Название: Understanding Large Language Models: Learning Their Underlying Concepts and Technologies
Автор: Thimira Amaratunga
Издательство: Apress
Год: 2023
Страниц: 166
Язык: английский
Формат: pdf (true), epub, mobi
Размер: 10.2 MB

This book will teach you the underlying concepts of large language models (LLMs), as well as the technologies associated with them.

The book starts with an introduction to the rise of conversational AIs such as ChatGPT, and how they are related to the broader spectrum of large language models. From there, you will learn about Natural Language Processing (NLP), its core concepts, and how it has led to the rise of LLMs. Next, you will gain insight into transformers and how their characteristics, such as self-attention, enhance the capabilities of language modeling, along with the unique capabilities of LLMs. The book concludes with an exploration of the architectures of various LLMs and the opportunities presented by their ever-increasing capabilities―as well as the dangers of their misuse. After completing this book, you will have a thorough understanding of LLMs and will be ready to take your first steps in implementing them into your own projects.

Today, finding someone who hasn’t heard of ChatGPT, the AI chatbot that took the world by storm, is hard. ChatGPT—and its competitors such as Google Bard, Microsoft Bing Chat, etc.—are part of a broader area in AI known as large language models (LLMs). LLMs are the latest frontier in AI, resulting from recent research into natural language processing (NLP) and deep learning. However, the immense popularity these applications have gained has created some concerns and misconceptions around them because of a lack of understanding of what they truly are. Understanding the concepts behind this new technology, including how it evolved, and addressing the misconceptions and genuine concerns around it are crucial for us to bring out its full potential. Therefore, this book was designed to provide a crucial overall understanding of large language models.

The main aim of Machine Learning (ML) is to provide machines with the ability to learn without explicit programming, in the hopes that such systems once built will be able to evolve and adapt when they are exposed to new data. The core idea is the ability of a learner to generalize from experience. The learner (the AI system being trained), once given a set of training samples, must be able to build a generalized model upon them, which would allow it to decide upon new cases with sufficient accuracy. Such training in ML can be provided in three main methods.

• Supervised learning: the system is given a set of labeled cases (training set) based on which the system is asked to create a generalized model that can act on unseen cases.
• Unsupervised learning: The system is given a set of unlabeled cases and asked to find a pattern in them. This is ideal for discovering hidden patterns.
• Reinforcement learning: The system is asked to take any action and is given a reward or a penalty based on how appropriate that action is to the given situation. The system must learn which actions yield the most rewards in given situations over time.

Machine Learning can also use a combination of these main learning methods, such as semi-supervised learning in which a small number of labeled examples are used with a large set of unlabeled data for training.

What You Will Learn:
Grasp the underlying concepts of LLMs
Gain insight into how the concepts and approaches of NLP have evolved over the years
Understand transformer models and attention mechanisms
Explore different types of LLMs and their applications
Understand the architectures of popular LLMs
Delve into misconceptions and concerns about LLMs, as well as how to best utilize them

Who This Book Is For:
Anyone interested in learning the foundational concepts of NLP, LLMs, and recent advancements of Deep Learning.




ОТСУТСТВУЕТ ССЫЛКА/ НЕ РАБОЧАЯ ССЫЛКА ЕСТЬ РЕШЕНИЕ, ПИШИМ СЮДА!