|
 |
|
 |
|
|
 |
|  |
|
 Название: Generative AI in Action (MEAP v5)
Автор: Amit Bahree
Издательство: Manning Publications
Год: 2024
Страниц: 266
Язык: английский
Формат: epub
Размер: 39.7 MB
Generative AI can transform your business by streamlining the process of creating text, images, and code. This book will show you how to get in on the action! Generative AI has created new opportunities for organizations of all sizes. You can easily use tools like ChatGPT, Bard, and Stable Diffusion to generate text and images for product catalogs, marketing campaigns, technical reporting, and other common tasks. Coding assistants like Copilot are accelerating productivity in software teams. In this insightful book, author Amit Bahree shares his experience leading Generative AI projects at Microsoft for nearly a decade, starting well before the current GPT revolution. Generative AI in Action shows you exactly how to add generative AI tools for text, images, and code, and more into your organization’s strategies and projects. The book begins with the fundamentals of generative AI models and architectures, and introduces practical use-cases to create efficient processes for marketing, software development, business report generation and other practical tasks. You’ll quickly master best practices for prompt engineering, model fine tuning and evaluation, and explore the emerging architecture patterns that support generative AI in your enterprise workflow. Along the way, you’ll explore important facts about AI safety and ethics, and look ahead to new trends such as explainable AI, transfer learning, and reinforcement learning. With a frank discussion of risks like hallucinations and jailbreaks, Generative AI in Action gives you the insight you need to incorporate these powerful technologies with confidence. For enterprise architects and senior developers interested in upgrading their architectures with generative AI. | |
Разместил: Ingvar16 14-04-2024, 15:16 | Комментарии: 0 | Подробнее
| | | |
 |
|  |
|
|
|
|
|
|
| |
|
 Название: Introduction to Data Science: A Python Approach to Concepts, Techniques and Applications 2nd Edition
Автор: Laura Igual, Santi Segui
Издательство: Springer
Серия: Undergraduate Topics in Computer Science
Год: 2024
Страниц: 255
Язык: английский
Формат: pdf
Размер: 10.1 MB
This accessible and classroom-tested textbook/reference presents an introduction to the fundamentals of the interdisciplinary field of Data Science. The coverage spans key concepts from statistics, Machine Learning/Deep Learning and responsible Data Science, useful techniques for network analysis and natural language processing (NLP), and practical applications of Data Science such as recommender systems or sentiment analysis. This book includes three different kinds of chapters. The first kind is about Python extensions. Python was originally designed to have a minimum number of data objects (int, float, string, etc.); but when dealing with data, it is necessary to extend the native set to more complex objects such as (NumPy) numerical arrays or (Pandas) data frames. The second kind of chapter includes techniques and modules to perform statistical analysis and Machine Learning. Finally, there are some chapters that describe several applications of Data Science, such as building recommenders or sentiment analysis. The composition of these chapters was chosen to offer a panoramic view of the Data Science field, but we encourage the reader to delve deeper into these topics and to explore those topics that have not been covered: big data analytics and more advanced mathematical and statistical methods (e.g., Bayesian statistics). This book is addressed to upper-tier undergraduate and beginning graduate students from technical disciplines. Moreover, this book is also addressed to professional audiences following continuous education short courses and to researchers from diverse areas following self-study courses. Basic skills in computer science, mathematics, and statistics are required. Code programming in Python is of benefit. | |
Разместил: Ingvar16 14-04-2024, 14:36 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
Название: Разработка мобильных и PC приложений на Python. Фреймворк Kivy
Автор: Алексей Ильющенко
Издательство: Stepik
Год: 2024
Формат: HTML
Страниц: много
Размер: 156 Mb
Язык: Русский
Курс по разработке мобильных и PC приложений на языке Python предназначен для тех, кто только начинает свой путь в этой области. Цель курса - научить студентов создавать мобильные приложения для различных операционных систем, используя язык программирования Python.
| |
Разместил: Chipa 14-04-2024, 11:00 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Causal AI (MEAP v9)
Автор: Robert Osazuwa Ness
Издательство: Manning Publications
Год: 2024
Страниц: 576
Язык: английский
Формат: epub
Размер: 39.0 MB
How do you know what might have happened, had you done things differently? Causal Machine Learning gives you the insight you need to make predictions and control outcomes based on causal relationships instead of pure correlation, so you can make precise and timely interventions. Causal Machine Learning is a major milestone in Machine Learning, allowing AI models to make accurate predictions based on causes rather than just correlations. Causal techniques help you make models that are more robust, explainable, and fair, and have a wide range of applications, from improving recommendation engines to perfecting self-driving cars. Causal AI teaches you how to build Machine Learning and Deep Learning models that implement causal reasoning. Discover why leading AI engineers are so excited by causal reasoning, and develop a high-level understanding of this next major trend in AI. New techniques are demonstrated with example models for solving industry-relevant problems. You’ll learn about causality for recommendations; causal modeling of online conversions; and uplift, attribution, and churn modeling. Each technique is tested against a common set of problems, data, and Python libraries, so you can compare and contrast which will work best for you. For data scientists and Machine Learning engineers. A familiarity with probability and statistics will be helpful, but not essential, to begin this guide. Examples in Python. | |
Разместил: Ingvar16 14-04-2024, 04:46 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Hacking Cryptography: Write, break, and fix real-world implementations (MEAP v9)
Автор: Kamran Khan, Bill Cox
Издательство: Manning Publications
Год: 2024
Страниц: 262
Язык: английский
Формат: pdf (true)
Размер: 16.6 MB
Learn how the good guys implement cryptography and how the bad guys exploit it. Theoretically strong cryptography often becomes vulnerable to exploitation as soon as it’s built into real applications and networks. Hacking Cryptography details dozens of practical cryptographic implementations and then breaks down the flaws that adversaries use to exploit them. You’ll learn just what it takes to write cryptographically secure code, build an intuition for spotting potential vulnerabilities, and master techniques to avoid the pitfalls that leave your systems at risk. Hacking Cryptography builds your understanding of cryptography by revealing the “lockpicks” that bad actors use to exploit security protocols, firewalls, and other cryptography-based protection schemes. The book dives deep into each cryptographic exploit, explaining complex concepts in detail through real-world analogies, code annotations, and pseudo-code. You’ll explore historical examples where popular cryptography has failed, such as the breaking of the WEP protocol, and see what impact those failures have had on modern cryptography. For software and security engineers. No advanced mathematical knowledge required. Examples in Go. | |
Разместил: Ingvar16 14-04-2024, 04:06 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Probabilistic Indexing for Information Search and Retrieval in Large Collections of Handwritten Text Images
Автор: Alejandro Hector Toselli, Joan Puigcerver, Enrique Vidal
Издательство: Springer
Год: 2024
Страниц: 372
Язык: английский
Формат: pdf (true)
Размер: 13.2 MB
This book provides a comprehensive presentation of a recently introduced framework, named "probabilistic indexing" (PrIx), for searching text in large collections of document images and other related applications. It fosters the development of new search engines for effective information retrieval from manuscripts which, however, lack the electronic text (transcripts) that would typically be required for such search and retrieval tasks. The book is structured into 11 chapters and three appendices. The first two chapters briefly outline the necessary fundamentals and state of the art in pattern recognition, statistical decision theory, and handwritten text recognition. Chapter 3 presents approaches for indexing (as opposed to “spotting”) each region of a handwritten text image which is likely to contain a word. Next, Chapter 4 describes models adopted for handwritten text in images, namely hidden Markov models, convolutional and recurrent neural networks and language models, and provides full details of weighted finite-state transducer (WFST) concepts and methods, needed in further chapters of the book. Chapter 5 explains the set of techniques and algorithms developed to generate image probabilistic indexes which allow for fast search and retrieval of textual information in the indexed images. This book is written for researchers and (post-)graduate students in pattern recognition and information retrieval. | |
Разместил: Ingvar16 14-04-2024, 03:28 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Deep Learning Models: A Practical Approach for Hands-On Professionals
Автор: Jonah Gamba
Издательство: Springer
Год: 2024
Страниц: 211
Язык: английский
Формат: pdf (true), epub
Размер: 65.3 MB
This book focuses on and prioritizes a practical approach, minimizing theoretical concepts to deliver algorithms effectively. With Deep Learning emerging as a vibrant field of research and development in numerous industrial applications, there is a pressing need for accessible resources that provide comprehensive examples and quick guidance. Unfortunately, many existing books on the market tend to emphasize theoretical aspects, leaving newcomers scrambling for practical guidance. This book takes a different approach by focusing on practicality while keeping theoretical concepts to a necessary minimum. The book begins by laying a foundation of basic information on Deep Learning, gradually delving into the subject matter to explain and illustrate the limitations of existing algorithms. A dedicated chapter is allocated to evaluating the performance of multiple algorithms on specific datasets, highlighting techniques and strategies that can address real-world challenges when Deep Learning is employed. The Chapter 2 introduce some of the concepts needed to start building Deep Learning models in Python. The chapter starts with basic principles related to data manipulation and ends with explanation on how to set up the modelling environment. It is expected that the reader is familiar with some high-level programming concepts which are very easy to acquire within a short space of time. Deep Learning models mostly deal with vectors and matrices as we know them from linear algebra. This book is designed to equip professionals with the necessary skills to thrive in the active field of Deep Learning, where it has the potential to revolutionize traditional problem-solving approaches. | |
Разместил: Ingvar16 13-04-2024, 19:06 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Designing Software Architectures: A Practical Approach, 2nd Edition (Early Release)
Автор: Humberto Cervantes, Rick Kazman
Издательство: Addison-Wesley Professional/Pearson Education
Год: 2024
Страниц: 312
Язык: английский
Формат: epub (true)
Размер: 28.5 MB
Successfully integrate practical designs that support the full software lifecycle! Designing Software Architectures, 2nd Edition, introduces a practical, step-by-step methodology for architecture design that any professional software engineer can use, with structured methods supported by reusable chunks of design knowledge and rich case studies that demonstrate how to use the methods. This newly updated edition reflects how contemporary architects are designing systems. You will find new chapters on supporting business agility through API-centric design, deployability, cloud-based solutions, and technical debt in design. This edition places more emphasis on the design of APIs for distributed systems so you can make design decisions in systematic, repeatable, and cost-effective ways. The Attribute-Driven Design method may not have changed since this book’s first printing, but almost everything else about the industry has. This book will help you become a better designer who can help pave the road from mediocrity to excellence and from a craft to a discipline of engineering. In the Chapter 1 we provide an introduction to the topic of software architecture and architecture design. We briefly discuss what architecture is and why it is fundamental to take it into account when developing software systems. We also discuss the activities that are associated with the development of software architecture so that architectural design—which is the primary topic of this book—can be understood in the context of these activities. We also briefly discuss the role of the architect, who is the person responsible for creating the design. Finally, we introduce the Attribute-Driven Design (ADD) method, the architecture design method that we will discuss extensively in this book. | |
Разместил: Ingvar16 13-04-2024, 16:32 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Generative Analysis: The Power of Generative AI for Object-Oriented Software Engineering with UML (Early Release)
Автор: Jim Arlow, Ila Neustadt
Издательство: Addison-Wesley Professional/Pearson Education
Год: 2024
Страниц: 512
Язык: английский
Формат: epub (true)
Размер: 67.4 MB
Learn a new method of object-oriented analysis called generative analysis and keep your skill-set on pace with how generative AI is transforming the face of software engineering. Generative AI is revolutionizing many industries, including software engineering. Many aspects of manual coding are becoming automated, and the skills needed by software engineers, developers, and analysts are evolving. Anyone who writes or works with code will need to produce precise analysis artifacts to feed the AI code generation process. Enter generative analysis: a precise, structured way to for software engineers, programmers, and analysts to transition to this new, AI-enhanced, software engineering world. In Generative Analysis, experts Jim Arlow and Ila Neustadt leverage literate modeling, M++, and multivalent logic to lay out a precise and structured, step-by-step approach to object-oriented analysis that produces clear and unambiguous results suitable for further processing into code by generative AI systems such as Copilot, ChatGPT, and Gemini. Ideally, you would be a business analyst who is also a competent programmer who is comfortable building models of software systems with the Unified Modeling Language (UML). We understand that this is a very big ask! However, you don’t need to be an expert programmer, you just need to be able to read code and understand UML artefacts without necessarily understanding the fine details. For code examples, we have chosen Python because this is probably the most easily readable programming language. | |
Разместил: Ingvar16 13-04-2024, 15:50 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
|
|
|
|
|
| |
|
 Название: Innovation in the University 4.0 System based on Smart Technologies
Автор: Shashi Kant Gupta, Joanna Rosak-Szyrocka
Издательство: CRC Press
Год: 2024
Страниц: 241
Язык: английский
Формат: pdf (true)
Размер: 36.2 MB
This text presents a comprehensive analysis of mathematical formulations for proving the effectiveness of Artificial Intelligence in education and investigates the possibilities for integrating advanced Artificial Intelligence algorithms. Artificial Intelligence (AI) in education signifies a paradigm shift in teaching and learning. A major driving force behind AI is the concept of neural networks and Deep Learning. These powerful tools enable AI applications to deliver personalized, dynamic, and engaging learning experiences. To understand the role of these technologies in education, we must first comprehend the basics. Neural networks are AI systems modeled after the human brain, consisting of interconnected layers of nodes, or “neurons,” that process information. These layers constitute an input layer, one or more hidden layers, and an output layer. Each node processes the input it receives and passes on the result, simulating the process of human brain cells transmitting signals. Deep Learning, a subset of Machine Learning, involves using neural networks with multiple hidden layers. The text is primarily written for graduate students, postgraduate students, and academic researchers working in the fields of Computer Science and engineering, information technology and Machine Learning. | |
Разместил: Ingvar16 13-04-2024, 06:24 | Комментарии: 0 | Подробнее
| | | |
|
| |
|
Навигация
Вход на сайт
Реклама
