Название: Computational Methods for Deep Learning (2nd Edition)
Автор: Wei Qi Yan
Издательство: Springer
Серия: Texts in Computer Science
Год: 2023
Страниц: 235
Язык: английский
Формат: pdf (true), epub
Размер: 25.1 MB

We have integrated materials on Deep Learning, Machine Learning, and computational mathematics, refining the contents to publish this book. Our aim is to provide a resource that benefits postgraduate students, particularly those working on their theses, by sharing our research outputs and teaching work to enhance their projects. In this book, we organize our material and present the story of Deep Learning in a progression from easy to difficult concepts in mathematics. We have structured the content with a focus on knowledge transfer from the perspective of machine intelligence. We begin by explaining artificial neural networks, including neuron design and activation functions. We then delve into the mechanics of Deep Learning using advanced mathematical concepts. At the end of each chapter, we emphasize the practical implementation of Deep Learning algorithms using Python-based platforms and the latest MATLAB toolboxes. Additionally, we provide a list of questions for reflection and discussion.

Название: Computational Methods with MATLAB
Автор: Erik Cuevas, Alberto Luque, Hector Escobar
Издательство: Springer
Год: 2024
Страниц: 217
Язык: английский
Формат: pdf (true), epub
Размер: 34.0 MB

The objective of this book is to present a comprehensive and consistent overview of numerical methods for undergraduate students and professionals in the engineering field. The book can also serve as a reference for engineering professionals who have the need to use MATLAB in their applications. This is because many of the MATLAB codes, presented after introducing the basic ideas of each algorithm, can be easily modified to solve similar problems even by those who do not know what goes on inside MATLAB routines and the algorithms they use. This book can be successfully used by two types of readers. The first type are those readers who require a detailed explanation of each algorithm and its potential. These readers are interested in knowing each method in such a way that they can modify the structure and make adaptations to solve their problems. The second are those readers who want to use numerical methods generically as subroutines. Just as most users of a household appliance need only know how to operate it to perform a task, these users need only know how to formulate their problems that they want to solve using MATLAB and how to use the corresponding routines to solve them. The book uses much more code than formal mathematics. This is because we are convinced that even readers with an excellent mathematical background have trouble understanding an approach until they see the algorithm implemented in code. This fact is because the implemented code removes all ambiguities.

Название: Learning with the Minimum Description Length Principle
Автор: Kenji Yamanishi
Издательство: Springer
Год: 2023
Страниц: 352
Язык: английский
Формат: pdf (true), epub
Размер: 41.3 MB

This book introduces readers to the minimum description length (MDL) principle and its applications in learning. The MDL is a fundamental principle for inductive inference, which is used in many applications including statistical modeling, pattern recognition and Machine Learning. At its core, the MDL is based on the premise that “the shortest code length leads to the best strategy for learning anything from data.” The MDL provides a broad and unifying view of statistical inferences such as estimation, prediction and testing and, of course, Machine Learning. Specifically, let us consider Machine Learning, which aims at extracting useful knowledge from data to make effective use of it. In real-world Machine Mearning applications, the data sources and models are not sufficiently simple that an elegant theory of statistics cannot straightforwardly be applied. This book is addressed to researchers or graduate students who specialize Machine Learning, statistics, information theory, or Computer Science. Hence, readers are assumed to have background knowledge about probability theory, linear algebra, analysis, elementary statistics, basics of Machine Learning, and Computer Science.

Название: Hands-on ML Projects with OpenCV: Master computer vision and Machine Learning using OpenCV and Python
Автор: Mugesh S.
Издательство: Orange Education Pvt Ltd, AVA
Год: August 2023
Страниц: 355
Язык: английский
Формат: pdf, epub (true)
Размер: 13.3 MB

Be at your A game in building Intelligent systems by leveraging Computer vision and Machine Learning. This book is an in-depth guide that merges machine learning techniques with OpenCV, the most popular computer vision library, using Python. The book introduces fundamental concepts in Machine Learning and computer vision, progressing to practical implementation with OpenCV. Concepts related to image preprocessing, contour and thresholding techniques, motion detection and tracking are explained in a step-by-step manner using code and output snippets. Hands-on projects with real-world datasets will offer you an invaluable experience in solving OpenCV challenges with machine learning. It’s an ultimate guide to explore areas like Deep Learning, transfer learning, and model optimization, empowering readers to tackle complex tasks. Every chapter offers practical tips and tricks to build effective ML models. This book is for everyone with a basic understanding of programming and who wants to apply machine learning in computer vision using OpenCV and Python.

Название: Introduction to Algorithms & Data Structures 3: Learn Linear Data Structures with Videos & Interview Questions
Автор: Bolakale Aremu
Издательство: Ojula Technology Innovations
Год: September 2023
Страниц: 271
Язык: английский
Формат: pdf, epub
Размер: 10.2 MB

This playbook is the third volume of the series Introduction to Algorithms & Data Structures. It is written in the form of a course. It is a very comprehensive data structures and algorithms book. Most data structure books and courses are too academic and boring. They have too much math and their codes look ugly, old and disgusting! This book is bundled with tutorial videos that are fun and easy to follow along, and show you how to write beautiful code like a software engineer, not a mathematician. Mastering data structures and algorithms is essential to getting your dream job. So, don't waste your time browsing disconnected tutorials or super long, boring courses. In this volume, we use Java to teach the concepts but you can apply these concepts in any programming language. Our focus is on problem-solving, not programming languages and tools. All you need to understand the codes are some basic programming skills, which were already taught in the first and second volumes of the series. Alternatively, if you already know variables, loops, and conditional statements, you're good to go.

Название: Code is for Humans: A guide to human-centric software engineering. Part I. Theory
Автор: Zohar Jackson
Издательство: Leanpub
Год: September 15, 2023
Страниц: 141
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

To write better code and build better products we must understand why engineering and design often fail. Why is it so difficult to write bug-free code? Why do people fail to use products? And why do engineering projects go sideways? The answer to these questions lies in the shortcomings of human cognition and the nature of complexity. This book explores these topics and presents a human-centric approach to software engineering. An approach that considers and compensates for our cognitive biases, cognitive weaknesses, and the chaotic nature of the universe. The ideas presented will help you write better code, build better products, and be a more effective engineer. Their years of university Computer Science education had failed them by focusing on algorithms and the theoretical. Valuable knowledge, but not very useful in solving the problems engineers face on a daily basis. These graduates were never taught what engineering is. What are its fundamental concepts and practices?

Название: From jаvascript to Rust: Map common jаvascript and Node.js workflows to the Rust ecosystem
Автор: Jarrod Overson, Vino Technologies
Издательство: Independently published
Год: 2022
Страниц: 166
Язык: английский
Формат: pdf (true)
Размер: 10.9 MB

Each chapter will take concepts you know in jаvascript and Node.js and translate them to their Rust counterparts. The first chapters start with the basics, like getting set up with Rust via a tool similar to nvm (rustup), using the package manager (cargo), and setting up VS Code. Later chapters go over language gotchas, how to perform common jаvascript tasks in Rust, and we’ll finish up by touching on solid dependencies to start adding to your projects. Why Rust? You could use C, C++, C#, Go, Java, Kotlin, Haskell or a hundred others. Rust is notoriously difficult even for system programmers to get into. Rust’s tooling and support for WebAssembly is better than everything else out there. You can rewrite CPU-heavy jаvascript logic into Rust and run it as WebAssembly. Which basically makes you a superhero. With jаvascript and Rust, there’s nothing you can’t handle. This book is not a deep, comprehensive Rust tutorial. It’s meant to bootstrap experienced programmers into Rust. We’ll take common Node.js workflows and idiomatic jаvascript and TypeScript and map them to their Rust counterparts.

Название: Beginner's Guide to Unity Shader Graph: Create Immersive Game Worlds Using Unity's Shader Tool
Автор: Alvaro Alda
Издательство: Apress
Год: 2023
Страниц: 453
Язык: английский
Формат: pdf (true), epub (true)
Размер: 83.5 MB

Discover how shaders can enhance your game and mesmerize players by making graphic gameplay elements more realistic and attractive. This book provides easy-to-follow recipes that will show you how to leverage the Unity Shader Graph to create more immersive, enjoyable games. Author ?lvaro Alda takes you through each effect step by step, so that you gain a foundational understanding of how they are created using the Shader Graph tool. Practical projects help you put what you’re learning into context, from simple effects like 3D scan lines to more complicated effects such as black holes, bubble particles, water, and even interactive snow. Twelve different effects are demonstrated, to cover almost everything related to shader graph. On completing this book, you will have a thorough understanding of the Shader Graph tool and samples to replicate and continue learning from. Whether you are an indie game developer or technical artist, Beginner's Guide to Unity Shader Graph will give you the confidence to use the Shader Graph tool to create games that will keep players glued to their screens.

Название: Node.js в действии (+ примеры)
Автор: М. Кантелон, М. Хартер, T. Головайчук, Н. Райлих
Издательство: Питер
Год: 2014
Формат: pdf
Размер: 12 мб
Язык: Русский

Эволюция jаvascript с каждым годом предоставляет веб-разработчикам все большее количество инноваций. Один из наиболее интересных и популярных инструментов для создания легко масштабируемых сетевых приложений является Node.js, основанный на движке V8 и превращающий jаvascript из узкоспециализированного языка в язык общего назначения. Node.js добавляет возможность jаvascript взаимодействовать с устройствами ввода-вывода через свой API (написанный на C++), подключать другие внешние библиотеки, написанные на разных языках, обеспечивая вызовы к ним из jаvascript-кода.

Название: Грокаем глубокое обучение с подкреплением
Автор: Моралес Мигель
Издательство: Питер
Год: 2023
Формат: pdf
Страниц: 464
Размер: 22,9 Мб
Язык: русский

Мы учимся, взаимодействуя с окружающей средой, и получаемые вознаграждения и наказания определяют наше поведение в будущем. Глубокое обучение с подкреплением привносит этот естественный процесс в искусственный интеллект и предполагает анализ результатов для выявления наиболее эффективных путей движения вперед. Агенты глубокого обучения с подкреплением могут способствовать успеху маркетинговых кампаний, прогнозировать рост акций и побеждать гроссмейстеров в Го и шахматах. Давайте научимся создавать системы глубокого обучения на примере увлекательных упражнений, сопровождаемых кодом на Python с подробными комментариями и понятными объяснениями. Вы увидите, как работают алгоритмы, и научитесь создавать собственных агентов глубокого обучения с подкреплением, используя оценочную обратную связь.