Name: ONNX.js Web Deployment: Building Machine Learning Apps for the Browser (en Inglés)
SKU: 68986799
Price: 53.31 USD
Availability: InStock
Author: Johnson, Robert U.
ISBN: 9798173369604

portada ONNX.js Web Deployment: Building Machine Learning Apps for the Browser (en Inglés)

ONNX.js Web Deployment: Building Machine Learning Apps for the Browser (en Inglés)

Formato

Libro Físico

Editorial

Independently published

Autor

Johnson, Robert U.

Idioma

Inglés

N° páginas

241

Encuadernación

Tapa Blanda

ISBN13

9798173369604

ONNX.js Web Deployment: Building Machine Learning Apps for the Browser (en Inglés)

Johnson, Robert U. (Autor) · Independently published · Tapa Blanda

Libro Nuevo Importado

Envío: 18 a 25 días háb.

$ 96.93$ 53.31

-45%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan más de 100 unidades

$ 53.31

Llega entre el 30 Oct y el 16 Nov a Quito, Pichincha. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "ONNX.js Web Deployment: Building Machine Learning Apps for the Browser (en Inglés)"

“ONNX.js Web Deployment: Building Machine Learning Apps for the Browser” is a practical guide for developers and data scientists who want to bring machine learning directly into modern web applications. The book introduces the ONNX ecosystem, explains the value of client-side inference, and shows how ONNX.js fits into the broader landscape of browser-based AI tools such as TensorFlow.js and WebDNN. Readers will gain a clear understanding of how to run models efficiently in the browser while delivering responsive, private, and interactive user experiences. The book covers the full workflow for building browser ML applications, from setting up a development environment with JavaScript, WebAssembly, and WebGL to converting, optimizing, and debugging models for web deployment. It explores ONNX.js architecture in depth, including backend design, kernel execution, tensor memory management, and error handling, while also offering practical guidance on performance tuning, quantization, backend selection, and model lifecycle management for resource-constrained environments. Through real-world examples and case studies, readers will learn how to build in-browser AI applications for computer vision, natural language processing, predictive analytics, and more. The book also addresses secure and compliant client-side deployment, integration with modern web frameworks, progressive web apps, and model delivery pipelines. It concludes with an outlook on emerging technologies such as WebGPU, federated learning, and enterprise-scale adoption, equipping readers to build the next generation of machine learning apps for the browser.