Academia.edu no longer supports Internet Explorer.
To browse Academia.edu 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
Thesis on Machine Learning Methods and Its Applications
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.
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.
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.
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
Machine learning , 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 . 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
International Journal of Engineering Applied Sciences and Technology
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.
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.
Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
Thrombosis and Haemostasis
The Journal of Urology
juan david rios ramos
Journal of Biological Researches
Prof. Devanildo Braz da Silva
New Insight into Brucella Infection and Foodborne Diseases
Maria do Céu Roldão
Computer Science and Communications Dictionary
DOAJ (DOAJ: Directory of Open Access Journals)
Journal of Separation Science
Dr. YAKUBU AZEH
Metabolic Brain Disease
Jurnal Syntax Fusion
- We're Hiring!
- Help Center
- Find new research papers in:
- Health Sciences
- Earth Sciences
- Cognitive Science
- Computer Science
- Academia ©2024
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
- Language Technologies Institute
- Doctor of Philosophy (PhD)
- 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.
- Download PDF
- Other Formats
References & Citations
- Google Scholar
- Semantic Scholar
BibTeX formatted citation
Bibliographic and Citation Tools
Code, data and media associated with this article, recommenders and search tools.
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 .