Все для школьников, студентов, учащихся, преподавателей и родителей - Обучалка - Obuchalka.org

GPT-4, Руководство по использованию API Open AI, Аймен Эль Амри, 2024.
     
   В книге рассказывается о том, как использовать генеративные текстовые модели поколений GPT-3.5 и GPT-4 для создания приложений различного назначения, в числе которых интерактивный психотерапевт, интеллектуальный голосовой помощник, система рекомендации товаров, генератор заметок в соцсетях, система распознавания речи и многие другие. Вы научитесь использовать векторные базы данных, узнаете, как управлять уровнем креативности моделей GPT, применять современные методы генерирования высококачественного текста, и даже организуете диалог между двумя чат-ботами. Примеры и практические упражнения помогут закрепить пройденный материал.
Издание предназначено для тех, кто владеет основами языка программирования Python и собирается использовать GPT в реальных сценариях для решения прикладных задач.

GPT-3, Руководство по использованию API Open AI, Кублик С., Сабу Ш., 2023.
     
   В книге исследуется мощная языковая модель GPT-3, упрощающая создание приложений с искусственным интеллектом. Рассматриваются основы API OpenAI и инновационные способы использования этого инструмента в разных областях, в частности для создания новых бизнес-продуктов. Обсуждается влияние GPT-3 на развитие мировой экономики и такие передовые тенденции, как программирование без кода и достижение общего искусственного интеллекта.
Издание рассчитано на читателей, интересующихся современными технологиями, в частности предпринимателей, деятельность которых связана с индустрией искусственного интеллекта, а также тех, кто планирует использовать языковые способности GPT-3 для реализации творческих проектов.

Deep Learning Demystified, A Step-by-Step Introduction to Neural Networks, Shin K., 2024.
     
    This book is for anyone who wants to understand the basics of neural networks and deep learning. Whether you are a student, a professional, or a hobbyist, this book is designed to help you grasp the foundational concepts of neural networks. If you have little to no prior knowledge of artificial intelligence but are eager to learn, this book will provide you with the necessary tools and understanding to start your journey. Additionally, if you already have some experience with machine learning and want to deepen your knowledge of neural networks, this book will offer valuable insights and practical knowledge.

Building Applications with Large Language Models, Singh B., 2024.
     
    This book is your guide in understanding different ways in which Large Language Models, like GPT, BERT, Claude, LLaMA, etc., can be utilized for building something useful. It takes you on a journey starting from very basic, like understanding the basic models in NLP, to complex techniques, like PEFT, RAG, Prompt Engineering, etc. Throughout the book, you will find several examples and code snippets which will help you appreciate the state-of-the-art NLP models. Whether you’re a student trying to get hold of the new technology, a data scientist transitioning to the field of NLP, or simply someone who is inquisitive about Large Language Models (LLMs), this book will build your concepts and equip you with the knowledge required to start building your own applications using LLMs.

Build Your Own Neural Networks, Step-By-Step Explanation For Beginners, Shin K., 2024.
     
    "Build Your Own Neural Networks: Step-By-Step Explanation For Beginners" is designed to demystify the complexities of neural networks for those who are new to the field of deep learning. This book is your comprehensive guide to understanding and implementing neural networks from the ground up, using the PyTorch framework. Each chapter is structured to provide hands-on experience with practical code examples, detailed step-by-step explanations, and engaging mini-projects that ensure a practical understanding of the concepts discussed. This approach not only enhances learning but also makes the journey fun and interactive. By avoiding complex jargon and focusing on clear, simple explanations, we ensure that you gain a solid foundation in neural networks without feeling overwhelmed.

AI-Powered Search, Grainger T., Turnbull D., Irwin M., 2025.
     
    Modern search is more than keyword matching. Much, much more. Search that learns from user interactions, interprets intent, and takes advantage of AI tools like large language models (LLMs) can deliver highly targeted and relevant results. Th is book shows you how to up your search game using state-of-the-art AI algorithms, techniques, and tools.
AI-Powered Search teaches you to create a search that understands natural language and improves automatically the more it is used. As you work through dozens of interesting and relevant examples, you’ll learn powerful AI-based techniques like semantic search on embeddings, question answering powered by LLMs, real-time personalization, and Retrieval Augmented Generation (RAG).

Advanced Techniques in Optimization for Machine Learning and Imaging, Benfenati A., Porta F., 2024.
     
    In recent years, non-linear optimization has had a crucial role in the development of modern techniques at the interface of machine learning and imaging. The present book is a collection of recent contributions in the field of optimization, either revisiting consolidated ideas to provide formal theoretical guarantees or providing comparative numerical studies for challenging inverse problems in imaging. The work of these papers originated in the INdAM Workshop “Advanced Techniques in Optimization for Machine learning and Imaging” held in Roma, Italy, on June 20–24, 2022.

Advanced Image Processing with Python and OpenCV, Chesterfield G., 2024.
     
    Image processing is a powerful technology that has evolved significantly over the past few decades. It involves the manipulation of digital images through various algorithms to enhance or extract information from them. At its core, image processing can be defined as the process of converting an image into a form that is suitable for analysis. This transformation is often necessary because raw images captured by cameras can be noisy, distorted, or lack the clarity needed for various applications.