Big data
Gian Marco Iodice, Ronan Naughton
This book explores TinyML, a fast-growing field at the unique intersection of machine learning and embedded systems to make AI ubiquitous with extremely low-powered devices such as microcontrollers.The TinyML Cookbook starts with a practical introduction to this multidisciplinary field to get you up to speed with some of the fundamentals for deploying intelligent applications on Arduino Nano 33 BLE Sense and Raspberry Pi Pico. As you progress, you’ll tackle various problems that you may encounter while prototyping microcontrollers, such as controlling the LED state with GPIO and a push-button, supplying power to microcontrollers with batteries, and more. Next, you’ll cover recipes relating to temperature, humidity, and the three “V” sensors (Voice, Vision, and Vibration) to gain the necessary skills to implement end-to-end smart applications in different scenarios. Later, you’ll learn best practices for building tiny models for memory-constrained microcontrollers. Finally, you’ll explore two of the most recent technologies, microTVM and microNPU that will help you step up your TinyML game.By the end of this book, you’ll be well-versed with best practices and machine learning frameworks to develop ML apps easily on microcontrollers and have a clear understanding of the key aspects to consider during the development phase.
Gian Marco Iodice
Discover the incredible world of tiny Machine Learning (tinyML) and create smart projects using real-world data sensors with the Arduino Nano 33 BLE Sense, Raspberry Pi Pico, and SparkFun RedBoard Artemis Nano.TinyML Cookbook, Second Edition, will show you how to build unique end-to-end ML applications using temperature, humidity, vision, audio, and accelerometer sensors in different scenarios. These projects will equip you with the knowledge and skills to bring intelligence to microcontrollers. You'll train custom models from weather prediction to real-time speech recognition using TensorFlow and Edge Impulse.Expert tips will help you squeeze ML models into tight memory budgets and accelerate performance using CMSIS-DSP.This improved edition includes new recipes featuring an LSTM neural network to recognize music genres and the Faster-Objects-More-Objects (FOMO) algorithm for detecting objects in a scene. Furthermore, you’ll work on scikit-learn model deployment on microcontrollers, implement on-device training, and deploy a model using microTVM, including on a microNPU. This beginner-friendly and comprehensive book will help you stay up to date with the latest developments in the tinyML community and give you the knowledge to build unique projects with microcontrollers!
TinyML. Wykorzystanie TensorFlow Lite do uczenia maszynowego na Arduino i innych mikrokontrolerach
Pete Warden, Daniel Situnayake
Może się wydawać, że profesjonalne systemy uczenia maszynowego wymagają sporych zasobów mocy obliczeniowej i energii. Okazuje się, że niekoniecznie: można tworzyć zaawansowane, oparte na sieciach neuronowych aplikacje, które doskonale poradzą sobie bez potężnych procesorów. Owszem, praca na mikrokontrolerach podobnych do Arduino lub systemach wbudowanych wymaga pewnego przygotowania i odpowiedniego podejścia, jest to jednak fascynujący sposób na wykorzystanie niewielkich urządzeń o niskim zapotrzebowaniu na energię do tworzenia zdumiewających projektów. Ta książka jest przystępnym wprowadzeniem do skomplikowanego świata, w którym za pomocą techniki TinyML wdraża się głębokie uczenie maszynowe w systemach wbudowanych. Nie musisz mieć żadnego doświadczenia z zakresu uczenia maszynowego czy pracy z mikrokontrolerami. W książce wyjaśniono, jak można trenować modele na tyle małe, by mogły działać w każdym środowisku - również Arduino. Dokładnie opisano sposoby użycia techniki TinyML w tworzeniu systemów wbudowanych opartych na zastosowaniu ucze nia maszynowego. Zaprezentowano też kilka ciekawych projektów, na przykład dotyczący budowy urządzenia rozpoznającego mowę, magicznej różdżki reagującej na gesty, a także rozszerzenia możliwości kamery o wykrywanie ludzi. W książce między innymi: praca z Arduino i innymi mikrokontrolerami o niskim poborze mocy podstawy uczenia maszynowego, budowy i treningu modeli TensorFlow Lite i zestaw narzędzi Google dla TinyML bezpieczeństwo i ochrona prywatności w aplikacji optymalizacja modelu tworzenie modeli do interpretacji różnego rodzaju danych Ograniczone zasoby? Poznaj TinyML!
Tomographic imaging in environmental, industrial and medical applications
Tomasz Rymarczyk
Monografia przedstawia szeroki zakres dziedzin, w których znajduje zastosowanie tomografia. W nowatorski sposób prezentuje ważne zagadnienia z zakresu rozwiązywania problemów odwrotnych w tomografii przemysłowej oraz prototypów, pomiarów i modeli układów złożonych. Rozważania i dogłębna analiza numeryczna zastosowana na potrzeby rozwiązania problemu naprzód i odwrotnego czynią tę pracę wyjątkową w skali krajowej i międzynarodowej. Autor wniósł znaczący wkład w rozwój naukowej dyscypliny: Informatyka w aspekcie praktycznych zastosowań, zarówno przemysłowych, jak i medycznych. Używał tomografii procesowej do badania bardzo dużych obiektów. Obiekty te to wielohektarowe obszary położone w znacznej odległości od siebie. To innowacyjne zastosowanie tomografii procesowej
Train Your Own GPT. How to Train ChatGPT to Think Like You
MrExcel's Holy Macro! Books, Bill Jelen
This book offers a hands-on guide to building GPTs that learn, adapt, and respond in your unique style. It begins by breaking down how ChatGPT understands instructions, then guides readers through training personalized GPTs that automate tasks, create structured outputs, and integrate across business applications.Readers gain practical experience in linking GPTs with Excel, Power Automate, and APIs while exploring advanced memory, context, and action features. With clear guidance, examples, and exercises, the book bridges theory and application to make AI personalization achievable for any professional.By the end, readers can confidently design custom AI agents that extend beyond ChatGPT’s limits—capable of mirroring workflows, preferences, and communication style for real-world automation and creativity.
MrExcel's Holy Macro! Books, Mike Girvin
This book begins with the fundamentals, introducing key concepts like let expressions, keywords, and identifiers, before guiding you through more advanced techniques such as creating custom functions, handling diverse data types, and building reusable queries. Each chapter combines theoretical insights with practical examples, empowering you to handle complex data challenges with confidence.As you progress, you’ll learn how to master lookup formulas, manipulate data with unpivot, append, join, and group operations, and explore advanced table transformations. A dedicated section on data connectors provides in-depth knowledge of importing data from various sources and locales, ensuring flexibility and adaptability.The book concludes with practical data modeling projects that include handling inconsistent tables, appending multiple files, and building dynamic SharePoint connections. With a final focus on privacy levels and data security, this book equips you to use Power Query effectively and securely in real-world scenarios.
Denis Rothman
Transformers for Natural Language Processing and Computer Vision, Third Edition, explores Large Language Model (LLM) architectures, practical applications, and popular platforms (Hugging Face, OpenAI, and Google Vertex AI) used for Natural Language Processing (NLP) and Computer Vision (CV).The book guides you through a range of transformer architectures from foundation models and generative AI. You’ll pretrain and fine-tune LLMs and work through different use cases, from summarization to question-answering systems leveraging embedding-based search. You'll also implement Retrieval Augmented Generation (RAG) to enhance accuracy and gain greater control over your LLM outputs. Additionally, you’ll understand common LLM risks, such as hallucinations, memorization, and privacy issues, and implement mitigation strategies using moderation models alongside rule-based systems and knowledge integration.Dive into generative vision transformers and multimodal architectures, and build practical applications, such as image and video classification. Go further and combine different models and platforms to build AI solutions and explore AI agent capabilities.This book provides you with an understanding of transformer architectures, including strategies for pretraining, fine-tuning, and LLM best practices.
Denis Rothman, Antonio Gulli
Transformers are...well...transforming the world of AI. There are many platforms and models out there, but which ones best suit your needs?Transformers for Natural Language Processing, 2nd Edition, guides you through the world of transformers, highlighting the strengths of different models and platforms, while teaching you the problem-solving skills you need to tackle model weaknesses.You'll use Hugging Face to pretrain a RoBERTa model from scratch, from building the dataset to defining the data collator to training the model.If you're looking to fine-tune a pretrained model, including GPT-3, then Transformers for Natural Language Processing, 2nd Edition, shows you how with step-by-step guides.The book investigates machine translations, speech-to-text, text-to-speech, question-answering, and many more NLP tasks. It provides techniques to solve hard language problems and may even help with fake news anxiety (read chapter 13 for more details).You'll see how cutting-edge platforms, such as OpenAI, have taken transformers beyond language into computer vision tasks and code creation using DALL-E 2, ChatGPT, and GPT-4.By the end of this book, you'll know how transformers work and how to implement them and resolve issues like an AI detective.