Practical Deep Learning: A Python-Based Introduction

Kneusel, Ron

  • 出版商: No Starch Press
  • 出版日期: 2021-02-23
  • 定價: $2,030
  • 售價: 9.5$1,929
  • 貴賓價: 9.0$1,827
  • 語言: 英文
  • 頁數: 464
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 1718500742
  • ISBN-13: 9781718500747
  • 相關分類: Python程式語言DeepLearning
  • 立即出貨 (庫存 < 3)

買這商品的人也買了...

商品描述

This book is for people with no experience with machine learning and who are looking for an intuition-based, hands-on introduction to deep learning using Python.

Practical Deep Learning with Python is for complete beginners in machine learning. It introduces fundamental concepts such as classes and labels, building a dataset, and what a model is and does before presenting classic machine learning models, neural networks, and modern convolutional neural networks. Experiments in Python--working with leading open-source toolkits and standard datasets--give you hands-on experience with each model and help you build intuition about how to transfer the examples in the book to your own projects.

You'll start with an introduction to the Python language and the NumPy extension that is ubiquitous in machine learning. Prominent toolkits, like sklearn and Keras/TensorFlow are used as the backbone to enable you to focus on the elements of machine learning without the burden of writing implementations from scratch. An entire chapter on evaluating the performance of models gives you the knowledge necessary to understand claims on performance and to know which models are working well and which are not. The book culminates by presenting convolutional neural networks as an introduction to modern deep learning. Understanding how these networks work and how they are affected by parameter choices leaves you with the core knowledge necessary to dive into the larger, ever-changing world of deep learning.

商品描述(中文翻譯)

這本書適合沒有機器學習經驗且希望透過使用Python進行基於直覺的實踐導向介紹來學習深度學習的人。《實用Python深度學習》適合機器學習的完全新手。它介紹了基本概念,如類別和標籤、建立資料集以及模型的定義和功能,然後介紹了經典的機器學習模型、神經網路和現代卷積神經網路。透過使用領先的開源工具包和標準資料集進行Python實驗,讓您能親身體驗每個模型並幫助您建立將書中的範例應用到自己專案的直覺。您將從Python語言和在機器學習中無所不在的NumPy擴展的介紹開始。著名的工具包,如sklearn和Keras/TensorFlow,被用作支撐,使您能夠專注於機器學習的要素,而不需要從頭開始撰寫實作。一整章關於評估模型性能的內容,讓您瞭解如何理解模型性能的聲明,並知道哪些模型運作良好,哪些模型不行。本書最後介紹卷積神經網路作為現代深度學習的入門。瞭解這些網路的運作方式以及參數選擇對其影響,讓您具備深入探索不斷變化的深度學習世界所需的核心知識。

作者簡介

Ron Kneusel has been working in the machine learning industry since 2003 and has been programming in Python since 2004. He received a PhD in Computer Science from UC Boulder in 2016 and is the author of two previous books: Numbers and Computers and Random Numbers and Computers.

作者簡介(中文翻譯)

Ron Kneusel自2003年起在機器學習行業工作,並自2004年起使用Python進行編程。他於2016年從UC Boulder獲得計算機科學博士學位,並是兩本先前書籍《數字與計算機》和《隨機數字與計算機》的作者。