Neural networks are getting smaller. Much smaller. The OK Google team, for example, has run machine learning models that are just 14 kilobytes in size--small enough to work on the digital signal processor in an Android phone. With this practical book, you'll learn about TensorFlow Lite for Microcontrollers, a miniscule machine learning library that allows you to run machine learning algorithms on tiny hardware.
Authors Pete Warden and Daniel Situnayake explain how you can train models that are small enough to fit into any environment, including small embedded devices that can run for a year or more on a single coin cell battery. Ideal for software and hardware developers who want to build embedded devices using machine learning, this guide shows you how to create a TinyML project step-by-step. No machine learning or microcontroller experience is necessary.
Learn practical machine learning applications on embedded devices, including simple uses such as speech recognition and gesture detection
Train models such as speech, accelerometer, and image recognition, you can deploy on Arduino and other embedded platforms
Understand how to work with Arduino and ultralow-power microcontrollers
Use techniques for optimizing latency, energy usage, and model and binary size
Chapter Goal: Introduce TensorFlow 2 and discuss preliminary material on conventions and practices specific to TensorFlow.
- Differences between TensorFlow iterations
- TensorFlow for economics and finance
- Introduction to tensors
- Review of linear algebra and calculus
- Loading data for use in TensorFlow
- Defining constants and variables
Chapter 2: Machine Learning and Economics
Chapter Goal: Provide a high-level overview of machine learning models and explain how they can be employed in economics and finance. Part of the chapter will review existing work in economics and speculate on future use-cases.
- Introduction to machine learning
- Machine learning for economics and finance
- Unsupervised machine learning
- Supervised machine learning
- Regularization
- Prediction
- Evaluation
Chapter 3: Regression
Chapter Goal: Explain how regression models are used primarily for prediction purposes in machine learning, rather than hypothesis testing, as is the case in economics. Introduce evaluation metrics and optimization routines used to solve regression models.
- Linear regression
- Partially-linear regression
- Non-linear regression
- Logistic regression
- Loss functions
- Evaluation metrics
- Optimizers
Chapter 4: Trees
Chapter Goal: Introduce tree-based models and the concept of ensembles.
- Decision trees
- Regression trees
- Random forests
- Model tuning
Chapter 5: Gradient Boosting
Chapter Goal: Introduce gradient boosting and discuss how it is applied, how models are tuned, and how to identify important features.
- Introduction to gradient boosting
- Boosting with regression models
- Boosting with trees
- Model tuning
- Feature importance
Chapter 6: Images
Chapter Goal: Introduce the high level Keras and Estimators APIs. Explain how these libraries can be used to perform image classification using a variety of deep learning models. Also, discuss the use of pretrained models and fine-tuning. Speculate on image classification uses in economics and finance.
- Keras
- Estimators
- Data preparation
- Deep neural networ
Автор: Boschetti Alberto, Massaron Luca, Thakur Abhishek Название: Tensorflow Deep Learning Projects ISBN: 1788398068 ISBN-13(EAN): 9781788398060 Издательство: Неизвестно Цена: 8091.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: This book is your guide to master deep learning with TensorFlow, with the help of 10 real-world projects. You will train high-performance models in TensorFlow to generate captions for images automatically, predict stocks` performance, create intelligent chatbots, perform large-scale text classification, develop recommendation systems, and more.
Build machine learning web applications without having to learn a new language. This book will help you develop basic knowledge of machine learning concepts and applications.
You'll learn not only theory, but also dive into code samples and example projects with TensorFlow.js. Using these skills and your knowledge as a web developer, you'll add a whole new field of development to your tool set. This will give you a more concrete understanding of the possibilities offered by machine learning. Discover how ML will impact the future of not just programming in general, but web development specifically.
Machine learning is currently one of the most exciting technology fields with the potential to impact industries from health to home automation to retail, and even art. Google has now introduced TensorFlow.js--an iteration of TensorFlow aimed directly at web developers. Practical Machine Learning in JavaScript will help you stay relevant in the tech industry with new tools, trends, and best practices.
What You'll Learn
Use the JavaScript framework for ML
Build machine learning applications for the web
Develop dynamic and intelligent web content
Who This Book Is For
Web developers and who want a hands-on introduction to machine learning in JavaScript. A working knowledge of the JavaScript language is recommended.
Описание: Python Machine Learning for BeginnersMachine Learning (ML) and Artificial Intelligence (AI) are here to stay. Yes, that's right. Based on a significant amount of data and evidence, it's obvious that ML and AI are here to stay.Consider any industry today. The practical applications of ML are really driving business results. Whether it's healthcare, e-commerce, government, transportation, social media sites, financial services, manufacturing, oil and gas, marketing and salesYou name it. The list goes on. There's no doubt that ML is going to play a decisive role in every domain in the future.But what does a Machine Learning professional do?A Machine Learning specialist develops intelligent algorithms that learn from data and also adapt to the data quickly. Then, these high-end algorithms make accurate predictions.
Python Machine Learning for Beginners presents you with a hands-on approach to learn ML fast.How Is This Book Different?AI Publishing strongly believes in learning by doing methodology. With this in mind, we have crafted this book with care. You will find that the emphasis on the theoretical aspects of machine learning is equal to the emphasis on the practical aspects of the subject matter.You'll learn about data analysis and visualization in great detail in the first half of the book. Then, in the second half, you'll learn about machine learning and statistical models for data science.Each chapter presents you with the theoretical framework behind the different data science and machine learning techniques, and practical examples illustrate the working of these techniques.When you buy this book, your learning journey becomes so much easier. The reason is you get instant access to all the related learning material presented with this book--references, PDFs, Python codes, and exercises--on the publisher's website. All this material is available to you at no extra cost. You can download the ML datasets used in this book at runtime, or you can access them via the Resources/Datasets folder.You'll also find the short course on Python programming in the second chapter immensely useful, especially if you are new to Python. Since this book gives you access to all the Python codes and datasets, you only need access to a computer with the internet to get started. The topics covered include:
Introduction and Environment Setup
Python Crash Course
Python NumPy Library for Data Analysis
Introduction to Pandas Library for Data Analysis
Data Visualization via Matplotlib, Seaborn, and Pandas Libraries
Solving Regression Problems in ML Using Sklearn Library
Solving Classification Problems in ML Using Sklearn Library
Data Clustering with ML Using Sklearn Library
Deep Learning with Python TensorFlow 2.0
Dimensionality Reduction with PCA and LDA Using Sklearn
Click the BUY NOW button to start your Machine Learning journey.
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data.
The updated edition of this practical book uses concrete examples, minimal theory, and three production-ready Python frameworks--scikit-learn, Keras, and TensorFlow--to help you gain an intuitive understanding of the concepts and tools for building intelligent systems. You'll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With exercises in each chapter to help you apply what you've learned, all you need is programming experience to get started.
Описание: This book is designed to guide you through TensorFlow 2 and how to use it effectively. Throughout the book, you will work through recipes and get hands-on experience to perform complex data computations, gain insights into your data, and more.
Описание: This volume reports on excavations in advance of the development of a site in Norton-on-Derwent, North Yorkshire close to the line of the main Roman road running from the crossing point of the River Derwent near Malton Roman fort to York. This site provided much additional information on aspects of the poorly understood `small town` of Delgovicia.
Описание: You will learn the principles of computer vision and deep learning, and understand various models and architectures with their pros and cons. You will learn how to use TensorFlow 2.x to build your own neural network model and apply it to various computer vision tasks such as image acquiring, processing, and analyzing.
Описание: This Workshop will teach you how to build deep learning models from scratch using real-world datasets with the TensorFlow framework. You will gain the knowledge you need to process a variety of data types, perform tensor computations, and understand the different layers in a deep learning model.
Companies are spending billions on machine learning projects, but it's money wasted if the models can't be deployed effectively. In this practical guide, Hannes Hapke and Catherine Nelson walk you through the steps of automating a machine learning pipeline using the TensorFlow ecosystem. You'll learn the techniques and tools that will cut deployment time from days to minutes, so that you can focus on developing new models rather than maintaining legacy systems.
Data scientists, machine learning engineers, and DevOps engineers will discover how to go beyond model development to successfully productize their data science projects, while managers will better understand the role they play in helping to accelerate these projects. The book also explores new approaches for integrating data privacy into machine learning pipelines.
Understand the machine learning management lifecycle
Implement data pipelines with Apache Airflow and Kubeflow Pipelines
Work with data using TensorFlow tools like ML Metadata, TensorFlow Data Validation, and TensorFlow Transform
Analyze models with TensorFlow Model Analysis and ship them with the TFX Model Pusher Component after the ModelValidator TFX Component confirmed that the analysis results are an improvement
Deploy models in a variety of environments with TensorFlow Serving, TensorFlow Lite, and TensorFlow.js
Learn methods for adding privacy, including differential privacy with TensorFlow Privacy and federated learning with TensorFlow Federated
Design model feedback loops to increase your data sets and learn when to update your machine learning models
ООО "Логосфера " Тел:+7(495) 980-12-10 www.logobook.ru
