Machine Learning in Elixir: Learning to Learn with Nx and Axon

Moriarity, Sean

Machine Learning in Elixir: Learning to Learn with Nx and Axon
  • 出版商: Pragmatic Bookshelf
  • 出版日期: 2024-10-01
  • 售價: $2,500
  • 貴賓價: 9.5 折 $2,375
  • 語言: 英文
  • 頁數: 374
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 9798888650349
  • ISBN-13: 9798888650349
  • 相關分類: Functional-programming、Machine Learning

    • 海外代購書籍(需單獨結帳)

相關主題

商品描述

Stable Diffusion, ChatGPT, Whisper - these are just a few examples of incredible applications powered by developments in machine learning. Despite the ubiquity of machine learning applications running in production, there are only a few viable language choices for data science and machine learning tasks. Elixir's Nx project seeks to change that. With Nx, you can leverage the power of machine learning in your applications, using the battle-tested Erlang VM in a pragmatic language like Elixir. In this book, you'll learn how to leverage Elixir and the Nx ecosystem to solve real-world problems in computer vision, natural language processing, and more.

The Elixir Nx project aims to make machine learning possible without the need to leave Elixir for solutions in other languages. And even if concepts like linear models and logistic regression are new to you, you'll be using them and much more to solve real-world problems in no time.

Start with the basics of the Nx programming paradigm - how it differs from the Elixir programming style you're used to and how it enables you to write machine learning algorithms. Use your understanding of this paradigm to implement foundational machine learning algorithms from scratch. Go deeper and discover the power of deep learning with Axon. Unlock the power of Elixir and learn how to build and deploy machine learning models and pipelines anywhere. Learn how to analyze, visualize, and explain your data and models.

Discover how to use machine learning to solve diverse problems from image recognition to content recommendation - all in your favorite programming language.

What You Need:

You'll need a computer with a working installation of Elixir v1.12 and Erlang/OTP 24. For some of the more compute intensive examples, you'll want to use EXLA, which currently only supports x86-64 platforms. While not explicitly required, some examples will demonstrate programs running on accelerators such as CUDA/ROCm enabled GPUs and Google TPUs. Most of these programs will still run fine on a regular CPU, just for much longer periods of time.

商品描述(中文翻譯)

Stable Diffusion、ChatGPT、Whisper——這些只是由機器學習發展驅動的驚人應用的一些例子。儘管機器學習應用在生產環境中無處不在，但在數據科學和機器學習任務中，只有少數幾種可行的語言選擇。Elixir 的 Nx 項目旨在改變這一點。使用 Nx，您可以在應用中利用機器學習的力量，並使用像 Elixir 這樣的實用語言中的經過考驗的 Erlang VM。在本書中，您將學習如何利用 Elixir 和 Nx 生態系統來解決計算機視覺、自然語言處理等現實世界中的問題。

Elixir Nx 項目的目標是使機器學習成為可能，而無需離開 Elixir 去尋找其他語言的解決方案。即使線性模型和邏輯回歸等概念對您來說是新的，您也將很快使用它們以及更多的內容來解決現實世界中的問題。

從 Nx 編程範式的基本概念開始——它與您習慣的 Elixir 編程風格有何不同，以及它如何使您能夠編寫機器學習算法。利用您對這一範式的理解，從零開始實現基礎的機器學習算法。深入了解，發現 Axon 的深度學習力量。釋放 Elixir 的潛力，學習如何在任何地方構建和部署機器學習模型和管道。學習如何分析、可視化和解釋您的數據和模型。

探索如何使用機器學習解決從圖像識別到內容推薦的各種問題——所有這些都可以在您最喜愛的編程語言中完成。

您需要的條件：
您需要一台安裝有 Elixir v1.12 和 Erlang/OTP 24 的電腦。對於一些計算密集型的範例，您將希望使用 EXLA，該工具目前僅支持 x86-64 平台。雖然不是明確要求，但某些範例將演示在支持 CUDA/ROCm 的 GPU 和 Google TPU 上運行的程序。大多數這些程序仍然可以在普通 CPU 上正常運行，只是所需的時間會長得多。

類似商品