Learning Probabilistic Graphical Models in R

David Bellot

買這商品的人也買了...

商品描述

Key Features

  • Predict and use a probabilistic graphical models (PGM) as an expert system
  • Comprehend how your computer can learn Bayesian modeling to solve real-world problems
  • Know how to prepare data and feed the models by using the appropriate algorithms from the appropriate R package

Book Description

Probabilistic graphical models (PGM, also known as graphical models) are a marriage between probability theory and graph theory. Generally, PGMs use a graph-based representation. Two branches of graphical representations of distributions are commonly used, namely Bayesian networks and Markov networks. R has many packages to implement graphical models.

We'll start by showing you how to transform a classical statistical model into a modern PGM and then look at how to do exact inference in graphical models. Proceeding, we'll introduce you to many modern R packages that will help you to perform inference on the models. We will then run a Bayesian linear regression and you'll see the advantage of going probabilistic when you want to do prediction.

Next, you'll master using R packages and implementing its techniques. Finally, you'll be presented with machine learning applications that have a direct impact in many fields. Here, we'll cover clustering and the discovery of hidden information in big data, as well as two important methods, PCA and ICA, to reduce the size of big problems.

What you will learn

  • Understand the concepts of PGM and which type of PGM to use for which problem
  • Tune the model's parameters and explore new models automatically
  • Understand the basic principles of Bayesian models, from simple to advanced
  • Transform the old linear regression model into a powerful probabilistic model
  • Use standard industry models but with the power of PGM
  • Understand the advanced models used throughout today's industry
  • See how to compute posterior distribution with exact and approximate inference algorithms

About the Author

David Bellot is a PhD graduate in computer science from INRIA, France, with a focus on Bayesian machine learning. He was a postdoctoral fellow at the University of California, Berkeley, and worked for companies such as Intel, Orange, and Barclays Bank. He currently works in the financial industry, where he develops financial market prediction algorithms using machine learning. He is also a contributor to open source projects such as the Boost C++ library.

Table of Contents

  1. Probabilistic Reasoning
  2. Exact Inference
  3. Learning Parameters
  4. Bayesian Modeling – Basic Models
  5. Approximate Inference
  6. Bayesian Modeling – Linear Models
  7. Probabilistic Mixture Models
  8. Appendix

商品描述(中文翻譯)

主要特點



  • 使用概率圖模型(PGM)作為專家系統,並進行預測

  • 了解計算機如何學習貝葉斯建模以解決現實世界問題

  • 使用適當的算法和適當的 R 套件來準備數據並餵養模型

書籍描述


概率圖模型(PGM,也稱為圖模型)是概率論和圖論的結合。通常,PGM使用基於圖的表示方法。常用的兩種分布圖形表示方法是貝葉斯網絡和馬爾可夫網絡。R 語言有許多套件可用於實現圖模型。


我們將首先向您展示如何將傳統統計模型轉換為現代 PGM,然後介紹如何在圖模型中進行精確推理。接下來,我們將向您介紹許多現代 R 套件,這些套件將幫助您對模型進行推理。然後,我們將運行一個貝葉斯線性回歸,您將看到在進行預測時使用概率模型的優勢。


接下來,您將掌握使用 R 套件並實施其技術。最後,我們將介紹對許多領域具有直接影響的機器學習應用。在這裡,我們將涵蓋聚類和在大數據中發現隱藏信息,以及兩種重要的方法,PCA 和 ICA,以減少大問題的規模。

您將學到什麼



  • 了解 PGM 的概念以及在哪種問題上使用哪種類型的 PGM

  • 調整模型的參數並自動探索新模型

  • 從簡單到高級,了解貝葉斯模型的基本原理

  • 將舊的線性回歸模型轉換為強大的概率模型

  • 使用標準行業模型,但具有 PGM 的優勢

  • 了解當今行業中使用的高級模型

  • 了解如何使用精確和近似推理算法計算後驗分布

關於作者


David Bellot 是法國 INRIA 的計算機科學博士,專注於貝葉斯機器學習。他曾在加州大學伯克利分校擔任博士後研究員,並曾在英特爾、Orange 和巴克萊銀行等公司工作。他目前在金融行業工作,使用機器學習開發金融市場預測算法。他還是開源項目(如 Boost C++ 库)的貢獻者。

目錄



  1. 概率推理

  2. 精確推理

  3. 學習參數

  4. 貝葉斯建模 - 基本模型

  5. 近似推理

  6. 貝葉斯建模 - 線性模型

  7. 概率混合模型

  8. 附錄