Litgu.ru - Литературный Гуру

Название: Prompt Engineering for Generative AI: Future-Proof Inputs for Reliable AI Outputs at Scale (5th Early Release)
Автор: James Phoenix, Mike Taylor
Издательство: O’Reilly Media, Inc.
Год: 2024-03-13
Страниц: 440
Язык: английский
Формат: epub
Размер: 78.0 MB

Large language models (LLMs) and diffusion models such as ChatGPT and Stable Diffusion have unprecedented potential. Because they have been trained on all the public text and images on the internet, they can make useful contributions to a wide variety of tasks. And with the barrier to entry greatly reduced today, practically any developer can harness LLMs and diffusion models to tackle problems previously unsuitable for automation. With this book, you'll gain a solid foundation in generative AI, including how to apply these models in practice. When first integrating LLMs and diffusion models into their workflows, most developers struggle to coax reliable enough results from them to use in automated systems. Authors James Phoenix and Mike Taylor show you how a set of principles called prompt engineering can enable you to work effectively with AI. The discipline of prompt engineering has arisen as a set of best practices for improving the reliability, efficiency, and accuracy of AI models.

Название: Hands-On Large Language Models: Language Understanding and Generation (6th Early Release)
Автор: Jay Alammar, Maarten Grootendorst
Издательство: O’Reilly Media, Inc.
Год: 2024-03-21
Страниц: 227
Язык: английский
Формат: epub
Размер: 11.0 MB

AI has acquired startling new language capabilities in just the past few years. Driven by the rapid advances in deep learning, language AI systems are able to write and understand text better than ever before. This trend enables the rise of new features, products, and entire industries. With this book, Python developers will learn the practical tools and concepts they need to use these capabilities today. One of the most common tasks in natural language processing, and machine learning in general, is classification. The goal of the task is to train a model to assign a label or class to some input text. Categorizing text is used across the world for a wide range of applications, from sentiment analysis and intent detection to extracting entities and detecting language. We can use an LLM to represent the text to be fed into our classifier. The choice of this model, however, may not be as straightforward as you might think. Models differ in the language they can handle, their architecture, size, inference speed, architecture, accuracy for certain tasks, and many more differences exist. BERT is a great underlying architecture for representing tasks that can be fine-tuned for a number of tasks, including classification. Although there are generative models that we can use, like the well-known Generated Pretrained Transformers (GPT) such as ChatGPT, BERT models often excel at being fine-tuned for specific tasks.

Название: Inter-Service Communication with Go: Mastering protocols, queues, and event-driven architectures in Go
Автор: Dušan Stojanović
Издательство: BPB Publications
Год: 2024
Страниц: 386
Язык: английский
Формат: pdf, epub
Размер: 10.1 MB

This book will cover different concepts of inter-service communication. They will be demonstrated through the Go programming language, its standard library, and popular third-party packages for concepts. Begin by understanding basic concepts such as clients, servers, and communication methods. Explore RESTful APIs and HTTP, the backbone of many systems. Learn about protocol buffers and gRPC for efficient data exchange. For asynchronous communication, discover message queuing with RabbitMQ and event-driven patterns with Redis. Lastly, explore event-driven architecture (EDA) and Apache Kafka for implementing this style of communication. Modern software architecture often consists of multiple services that communicate with each other. Designing and building efficient and performant inter-service communication is essential. Without it, a solution will not provide a proper user experience. The Go programming language has become the preferred language for backend services due to its simplicity, efficiency, and concurrency support. A combination of well-designed inter-service communication systems and the Go programming language can create powerful software solutions. This book was created to provide a guide for multiple inter-service communication concepts, including their advantages, disadvantages, and typical uses. All presented concepts will be covered with practical examples and implementations in the Go programming language. Implementations combine the Go standard library and third-party packages (when the standard library does not support a specific concept or the third-party package provides a more efficient solution).

Название: C++ Cookbook: How to write great code with the latest C++ releases
Автор: Wayne Murphy
Издательство: BPB Publications
Год: 2024
Страниц: 1308
Язык: английский
Формат: pdf, epub
Размер: 32.6 MB

Getting up to speed with the latest C++ features. C++ continues to remain relevant despite the advent of many new modern languages. This book dives into the significant features of C++20 ("big four") and C++23, addressing challenges and improving development. You will learn how to write cleaner, more efficient, and safer code. From organizing your projects better to handling complex tasks easily, this guide equips you to take your C++ skills to the next level. We start by discussing basic concepts and learning how to use them in templates. Then, we explore advanced topics like asynchronous programming with coroutines and tools for handling multiple tasks at once. You will discover C++ modules for building modular applications to organize code better. You will learn about ranges for processing data sequences efficiently, including views and adaptors for transforming and filtering data. Further, you will explore new features for containers, cleaner coding practices, and performance optimizations in C++20/23. The book outlines new features, with lots of code examples. They can use it as a reference guide, or progress through each how-to recipe to maximize their knowledge. This book empowers C++ programmers, from experienced professionals to those looking to level up their skills, by teaching the latest features for writing cleaner, more efficient, and powerful C++ code.

Название: Interactive Web Development With Three.js and A-Frame: Create Captivating Visualizations and Projects in Immersive Creative Technology for 3D, WebAR, and WebVR Using Three.js and A-Frame
Автор: Alessandro Straccia
Издательство: Orange Education Pvt Ltd, AVA
Год: 2024
Страниц: 350
Язык: английский
Формат: pdf, epub (true)
Размер: 11.8 MB

Build rich Creative Technology projects using 3D, AR, and VR. Creative Development is a relatively lesser-known area in software development. It involves various creative tools glued together with coding languages. While you don’t need to be a master in 3D, design, or even sound design to be a good creative developer, it’s important to know the basics of all these areas and, especially, understand how to put them together to build amazing Creative Dev apps. This book focuses on web tools – specifically Three.js and A-Frame – due to their popularity and relatively low learning curve, basically relying on HTML, CSS, and jаvascript. This book is organized into nine chapters to guide you from the basics of Three.js to more complex and specialized lessons. By the end of this book, you will be able to build Creative Development apps based on the web, both for desktop and mobile platforms. You will learn to interact with rich content such as 3D assets, videos, and more. Even if you are an experienced Three.js developer, this book contains useful examples and templates that will help you enhance your own projects.

Название: Ultimate Microservices with Go: Combine the Power of Microservices with Go to Build Highly Scalable, Maintainable, and Efficient Systems
Автор: Nir Shtein
Издательство: Orange Education Pvt Ltd, AVA
Год: 2024
Страниц: 257
Язык: английский
Формат: pdf, epub (true), mobi
Размер: 10.1 MB

Develop production-ready, high-performance, and scalable microservices with Go. Embark on a comprehensive journey through microservices architecture with a focus on harnessing the power of Go in modern cloud-based solutions. This book begins with a succinct introduction to microservices and their synergy with cloud strategies, emphasizing Go's aptitude for developing scalable and efficient services. You'll then delve into the fundamentals of Go, covering essential practices and core concepts, establishing a strong language foundation. The exploration continues with a detailed examination of constructing a single service, emphasizing design, documentation, and structure. Through various design patterns, you'll learn to implement a server capable of serving as a RESTful API, an internal worker, and more. This hands-on approach equips you with the expertise to craft robust and sustainable services. Throughout this book, we will explore the essentials of Go programming, delve into advanced topics, and navigate the complexities of building and deploying microservices. We will emphasize the strong connection between microservices, Go, RESTful APIs, and Kubernetes, covering key areas such as service communication, API design, container orchestration, security, and observability. By the end of this journey, you will have a solid grasp of architecting and implementing microservices using Go, preparing you to tackle the challenges of efficiently bringing your services to production. Finally, the book guides you through deploying your service to production using Kubernetes. You'll explore scaling techniques, performance optimization, and observability, ensuring your service is ready for the demands of the real world.

Название: Monte Carlo with Python: A comprehensive Guide to Building Monte Carlo Simulations with Python
Автор: Hayden Van Der Post
Издательство: Reactive Publishing
Год: 2024
Страниц: 430
Язык: английский
Формат: pdf, epub, mobi
Размер: 10.1 MB

Unlock the Power of Monte Carlo Simulations Using Python. Dive into the world of probabilistic modeling and numerical analysis with "Monte Carlo with Python," your comprehensive guide to mastering Monte Carlo methods. This book is meticulously crafted for professionals, academics, and enthusiasts eager to harness the capabilities of Python for complex statistical modeling and decision-making processes. Grasping the basics of Python's data types, variables, and operators is indispensable for anyone looking to employ Monte Carlo simulations in their projects. This understanding not only aids in crafting efficient simulation models but also enhances the ability to debug and optimize existing code. As we continue to explore Python's capabilities in subsequent sections, these foundational concepts will serve as the underpinnings for more advanced programming tasks, ensuring that each simulation is built on a robust and error-resilient framework. Whether you are a data scientist, a finance professional, or a student of quantitative disciplines, "Monte Carlo with Python" provides the tools you need to excel in your field. Elevate your analytical skills, enhance your understanding of risk and uncertainty, and make informed decisions using the power of Python and Monte Carlo simulations.

Название: Deep Learning in Medical Image Analysis: Recent Advances and Future Trends
Автор: R. Indrakumari, T. Ganesh Kumar, D. Murugan, Sherimon P.C.
Издательство: CRC Press
Серия: Artificial Intelligence in Smart Healthcare Systems
Год: 2025
Страниц: 197
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB

The proposed book is designed as a reference text and provides a comprehensive overview of conceptual and practical knowledge about Deep Learning in medical image processing techniques. The post-pandemic situation teaches us the importance of doctors, medical analysis, and diagnosis of diseases in a rapid manner. This book provides a snapshot of the state of current research between Deep Learning, medical image processing, and healthcare with special emphasis on saving human life. The chapters cover a range of advanced technologies related to patient health monitoring, predicting diseases from genomic data, detecting artefactual events in vital signs monitoring data, and managing chronic diseases. Deep Learning, a subtype of Machine Learning, uses deep neural networks, which are neural networks with several layers. Deep Learning algorithms can learn from vast amounts of data and can automatically extract complex features and patterns from the input data. The layers of interconnected neurons that make up deep neural networks each process the output from the layer before it. Depending on how difficult the problem being handled is, a deep neural network may have a few, hundreds, or even thousands of layers. Deep Learning has had great success in many different areas, including natural language processing, recognizing images, and recognizing speech. Deep neural networks, for instance, have been applied to create extremely precise image identification systems, such as those used in self-driving cars and facial recognition technology.

Название: Core Java, Volume II: Advanced Features, 13th Edition (Early Release)
Автор: Cay S. Horstmann
Издательство: Oracle Press/Pearson Education
Год: 2024
Страниц: 944
Язык: английский
Формат: epub
Размер: 19.2 MB

The Classic Guide to Advanced Java Programming: Fully Updated for Java 21. Core Java is the leading no-nonsense tutorial and reference for experienced programmers who want to write robust Java code for real-world applications. Now, Core Java, Volume II: Advanced Features, Thirteenth Edition, has been revised to cover the new features and enhancements in the Java 21 long-term support release. As always, all chapters have been completely updated, outdated material has been removed, and the new APIs are covered in detail. This volume focuses on the advanced topics that a programmer needs to know for professional software development and includes authoritative coverage of enterprise programming, networking, databases, security, modularization, internationalization, code processing, and native methods, as well as complete chapters on the Streams, XML, and Date and Time APIs. In addition, the chapters on Swing and Graphics cover techniques that are applicable to both client-side user interfaces and server-side generation of graphics and images. Cay S. Horstmann clearly explains sophisticated new features with depth and completeness and demonstrates how to use them to build professional-quality applications. Horstmann's thoroughly tested sample code reflects modern Java style and best practices. The examples are carefully crafted for easy understanding and maximum practical value, so you can rely on them to jump-start your own programs.

Название: What Is LLMOps? Large Language Models in Production
Автор: Abi Aryan
Издательство: O’Reilly Media, Inc.
Год: 2024-05-03
Язык: английский
Формат: pdf, azw3, epub, mobi
Размер: 10.1 MB

Large language models (LLMs), a subcategory of Generative AI, have taken the world by storm. Commonly known for their application in ChatGPT, LLMs have unleashed new energy among developers and businesses looking to integrate AI into their applications. But the internet is also full of disjointed information about LLM applications and how to integrate and deploy them reliably into products and applications. A large language model (LLM) is a statistical model trained on large amounts of text data to emulate human speech for natural language processing (NLP) tasks, such as information extraction, text classification, speech synthesis, summarization, and machine translation. LLMOps, thus, is a framework to automate and streamline large language model (also called a foundational or generative AI model) pipelines. While task-specific models for natural language processing (NLP) have been used in practice for a while, recent advances in NLP have shifted public interest to more task-agnostic models that allow a single model to do all of the tasks listed in the preceding paragraph. LLMs show remarkable performance at programming and coding, due to their capacity for context understanding and syntax awareness. Programming is a highly autoregressive task (i.e., it looks at the previous word to predict the next one), such that code completion is based on previous code elements in the sequence. LLMs, being naturally autoregressive, perform well at autocompleting code snippets to generate syntactically accurate code, drawing on patterns learned from vast repositories of code examples from GitHub or otherwise.