product
1308204Hands-On Graph Neural Networks Using Pythonhttps://www.gandhi.com.mx/graph-neural-networks/phttps://gandhi.vtexassets.com/arquivos/ids/1167434/cd9600dc-2244-4871-ad4e-23d77eae8805.jpg?v=638337524027200000739821MXNPackt PublishingInStock/Ebooks/1297878Hands-On Graph Neural Networks Using Python739821https://www.gandhi.com.mx/graph-neural-networks/phttps://gandhi.vtexassets.com/arquivos/ids/1167434/cd9600dc-2244-4871-ad4e-23d77eae8805.jpg?v=638337524027200000InStockMXN99999DIEbook20239781804610701_W3siaWQiOiJiZDA4NDMxYi1iMDVmLTQyYTEtOGQwYi1jZjI4OTA2YjVhYjgiLCJsaXN0UHJpY2UiOjgyMSwiZGlzY291bnQiOjgyLCJzZWxsaW5nUHJpY2UiOjczOSwiaW5jbHVkZXNUYXgiOnRydWUsInByaWNlVHlwZSI6Ildob2xlc2FsZSIsImN1cnJlbmN5IjoiTVhOIiwiZnJvbSI6IjIwMjQtMDQtMDhUMTY6MDA6MDBaIiwicmVnaW9uIjoiTVgiLCJpc1ByZW9yZGVyIjpmYWxzZX1d9781804610701_<p><strong>Build previously impossible applications using graph data and become an expert in graph neural networks</strong></p><h4>Key Features</h4><ul><li>Learn the fundamentals of graph theory for data science and machine learning</li><li>Implement state-of-the-art graph neural network architectures</li><li>Build creative and powerful applications in various fields</li></ul><h4>Book Description</h4><p>Only ten years after their creation, graph neural networks have become one of the most interesting architectures in deep learning. They have revolutionized multi-billion-dollar industries like drug discovery, where they predicted a brand-new antibiotic named Halicin. Tech companies are now trying to apply them everywhere: recommender systems for food, videos, and romantic partners; fake news detection, chip design, and 3D reconstruction.</p><p>In Graph Neural Networks, we will explore the fundamentals of graph theory and create our own datasets from raw or tabular data. We will introduce major graph neural network architectures to understand crucial concepts like graph convolution and self-attention. This knowledge will then be applied to understand and implement more specialized models, designed for various tasks (including link prediction and graph classification) or contexts (spatio-temporal data, heterogeneous graphs, and so on). Finally, we will solve real-life problems using this technology and start building a professional portfolio.</p><p>By the end of this book, you will become a Graph Neural Network expert. You will be able to reframe your problems to leverage the unreasonable effectiveness of this architecture. With these skills, you will create unique solutions using novel, state-of-the-art approaches.</p><h4>What you will learn</h4><ul><li>Create your own graph datasets from tabular or raw data</li><li>Transform nodes and edges into high-quality embeddings</li><li>Implement graph neural networks using PyTorch Geometric</li><li>Select the best graph neural network model according to your problem</li><li>Perform tasks like node classification, graph generation, link prediction</li><li>Apply this knowledge to real use cases with raw data</li></ul><h4>Who This Book Is For</h4><p>If youre interested in machine learning, Graph Neural Networks will unlock a whole range of applications that were previously impossible. Students, data scientists, and machine learning and deep learning experts will find clear and illustrated explanations with code and notebooks to get a head start. With minimal knowledge of Python and linear algebra, you will acquire highly valuable expertise in one of the most popular architectures in AI.</p><h4>Table of Contents</h4><ol><li>Getting Started with Graph Learning</li><li>Graph Theory for Graph Neural Networks</li><li>Creating Node Representations with DeepWalk</li><li>Node2Vec</li><li>Vanilla Neural Network</li><li>Normalizing Features with Graph Convolutional Networks</li><li>Graph Attention Network</li><li>Scaling Graph Neural Networks</li><li>Graph Classification</li><li>Link Prediction</li><li>Graph Generation</li><li>Learning from Heterogeneous Graphs</li><li>Temporal Graph Neural Networks</li><li>Explainability</li><li>Traffic Forecasting</li><li>Anomaly Detection</li><li>Recommender Systems</li></ol>...(*_*)9781804610701_<p><b>Design robust graph neural networks with PyTorch Geometric by combining graph theory and neural networks with the latest developments and apps Purchase of the print or Kindle book includes a free PDF eBook</b></p><h2>Key Features</h2><ul><li>Implement -of-the-art graph neural architectures in Python</li><li>Create your own graph datasets from tabular data</li><li>Build powerful traffic forecasting, recommender systems, and anomaly detection applications</li></ul><h2>Book Description</h2>Graph neural networks are a highly effective tool for analyzing data that can be represented as a graph, such as networks, chemical compounds, or transportation networks. The past few years have seen an explosion in the use of graph neural networks, with their application ranging from natural language processing and computer vision to recommendation systems and drug discovery. Hands-On Graph Neural Networks Using Python begins with the fundamentals of graph theory and shows you how to create graph datasets from tabular data. As you advance, youll explore major graph neural network architectures and learn essential concepts such as graph convolution, self-attention, link prediction, and heterogeneous graphs. Finally, the book proposes applications to solve real-life problems, enabling you to build a professional portfolio. The code is readily available online and can be easily adapted to other datasets and apps. By the end of this book, youll have learned to create graph datasets, implement graph neural networks using Python and PyTorch Geometric, and apply them to solve real-world problems, along with building and training graph neural network models for node and graph classification, link prediction, and much more.<h2>What you will learn</h2><ul><li>Understand the fundamental concepts of graph neural networks</li><li>Implement graph neural networks using Python and PyTorch Geometric</li><li>Classify nodes, graphs, and edges using millions of samples</li><li>Predict and generate realistic graph topologies</li><li>Combine heterogeneous sources to improve performance</li><li>Forecast future events using topological information</li><li>Apply graph neural networks to solve real-world problems</li></ul><h2>Who this book is for</h2><p>This book is for machine learning practitioners and data scientists interested in learning about graph neural networks and their applications, as well as students looking for a comprehensive reference on this rapidly growing field. Whether youre new to graph neural networks or looking to take your knowledge to the next level, this book has something for you. Basic knowledge of machine learning and Python programming will help you get the most out of this book.</p>...9781804610701_Packt Publishinglibro_electonico_c4bdfdf1-a258-34af-b8e4-55bd7a19813a_9781804610701;9781804610701_9781804610701Maxime LabonneInglésMéxicohttps://getbook.kobo.com/koboid-prod-public/packt-epub-8bead78c-a94e-4455-9d83-c347404f5193.epub2023-04-14T00:00:00+00:00Packt Publishing