Название: Machine Learning Evaluation: Towards Reliable and Responsible AI, 2nd Revised Edition
Автор: Nathalie Japkowicz, Zois Boukouvalas
Издательство: Cambridge University Press
Год: 2025
Страниц: 427
Язык: английский
Формат: pdf (true), epub
Размер: 10.1 MB

As Machine Learning applications gain widespread adoption and integration in a variety of applications, including safety and mission-critical systems, the need for robust evaluation methods grows more urgent. This book compiles scattered information on the topic from research papers and blogs to provide a centralized resource that is accessible to students, practitioners, and researchers across the sciences. The book examines meaningful metrics for diverse types of learning paradigms and applications, unbiased estimation methods, rigorous statistical analysis, fair training sets, and meaningful explainability, all of which are essential to building robust and reliable Machine Learning products. In addition to standard classification, the book discusses unsupervised learning, regression, image segmentation, and anomaly detection. The book also covers topics such as industry-strength evaluation, fairness, and responsible AI. Implementations using Python and Scikit-learn are available on the book's website.

Название: Атлас искусственного интеллекта: руководство для будущего
Автор: Кейт Кроуфорд
Издательство: АСТ
Серия: Программирование для всех
Год: 2023
Страниц: 321
Язык: русский
Формат: pdf, fb2, epub
Размер: 11.3 MB

Искусственный интеллект стал неотъемлемой частью современного мира, помогая людям в множестве сфер – от медицины до тяжелой промышленности. Оптимизация рабочих процессов, скорость выполнения, машинная точность в расчетах или креатив в творчестве – кажется, что ИИ стал совершенным инструментом для любой задачи. Кейт Кроуфорд – старший научный сотрудник Microsoft, профессор Калифорнийского университета – предлагает нам книгу-исследование, обращая наше внимание на темную сторону успеха и скрытые издержки искусственного интеллекта. При контролируемом машинном обучении инженеры предоставляют компьютеру маркированные обучающие данные. Затем в игру вступают два различных типа алгоритмов: обучающие и классифицирующие. Обучающий алгоритм – это алгоритм, который учится на помеченных данных; он сообщает классификатору, как лучше проанализировать связь между новыми входными данными и желаемым конечным результатом (или предсказанием). Например, он может определить: содержится ли на изображении лицо, является ли электронное письмо спамом. Существует множество видов моделей машинного обучения, включая нейронные сети, логистическую регрессию и деревья решений. Инженеры выбирают модель в зависимости от того, что они создают – будь то система распознавания лиц или средство определения настроений в социальных сетях, – а затем подбирают ее под свои вычислительные ресурсы.

Название: Data Structure in Python: Essential Techniques
Автор: Ed Norex
Издательство: HiTeX Press
Год: 2024
Страниц: 566
Язык: английский
Формат: pdf, epub, mobi
Размер: 10.1 MB

Dive into the advanced world of Python data structures with "Data Structure in Python: Essential Techniques," a comprehensive guide designed to elevate your programming skills to the next level. From the fundamental constructs of lists and tuples to the complex landscapes of trees, graphs, and hashing, this book offers an in-depth exploration of Python's powerful data manipulation capabilities.Structured into focused chapters, each delving into different data structures, this book meticulously breaks down advanced techniques such as implementing stacks and queues, mastering dictionary and set operations, advanced string manipulation, and explores the intricacies of searching and sorting algorithms.Whether you're a seasoned developer looking to refine your expertise or an intermediate programmer keen on tackling complex programming challenges, this book serves as an indispensable resource. Through practical case studies, it bridges the gap between theoretical knowledge and real-world application, equipping you with the know-how to optimize data access, enhance program efficiency, and develop scalable Python applications.

Название: Python Programming Bible [3 in 1] The Complete Crash Course to Learn and Explore Python beyond the Basics. Including Examples and Practical Exercises to Master Python from Beginners to Pro
Автор: James P. Meyers
Издательство: Independently published
Год: 2024
Страниц: 702
Язык: английский
Формат: pdf, epub
Размер: 10.1 MB

Master Python programming and develop a highly profitable skill with this complete beginner’s crash course on coding! Are you curious about learning Python for your career or hobbies? Do you want to learn how to develop web applications, code games, manage data, and create machine learning algorithms? Or are you searching for a simple & straightforward crash course to help you add this valuable programming skill to your virtual toolbelt? As a favorite of programmers and web developers across the globe, Python is a powerful and versatile programming language that has an immense amount of functionality. Its focus on simplicity and readability makes it perfect for absolute beginners – but how can you begin learning the fundamentals of this amazing language, access the vast library of APIs, and write your first code? Packed with dozens of user-friendly exercises and easy-to-understand explanations, this beginner-friendly crash course arms readers with an all-in-one guide to mastering Python programming. Whether you dream of designing video games, building stylish websites, or landing a lucrative job in the ever-growing tech industry, this Python Programming Bible combines 3 unique books to give you a comprehensive overview of Python – from basic functions to mobile app development, GUIs, Big Data & more.

Название: Principles of Data Structures Using C and C++
Автор: Julio Martell
Издательство: Independently published
Год: 2024
Страниц: 977
Язык: английский
Формат: epub
Размер: 10.1 MB

"Principles of Data Structures Using C and C++" provides a comprehensive exploration of essential data structures and algorithms, tailored for both beginners and experienced programmers. This book bridges theory and practical application, offering clear explanations and hands-on examples in both C and C++. Readers will learn to: •Understand fundamental data structures, including arrays, linked lists, stacks, queues, trees, and graphs; •Implement various algorithms for sorting, searching, and manipulating data efficiently; •Analyze the time and space complexity of algorithms to optimize performance; •Utilize object-oriented programming principles in C++ to create robust data structures; •Gain practical experience through coding exercises and real-world applications. Whether you're a student seeking to master the principles of data structures or a professional looking to enhance your programming skills, this book serves as an invaluable resource for understanding how to effectively organize and manage data in software development.

Название: Fundamentals of Software Engineering: From Coder to Engineer (Fourth Early Release)
Автор: Nathaniel Schutta, Dan Vega
Издательство: O’Reilly Media, Inc.
Год: 2024-09-19
Язык: английский
Формат: epub
Размер: 10.1 MB

What do you need to know to move from developer to senior engineer? Undergraduate curricula and bootcamps may teach the fundamentals of algorithms and writing code, but they rarely cover topics vital to your success as a software engineer. With this practical book, you'll learn the skills you need to succeed and thrive. Authors Nathaniel Schutta and Jakub Pilimon guide your journey with pointers to deep dives into specific topic areas. To understand the skills that really matter as a software engineer, this is the guide you'll want to read the first week at your first job. It also serves as a handy reminder when you move to a new organization or to a new position in your current organization. Ultimately, this book is targeted at new developers, and we wrote it with them foremost in our minds. We hope this book will show you the full picture of what it means to be more than a “coder”, to evolve into a software engineer and, more importantly, to help your career advancement. But it isn’t just newly minted developers who benefit from mastering the fundamentals. This book will also help more seasoned developers advance beyond their first job and grow their career to a senior role.

Название: Homomorphic Encryption for Data Science (HE4DS)
Автор: Allon Adir, Ehud Aharoni, Nir Drucker, Ronen Levy
Издательство: Springer
Год: 2024
Страниц: 311
Язык: английский
Формат: pdf (true), epub
Размер: 34.0 MB

This book provides basic knowledge required by an application developer to understand and use the Fully Homomorphic Encryption (FHE) technology for privacy preserving Data-Science applications. The authors present various techniques to leverage the unique features of FHE and to overcome its characteristic limitations. Homomorphic encryption (HE) is a cryptographic primitive that provides unique security guarantees in the privacy enhancing technologies (PETs) ecosystem. HE is a special type of encryption that allows computations to be performed on encrypted data. For example, it enables additions, multiplications, or both on ciphertexts, where the resulting ciphertext can be decrypted to have the same value as if the mathematical operations were performed directly on the encrypted data. This property is called homomorphism, hence the name of the HE primitive. This book aims to simplify the FHE world for those who are interested in privacy preserving Data Science tasks, and for an audience that does not necessarily have a deep cryptographic background, including undergraduate and graduate-level students in Computer Science, and data scientists who plan to work on private data and models.

Название: AI Literacy Fundamentals
Автор: Ben Jones
Издательство: Data Literacy Press
Год: 2024
Страниц: 240
Язык: английский
Формат: epub (true)
Размер: 10.1 MB

Feeling overwhelmed by AI? It's not you—it's the breakneck speed of technological progress. To quickly get into the AI conversation, you need a clear and simple foundation of knowledge to build on. This book is a friendly primer on the basic concepts of AI, how it's already snuck into our daily lives, and what we need to know to prepare for the future. Machine Learning (ML) is an umbrella term describing the study and use of different types of statistical algorithms that we can apply to data sets in order to learn from the patterns in those data sets how to accomplish specific tasks. When we apply a Machine Learning algorithm to a data set to learn its patterns, we say that we are training a model. Deep Learning is a special branch of Machine Learning that involves a specific family of artificial neural networks: deep neural networks (DNN). DNNs have changed the world of AI, and in so doing they have changed the world we live in. Any neural network that contains two or more hidden layers is considered a deep neural network. Unsurprisingly, then, a neural network with a single hidden layer is sometimes referred to as a shallow neural network. Furthermore, the number of hidden layers corresponds to the depth of the deep neural network. To wrap up our own study of Deep Learning and neural networks, I’d like to instead consider a few different types of deep neural networks that have led to breakthrough capabilities in the fields of computer vision and natural language processing. The first type is the convolutional neural network (CNN), sometimes called the ConvNet.

Название: Just Enough Data Science and Machine Learning: Essential Tools and Techniques
Автор: Mark Levene, Martyn Harris
Издательство: Addison-Wesley Professional/Pearson Education
Год: 2025
Страниц: 224
Язык: английский
Формат: epub
Размер: 10.1 MB

An accessible introduction to applied Data Science and Machine Learning, with minimal math and code required to master the foundational and technical aspects of Data Science. In Just Enough Data Science and Machine Learning, authors Mark Levene and Martyn Harris present a comprehensive and accessible introduction to Data Science. It allows the readers to develop an intuition behind the methods adopted in both Data Science and Machine Learning, which is the algorithmic component of Data Science involving the discovery of patterns from input data. This book looks at Data Science from an applied perspective, where emphasis is placed on the algorithmic aspects of Data Science and on the fundamental statistical concepts necessary to understand the subject. The book begins by exploring the nature of Data Science and its origins in basic statistics. The authors then guide readers through the essential steps of Data Science, starting with exploratory data analysis using visualisation tools. The book is packed with practical examples and real-world data sets throughout to reinforce the concepts. All examples are supported by Python code external to the reading material to keep the book timeless.

Название: Building a Debugger (Early Access)
Автор: Sy Brand
Издательство: No Starch Press
Год: 2025
Страниц: 738
Язык: английский
Формат: pdf (true)
Размер: 11.9 MB

Master the inner workings of your x64 Linux system and expand your OS expertise by writing your very own debugger using C++. If debuggers seem like magic to you, there is no better way to demystify them than to write your own. This book will show you exactly how to do it, walking you through the entire process of building a debugger for x64 Linux systems using C++. As go from an empty filesystem folder to a fully fledged debugger capable of setting breakpoints, stepping through code, manipulating variables, and more. As you add features to your debugger, you’ll also pick up a wealth of knowledge about operating systems, compilers, software testing, and low-level programming that you can use in your day-to-day development. In this book, we’re particularly concerned with debuggers for compiled code that runs directly on your central processing unit (CPU), written in a language like C, C++, Rust, or FORTRAN. Debuggers for these programs need to interface directly with the operating system and the underlying hardware, which can lead us to some deep insights into how computers actually work. What Will We Build? Over the course of this book, we’ll build a command line debugger for native code. I’ll call the debugger sdb, for Sy’s Debugger, but you can call yours whatever you like.