Название: Digital Watermarking for Machine Learning Model: Techniques, Protocols and Applications
Автор: Lixin Fan, Chee Seng Chan, Qiang Yang
Издательство: Springer
Год: 2023
Страниц: 233
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB

Machine Learning (ML) models, especially large pretrained Deep Learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR). Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model’s owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, Natural Language Processing (NLP) and Reinforcement Learning.

Название: Artificial Intelligence for Smart Manufacturing: Methods, Applications, and Challenges
Автор: Kim Phuc Tran
Издательство: Springer
Год: 2023
Страниц: 271
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

This book provides readers with a comprehensive overview of the latest developments in the field of smart manufacturing, exploring theoretical research, technological advancements, and practical applications of AI approaches. With Industry 4.0 paving the way for intelligent systems and innovative technologies to enhance productivity and quality, the transition to Industry 5.0 has introduced a new concept known as Augmented Intelligence (AuI), combining Artificial Intelligence (AI) with Human Intelligence (HI).

Название: 60 ChatGPT Prompts for Data Science
Автор: Travis Tang
Издательство: Independently published
Год: 2023
Язык: английский
Формат: pdf
Размер: 11.1 MB

The ChatGPT model is a large language model trained by OpenAI that is capable of generating human-like text. By providing it with a prompt, it can generate responses that continue the conversation or expand on the given prompt. In this book, you will find prompts that can be used with ChatGPT for data science purposes. It is curated by Travis Tang. To get started, simply use the prompts below as input for ChatGPT. Replace everything in [squarebrackets] with your own to achieve results specific to your use case.

Название: Intelligent Technologies: Concepts, Applications, and Future Directions, Volume 2
Автор: Satya Ranjan Dash, Himansu Das, Kuan-Ching Li
Издательство: Springer
Серия: Studies in Computational Intelligence
Год: 2023
Страниц: 260
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

This book discusses automated computing systems which are mostly powered by intelligent technologies like Artificial Intelligence, Machine Learning, image recognition, speech processing, cloud computing, etc., to perform complex automated tasks which are not possible by traditional computing systems. The chapters are extended version of research works presented at second PhD Research Symposium in various advanced technologies used in the field of Computer Science. This book provides an opportunity for the researchers to get ideas regarding the ongoing works that help them in formulating problems of their interest. The academicians can also be benefited to know about the current research trends that smooth the way to guide their students to carry out research work in the proper direction. The industry people will be also facilitated to know about the current advances in research work and materialize the research work into industrial applications.

Название: Visual Studio for Mac Succinctly
Автор: Alessandro Del Sole
Издательство: Syncfusion Inc.
Год: 2021
Страниц: 115
Язык: английский
Формат: pdf (true)
Размер: 10.3 MB

Visual Studio for Mac is an integrated development environment that can be used on macOS to build apps in C# and F# with a native user interface and tools tailored for macOS and for cross-platform development. Alessandro Del Sole provides a guide to this latest VS product, paying particular attention to the Integrated Development Environment, the workspace, and all the integrated tools you can leverage to build high-quality, professional applications for mobile devices and the web. Visual Studio for Mac Succinctly also includes an introduction to building apps with Xamarin and .NET Core and has been updated for the last version of the IDE. Visual Studio for Mac is the latest addition to the Microsoft Visual Studio family, and it allows you to reuse your existing development skills on macOS for cross-platform development. This chapter provides an introduction to Visual Studio for Mac, with an overview of the scenarios it best fits in and how to configure your Mac for development.

Название: Clojure
Автор: Karthikeyan A.K.
Издательство: Independently published
Год: 2023
Страниц: 172
Язык: английский
Формат: pdf (true)
Размер: 11.3 MB

Many hackers swear by LISP, and just like any other programmer coming from OOPS background I was skeptical about functional programming. When I started learning it, it wasn't straight forward (for an OOP developer), but I persisted and when I reached what's called REPL driven development I was blown away. Clojure is a dialect of LISP, and it was smartly designed to be hosted and not compiled, which means that when you learn it, you can target multiple platforms like Java runtime, Common Language Runtime, jаvascript and Dart platforms, hence your job potential will be huge. Clojure and all LISP based languages, surprisingly has only one syntax, which makes it simple and unimaginably powerful, and hence makes it easier to learn compared to other languages, and hence I feel it could be great first programming language for many who had never coded before.

Название: Azure Durable Functions Succinctly
Автор: Massimo Bonanni
Издательство: Syncfusion Inc.
Год: 2022
Страниц: 101
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

Durable Functions is an Azure Functions extension that implements triggers and bindings that abstract and manage state persistence. Using Durable Functions, you can easily create stateful objects entirely managed by the extension. Azure Durable Functions Succinctly author Massimo Bonanni will take readers from a recap of Azure Functions through Durable entities so that you can determine if this technology is right for your needs. Azure Functions is one of the most important serverless technologies proposed by Azure. Even though this book is not directly about standard Azure functions, it is fundamental to recap what an Azure function is. As we will see in the following chapters, Durable Functions is based on Azure Functions, so all the basic behavior is the same. An Azure function is literally a snippet of code that executes on a runtime called Azure Functions Runtime and can be written in several programming languages (C#, jаvascript, TypeScript, F#, Java, Python, PowerShell).

Название: MonoGame Roleplaying Game Development Succinctly
Автор: Jim Perry, Charles Humphrey
Издательство: Syncfusion Inc.
Год: 2022
Страниц: 154
Язык: английский
Формат: pdf (true), epub
Размер: 12.7 MB

For MonoGame developers looking to build their own role-playing game, this ebook is an essential guide. Authors Jim Perry and Charles Humphrey break down design complexities into smaller topics that are easy to think through to help you produce a working game. Learn how to animate sprites, construct conversation trees, build multilevel maps, manage combat, and much more, all on top of the MonoGame framework.

Название: Enhancing Surrogate-Based Optimization Through Parallelization
Автор: Frederik Rehbach
Издательство: Springer
Серия: Studies in Computational Intelligence
Год: 2023
Страниц: 123
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

This book presents a solution to the challenging issue of optimizing expensive-to-evaluate industrial problems such as the hyperparameter tuning of Machine Learning models. The approach combines two well-established concepts, Surrogate-Based Optimization (SBO) and parallelization, to efficiently search for optimal parameter setups with as few function evaluations as possible. Through in-depth analysis, the need for parallel SBO solvers is emphasized, and it is demonstrated that they outperform model-free algorithms in scenarios with a low evaluation budget. The SBO approach helps practitioners save significant amounts of time and resources in hyperparameter tuning as well as other optimization projects. As a highlight, a novel framework for objectively comparing the efficiency of parallel SBO algorithms is introduced, enabling practitioners to evaluate and select the most effective approach for their specific use case.

Название: Algorithmic Intelligence: Towards an Algorithmic Foundation for Artificial Intelligence
Автор: Stefan Edelkamp
Издательство: Springer
Год: 2023
Страниц: 482
Язык: английский
Формат: pdf (true)
Размер: 53.9 MB

In this book the author argues that the basis of what we consider computer intelligence has algorithmic roots, and he presents this with a holistic view, showing examples and explaining approaches that encompass theoretical Computer Science and Machine Learning via engineered algorithmic solutions. Part I of the book introduces the basics. The author starts with a hands-on programming primer for solving combinatorial problems, with an emphasis on recursive solutions. The other chapters in the first part of the book explain shortest paths, sorting, Deep Learning, and Monte Carlo search.