture 5

  4. Research Methods

  5. Workshop on "Research Methodology & Project Writing"

  6. Lec07_part1_introduction to machine learning


  1. PDF Undergraduate Fundamentals of Machine Learning

    of the basics of machine learning, it might be better understood as a collection of tools that can be applied to a speci c subset of problems. 1.2 What Will This Book Teach Me? The purpose of this book is to provide you the reader with the following: a framework with which to approach problems that machine learning learning might help solve ...

  2. PDF Master Thesis Using Machine Learning Methods for Evaluating the ...

    Master Thesis Using Machine Learning Methods for Evaluating the Quality of Technical Documents Author: Supervisor: Examiner: Reader: Semester: Subject: Course: Michael LUCKERT Moritz SCHAEFER-KEHNERT Prof. Dr. Welf LÖWE Prof. Dr. Andreas KERREN Dr. Ola PETERSSON HT2015 Computer Science 15HT - 5DV50E/4DV50E

  3. PhD Dissertations

    PhD Dissertations [All are .pdf files] Probabilistic Reinforcement Learning: Using Data to Define Desired Outcomes, and Inferring How to Get There Benjamin Eysenbach, 2023. Data-driven Decisions - An Anomaly Detection Perspective Shubhranshu Shekhar, 2023. METHODS AND APPLICATIONS OF EXPLAINABLE MACHINE LEARNING Joon Sik Kim, 2023. Applied Mathematics of the Future Kin G. Olivares, 2023

  4. PDF Solving Machine Learning Problems

    homework, and quiz questions from MIT's 6.036 Introduction to Machine Learning course and train a machine learning model to answer these questions. Our system demonstrates an overall accuracy of 96% for open-response questions and 97% for multiple-choice questions, compared with MIT students' average of 93%, achieving

  5. PDF Bachelor Thesis

    Computer graphics, Machine learning, Deep Learning, Convolutional neural net-works, Object Classication, Synthetic data, Three.js Abstract One of the limitations of supervised learning in deep learning algorithm is to gather and label a large set of data. In this document, the approach to solve this limitation is presented by using synthetic data.


    Machine learning (ML) systems are remarkably successful on a variety of benchmarks across sev-eral domains. In these benchmarks, the test data points, though not identical, are very similar to ... This thesis focuses on an extreme version of this brittleness, adversarial examples, where even imperceptible (but carefully constructed) changes ...

  7. A machine learning approach to modeling and predicting training

    However, traditional analysis techniques and human intuition are of limited use on so-called "big-data" environments, and one of the most promising areas to prepare for this influx of complex training data is the field of machine learning. Thus, the objective of this thesis was to lay the foundations for the use of machine learning algorithms ...


    In this thesis, we develop novel methods to show how longitudinal health data contained in Electronic Health Records (EHRs) can be harnessed for making novel clinical discoveries. ... this thesis illustrates how the use of machine learning for analyzing these large scale digital patient data repositories can yield new clinical discoveries and ...

  9. PDF Integrating Machine Learning into Data Analysis and Plant Performance

    This thesis shows, drawing from a recent project at Nissan's Canton, ... Machine learning was not initially a part of our project scope. Two things led us to it. The first was the general frustration we heard from operators, engineers, and managers about the challenges they had dealing with data. With the number

  10. PDF

    In this PhD dissertation, Liam Li from the Machine Learning Department at Carnegie Mellon University presents a novel framework for massively parallel hyperparameter optimization, which can significantly improve the efficiency and scalability of machine learning algorithms. The thesis also includes applications to neural networks, natural language processing, and computer vision. If you are ...

  11. PDF Master's Thesis: Machine Learning for Technical Information Quality

    machine learning might be a solution, which is what is evaluated in this thesis. 1.2 Problem The purpose of this master thesis is to try to nd an answer to the question: How well can we grade the quality of technical texts using machine learning with graded job application tests from Sigma Technology as reference? 1


    Gorgonia [26] is an open source deep learning API that uses Go. It uses the Gorgonia/cu Go bindings for CUDA. The goal of Gorgonia is to provide a machine learning/graph computation based library. Using Gorgonia should feel familiar to other Python learning APIs like TensorFlow or Keras. However, as a deep learning

  13. (PDF) Research on Machine Learning and Its Algorithms and Development

    Machine Learning Research on Machine Learning and Its Algorithms and Development Journal of Physics Conference Series 1544 (1):012003 License CC BY 3.0 Authors: Wei Jin Abstract This article...

  14. PDF Machine Learning for Decision Making

    Machine learning applications to both decision-making and decision-support are growing. Further,witheachsuccessfulapplication,learningalgorithmsaregain- ing increased autonomy and control over decision-making. As a result, research into intelligent decision-making algorithms continues to improve. For example, theStanfordResearchInstitute ...

  15. PDF Machine Learning Techniques for Weather Forecasting Abstract

    (World Meteorological Organization, 2003). The machine-learning software Weka (Hall et al., 2009) was chosen for training and testing all models generated in this thesis. This thesis attempted to analyze the effect of using NOAA predictions for air temperature, precipitation rate, visibility, wind speed, wind direction, dew point temperature, air

  16. PDF Abstract Using Machine Learning Techniques for Analyzing Educational

    This thesis uses machine learning techniques and statistical analysis in two separate educational experiments. In the first experiment we attempt to find relationships between students' written essay responses to physics questions and their learning of the physics data. To find these relationships, we used multiple types

  17. [2402.10888] Explainability for Machine Learning Models: From Data

    Download PDF Abstract: This thesis explores the generation of local explanations for already deployed machine learning models, aiming to identify optimal conditions for producing meaningful explanations considering both data and user requirements. The primary goal is to develop methods for generating explanations for any model while ensuring that these explanations remain faithful to the ...

  18. PDF Master Thesis

    Master Thesis Machine Learning approach for En-terprise Data with a focus on SAP Leonardo Kavish Rastogi Magdeburg, September 20, 2018 Supervisor: MSc. Gabriel Campero Durand Professor: Prof. Dr. Alexander Zeier Second Assessor: Prof. Dr. Klaus Turowski Otto-von-Guericke-UniversityMagdeburg


    1.1.1 What is Machine Learning? Learning, like intelligence, covers such a broad range of processes that it is dif- cult to de ne precisely. A dictionary de nition includes phrases such as \to gain knowledge, or understanding of, or skill in, by study, instruction, or expe- rience," and \modi cation of a behavioral tendency by experience."

  20. (PDF) PhD Thesis: Novel applications of Machine Learning to Network

    Specifically, it is important to mention the contributions made in this thesis to the areas of: 1) estimation (both detection and prediction) of the quality of a user's experience when viewing...

  21. Thesis on Machine Learning Methods and Its Applications

    Thesis on Machine Learning Methods and Its Applications IJRASET Publication 2021, IJRASET In the 1950s, the concept of machine learning was discovered and developed as a subfield of artificial intelligence. However, there were no significant developments or research on it until this decade.

  22. PDF Python-basedDeep-Learningmethods forenergyconsumptionforecasting. Thesis

    1 Abstract Inasocietywherewedonothingbutincreasetheuseofelectricityinourdailylife,en-ergyconsumptionandthecorrespondingmanagementisamajorissue.Theprediction

  23. PDF Machine learning for detection of cyberattacks on industrial control

    This thesis aims to help researchers and industry leaders understand how to implement machine learning (ML) as an early detection tool for anomalies (cyberattacks being a subset of anomalies) in their processes. With learnings from an end-to-end implementation of some stateart machine learning models and a -of-the-

  24. PDF Bachelor Thesis A machine learning approach to enhance the ...

    lem. In this chapter, two machine learning algorithms are presented that are commonly usedfortextclassification. 2.2.1 SupportVectorMachine-SVM Support Vector Machine is a supervised machine learning algorithm that can be used for text classification. The objective of the algorithm is to determine the best decision

  25. Efficient Lifelong Learning in Deep Neural Networks: Optimizing

    The prevalent machine learning paradigm involves training a separate model for every new task given a static dataset. In contrast, humans accumulate knowledge over time, and the lifelong learning paradigm seeks to emulate this process by enabling systems to learn continuously from a stream of tasks, retaining past knowledge for efficient future learning. This paradigm also offers advantages ...

  26. (PDF) Machine learning in financial markets: A critical review of

    The integration of machine learning (ML) techniques in financial markets has revolutionized traditional trading and risk management strategies, offering unprecedented opportunities and challenges.

  27. Data-Driven Stochastic AC-OPF using Gaussian Processes

    Download PDF Abstract: The thesis focuses on developing a data-driven algorithm, based on machine learning, to solve the stochastic alternating current (AC) chance-constrained (CC) Optimal Power Flow (OPF) problem. Although the AC CC-OPF problem has been successful in academic circles, it is highly nonlinear and computationally demanding, which limits its practical impact.