Название: Elements of Data Science, Machine Learning, and Artificial Intelligence Using R
Автор: Frank Emmert-Streib, Salissou Moutari, Matthias Dehmer
Издательство: Springer
Год: 2023
Страниц: 582
Язык: английский
Формат: pdf (true)
Размер: 22.2 MB

The textbook provides students with tools they need to analyze complex data using methods from Data Science, Machine Learning and Artificial Intelligence. The authors include both the presentation of methods along with applications using the programming language R, which is the gold standard for analyzing data. The authors cover all three main components of Data Science: Computer Science; mathematics and statistics; and domain knowledge. The book presents methods and implementations in R side-by-side, allowing the immediate practical application of the learning concepts. Furthermore, this teaches computational thinking in a natural way. The book includes exercises, case studies, Q&A and examples. Regarding useful programming languages, R and Python are very popular today. However, while both provide similar capabilities, there are differences in certain situations. In this book, we prefer R over Python due to its statistical origin. In fact, R was developed to provide a “statistical programming language.” We will see the benefits of this when discussing hypothesis testing (Chap. 10), resampling methods (Chap. 4), and linear regression (Chap. 11), where R provides excellent functionalities. Although this book does not provide an introduction to programming and mathematics, it presents examples in R for the methods from Machine Learning, Artificial Intelligence, and statistics.

Название: Machine Learning Approaches in Financial Analytics
Автор: Leandros A. Maglaras, Sonali Das, Naliniprava Tripathy, Srikanta Patnaik
Издательство: Springer
Год: 2024
Страниц: 485
Язык: английский
Формат: pdf (true), epub
Размер: 53.1 MB

This book addresses the growing need for a comprehensive guide to the application of Machine Learning in financial analytics. It offers a valuable resource for both beginners and experienced professionals in finance and Data Science by covering the theoretical foundations, practical implementations, ethical considerations, and future trends in the field. It bridges the gap between theory and practice, providing readers with the tools and knowledge they need to leverage the power of Machine Learning in the financial sector responsibly. The financial world has always been a realm of complexity, marked by volatility, uncertainty, and dynamic interconnectedness. Traditional models and tools have often struggled to capture the multifaceted nature of this domain. However, Machine Learning techniques offer a paradigm shift, providing the capability to process vast amounts of data, identify patterns, and generate insights that were previously unimaginable. Throughout the chapters of this book, we explore the fundamental principles of Machine Learning and how they can be applied to tackle a myriad of financial challenges. From predictive modeling, risk assessment, algorithmic trading, portfolio optimization, fraud detection, to customer segmentation, the potential applications are boundless. Object-oriented programming in Python combined with the power of NumPy, Matplotlib and Jupyter fits the bill perfectly for design and visualization in financial engineering. We find that Python combined with Jupyter is not only very well suited for designing and visualizing structured products and examining the impact on pricing as different design elements are tweaked, but it is also amenable to a variety of extensions and integration with other open-source computational finance libraries.

Название: Data-Driven Systems and Intelligent Applications
Автор: Mangesh M. Ghonge, N. Krishna Chaitanya, Pradeep N., Harish Garg, Alessandro Bruno
Издательство: CRC Press
Серия: Intelligent Data-Driven Systems and Artificial Intelligence
Год: 2025
Страниц: 197
Язык: английский
Формат: pdf (true)
Размер: 12.5 MB

This book comprehensively discusses basic data-driven intelligent systems, the methods for processing the data, and cloud computing with Artificial Intelligence (AI). It presents fundamental and advanced techniques used for handling large user data, and for the data stored in the cloud. It further covers data-driven decision-making for smart logistics and manufacturing systems, network security, and privacy issues in cloud computing. The foundation of Machine Learning is the precise use of models and algorithms. Put another way, an algorithm is just a basic procedure for making use of data, either structured or unstructured, to get a result. Concurrently, a Machine Learning model denotes the program–algorithm combination that allows the program to achieve the required objective. Machine Learning models encompass the broader scope of the output generated by algorithms, which are formulas for making predictions. As a result, making the claim that ML models come from Machine Learning algorithms rather than the other way around is technically correct. Viewing the models in Machine Learning will help us comprehend the function of ML algorithms. Presents the advent of Machine Learning, Deep Learning, and reinforcement technique for cloud computing to provide cost-effective and efficient services. The text will be useful for senior undergraduate, graduate students, and academic researchers in diverse fields including electrical engineering, electronics and communications engineering, computer engineering, manufacturing engineering, and production engineering.

Название: Predictive Analytics for Business using R
Автор: Russell R Barton
Издательство: World Scientific Publishing
Год: 2025
Страниц: 464
Язык: английский
Формат: pdf (true)
Размер: 14.5 MB

The fields of mathematical statistics, statistical graphics, Computer Science and operations research have created the rich set of methods now called Analytics. Often analytics is characterized along three poles: descriptive analytics (what do data tell us), predictive analytics (what can be forecast based on the data, and with what certainty), and prescriptive analytics (how can the data inform changes to improve system performance). This book focuses on the second pole, predictive analytics. The areas of predicting a number, a class, and dynamic behavior are distinct, with different methods. This text has three parts based on these areas. Topics in predicting a number include simple and multiple linear regression, transformation of variables, analysis of observational data via cross-validation, the generalized linear model, designed experiments, and Gaussian process and neural network regression. Classification methods include neural networks, logistic regression, k-nearest neighbor, and linear discriminant analysis. Methods for predicting dynamic behavior include trend analysis, time series analysis and discrete-event dynamic simulation. Characterizing prediction uncertainty is a key focus of this text. The text provides analytic methods appropriate to each area, with an explicit process for applying such methods. The text illustrates the application of predictive analytics methods using the R programming language.

Название: Metaheuristics and Reinforcement Techniques for Smart Sensor Applications
Автор: Adwitiya Sinha, Manju, Samayveer Singh
Издательство: CRC Press
Год: 2025
Страниц: 253
Язык: английский
Формат: pdf (true), epub
Размер: 14.5 MB

This book discusses the fundamentals of wireless sensor networks,and the prevailing method and trends of smart sensor applications. It presents analytical modelling to foster the understanding of network challenges in developing protocols for next-generation communication standards. Metaheuristic algorithms are optimization techniques that draw inspiration from natural and abstract concepts to solve complex problems. Unlike exact algorithms, which aim for optimal solutions, metaheuristics prioritize speed and adaptability, making them suitable for addressing computationally challenging problems with large solution spaces. These algorithms play a vital role in various fields, including combinatorial optimization, Machine Learning, and operations research. In the realm of WSNs, metaheuristic algorithms are instrumental in optimizing routing protocols. WSNs comprise nodes with limited computational resources, energy constraints, and often operate in dynamic environments. Efficient data routing in WSNs is critical for conserving energy, extending network lifetime, and ensuring reliable data delivery. Genetic Algorithms (GA) for CH selection play a pivotal role in the efficiency and performance of wireless sensor networks. The GA algorithm employs evolutionary principles to strategically choose CHs that are responsible for efficient and reliable data transmission in the network.

Название: Обработка естественного языка с TensorFlow
Автор: Ганегедара Т.
Издательство: ДМK
Год: 2020
Cтраниц: 382
Формат: pdf (ocr)
Размер: 17 мб
Язык: русский

Обработка естественного языка применяется в различных приложениях машинного обучения, а TensorFlow является важнейшей библиотекой для реализации систем глубокого обучения на практике. Эта книга знакомит читателя с методами обработки естественного языка и содержит практическое руководство по работе с TensorFlow, предоставляя мощный инструмент для работы с огромными объемами неструктурированных данных и решения уникальных задач по обработке естественного языка.

Название: Embedded Artificial Intelligence: Principles, Platforms and Practices
Автор: Bin Li
Издательство: Springer
Год: 2024
Страниц: 262
Язык: английский
Формат: pdf (true), epub
Размер: 41.6 MB

This book focuses on the emerging topic of Embedded Artificial Intelligence and provides a systematic summary of its principles, platforms, and practices. In the section on principles, it analyzes three main approaches for implementing Embedded Artificial Intelligence: cloud computing mode, local mode, and local-cloud collaborative mode. The book identifies five essential components for implementing Embedded Artificial Intelligence: embedded AI accelerator chips, lightweight neural network algorithms, model compression techniques, compiler optimization techniques, and multi-level cascaded application frameworks. The platform section introduces mainstream embedded AI accelerator chips and software frameworks currently used in the industry. The practical part outlines the development process of Embedded Artificial Intelligence and showcases real-world application examples with accompanying code. As a comprehensive guide to the emerging field of Embedded Artificial Intelligence, the book offers rich and in-depth content, a clear and logical structure, and a balanced approach to both theoretical analysis and practical applications. It provides significant reference value and can serve as an introductory and reference guide for researchers, scholars, students, engineers, and professionals interested in studying and implementing Embedded Artificial Intelligence.

Название: The New Quantum Era: An Outsider’s Introduction (Final Release)
Автор: Sebastian Hassinger
Издательство: O’Reilly Media, Inc.
Год: 2024
Страниц: 131
Язык: английский
Формат: epub
Размер: 10.1 MB

Quantum computing and associated technologies and ideas seem to be everywhere today, even in blockbuster movies. As a field, quantum information science only goes back a few decades, but it's generating outsize excitement and investment in the 21st century. There's reason for the enthusiasm, but we're still a long way from being able to build and use these exotic machines. In this book, author Sebastian Hassinger guides you through the foundational ideas of quantum computing, providing insight into where it came from, what it is today, and what it may be in the future. Grounded in information science and quantum mechanics with straightforward explorations of the technology's crucial concepts and elements, this book demystifies the field and helps you develop your quantum intuition, making it easier to learn and use the technologies available on the cloud today.

Название: Federated Learning: From Algorithms to System Implementation
Автор: Liefeng Bo, Heng Huang, Songxiang Gu, Yanqing Chen
Издательство: World Scientific Publishing
Год: 2025
Страниц: 546
Язык: английский
Формат: pdf (true)
Размер: 24.9 MB

Authored by researchers and practitioners who build cutting-edge Federated Learning (FL) applications to solve real-world problems, this book covers the spectrum of Federated Learning technology from concepts and application scenarios to advanced algorithms and finally system implementation in three parts. It provides a comprehensive review and summary of Federated Learning technology, as well as presenting numerous novel Federated Learning algorithms which no other books have summarized. The work also references the most recent papers, articles and reviews from the past several years to keep pace with the academic and industrial state of the art of Federated Learning. The first part lays a foundational understanding of Federated Learning by going through its definition and characteristics, and also possible application scenarios and related privacy protection technologies. The second part elaborates on some of the Federated Learning algorithms innovated by JD Technology which encompass both vertical and horizontal scenarios, including vertical federated tree models, linear regression, kernel learning, asynchronous methods, Deep Learning, homomorphic encryption, and reinforcement learning. The third and final part shifts in scope to Federated Learning systems - namely JD Technology's own FedLearn system - by discussing its design and implementation using gRPC, in addition to specific performance optimization techniques plus integration with blockchain technology. This book will serve as a great reference for readers who are experienced in Federated Learning algorithms, building privacy-preserving Machine Learning applications or solving real-world problems with privacy-restricted scenarios.

Название: Artificial Intelligence and Beyond for Finance
Автор: Marco Corazza, René Garcia, Faisal Shah Khan, Davide La Torre, Hatem Masri
Издательство: World Scientific Publishing
Год: 2024
Страниц: 429
Язык: английский
Формат: pdf (true)
Размер: 13.6 MB

Why did we write this book? We wanted to help financial experts and investors to understand the state of the art of Artificial Intelligence and Machine Learning in finance. And so, what is Artificial Intelligence? Deep Learning (DL) is a type of Machine Learning (ML) model that is typically used in supervised learning. The main feature of DL is the use of artificial neurons that model neurons of the human brain. Arranging many artificial neurons as nodes in vertical layers from left to right produces a neural network consisting of interconnected nodes. Each vertical collection of nodes is called a layer of the neural network. The layers in between the first and the last layers are called hidden layers. If there are one or two hidden layers in a neural network, it is called shallow ; otherwise, a network is called deep. Therefore, DL refers to learning that takes place with respect to a deep neural network. For context, we note that a linear regression can be implemented on a shallow neural network. No matter the specific industry or application, AI has become a new engine of growth. Both finance and banking have been leveraging AI technologies and algorithms and applying them to automate routine tasks, procedures, forecasting, and improving the overall customer experience.