PyTorch Artificial Intelligence Fundamentals
暫譯: PyTorch 人工智慧基礎知識

Mathew, Jibin

PyTorch Artificial Intelligence Fundamentals
  • 出版商: Packt Publishing
  • 出版日期: 2020-02-28
  • 售價: $1,690
  • 貴賓價: 9.5 折 $1,606
  • 語言: 英文
  • 頁數: 200
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 1838557040
  • ISBN-13: 9781838557041
  • 相關分類: DeepLearning、人工智慧

    • 海外代購書籍(需單獨結帳)

相關主題

商品描述

Artificial Intelligence (AI) continues to grow in popularity and disrupt a wide range of domains, but it is a complex and daunting topic. In this book, you'll get to grips with building deep learning apps, and how you can use PyTorch for research and solving real-world problems.

 

This book uses a recipe-based approach, starting with the basics of tensor manipulation, before covering Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) in PyTorch. Once you are well-versed with these basic networks, you'll build a medical image classifier using deep learning. Next, you'll use TensorBoard for visualizations. You'll also delve into Generative Adversarial Networks (GANs) and Deep Reinforcement Learning (DRL) before finally deploying your models to production at scale. You'll discover solutions to common problems faced in machine learning, deep learning, and reinforcement learning. You'll learn to implement AI tasks and tackle real-world problems in computer vision, natural language processing (NLP), and other real-world domains.

 

By the end of this book, you'll have the foundations of the most important and widely used techniques in AI using the PyTorch framework.

商品描述(中文翻譯)

人工智慧 (AI) 持續在各個領域中增長其受歡迎程度並帶來顛覆，但這是一個複雜且令人畏懼的主題。在本書中，您將學會如何構建深度學習應用程式，以及如何使用 PyTorch 進行研究和解決現實世界中的問題。

本書採用食譜式的方法，從張量操作的基本概念開始，然後介紹在 PyTorch 中的卷積神經網絡 (CNN) 和遞迴神經網絡 (RNN)。一旦您熟悉這些基本網絡，您將使用深度學習構建一個醫療影像分類器。接下來，您將使用 TensorBoard 進行可視化。您還將深入探討生成對抗網絡 (GAN) 和深度強化學習 (DRL)，最後將您的模型部署到大規模的生產環境中。您將發現機器學習、深度學習和強化學習中常見問題的解決方案。您將學會實現 AI 任務並解決計算機視覺、自然語言處理 (NLP) 及其他現實世界領域中的問題。

在本書結束時，您將掌握使用 PyTorch 框架的最重要和最廣泛使用的 AI 技術的基礎知識。

作者簡介

Jibin Mathew is a senior data scientist and machine learning researcher who has worked in the AI domain for more than 7 years. He is a serial entrepreneur and has founded multiple AI start-ups. He has a strong software engineering background and understands the complete workflow, from research to scalable production deployment. He has built solutions in the fields of healthcare, environment, finance, industrial monitoring, and retail. He has been an adviser to various companies in their AI endeavors. He was the winner of Singularity University's Global Impact Challenge 2018 and has been part of various global platforms. He is an active contributor to the community and shares his knowledge by authoring content and through blog posts.

作者簡介(中文翻譯)

Jibin Mathew 是一位資深數據科學家和機器學習研究員，擁有超過 7 年的人工智慧（AI）領域工作經驗。他是一位連續創業家，創立了多家 AI 初創公司。他擁有堅實的軟體工程背景，了解從研究到可擴展生產部署的完整工作流程。他在醫療、環境、金融、工業監控和零售等領域構建了解決方案。他曾擔任多家公司的顧問，協助其 AI 相關的努力。他是 2018 年 Singularity University 全球影響挑戰賽的獲獎者，並參與了多個全球平台。他積極貢獻於社群，通過撰寫內容和部落格文章分享他的知識。

目錄大綱

  1. Working with Tensors Using PyTorch
  2. Dealing with Neural Networks
  3. Convolutional Neural Networks for Computer Vision
  4. Recurrent neural networks for NLP
  5. Transfer Learning and TensorBoard
  6. Exploring Generative Adversarial Networks
  7. Deep Reinforcement Learning
  8. Productionizing AI models in PyTorch

目錄大綱(中文翻譯)


  1. Working with Tensors Using PyTorch

  2. Dealing with Neural Networks

  3. Convolutional Neural Networks for Computer Vision

  4. Recurrent neural networks for NLP

  5. Transfer Learning and TensorBoard

  6. Exploring Generative Adversarial Networks

  7. Deep Reinforcement Learning

  8. Productionizing AI models in PyTorch

類似商品