Predictive Analytics with TensorFlow
Md. Rezaul Karim
- 出版商: Packt Publishing
- 出版日期: 2017-10-26
- 售價: $1,980
- 貴賓價: 9.5 折 $1,881
- 語言: 英文
- 頁數: 522
- 裝訂: Paperback
- ISBN: 1788398920
- ISBN-13: 9781788398923
-
相關分類:
DeepLearning、TensorFlow、Machine Learning
海外代購書籍(需單獨結帳)
買這商品的人也買了...
-
$350$315 -
$2,170$2,062 -
$1,780$1,691 -
$990Web Scraping with Python: Collecting More Data from the Modern Web, 2/e (Paperback)
-
$1,380$1,311 -
$199AlphaGo 如何戰勝人類圍棋大師 — 智能硬件 TensorFlow 實踐
-
$690$538 -
$1,308Applied Deep Learning: A Case-Based Approach to Understanding Deep Neural Networks
相關主題
商品描述
Key Features
- A quick guide to gain hands-on experience with deep learning in different domains such as digit/image classification, and texts
- Build your own smart, predictive models with TensorFlow using easy-to-follow approach mentioned in the book
- Understand deep learning and predictive analytics along with its challenges and best practices
Book Description
Predictive decisions are becoming a huge trend worldwide catering wide sectors of industries by predicting which decisions are more likely to give maximum results. The data mining, statistics, machine learning allows users to discover predictive intelligence by uncovering patterns and showing the relationship among the structured and unstructured data. This book will help you build solutions which will make automated decisions. In the end tune and build your own predictive analytics model with the help of TensorFlow.
This book will be divided in three main sections.
In the first section-Applied Mathematics, Statistics, and Foundations of Predictive Analytics; will cover Linear algebra needed to getting started with data science in a practical manner by using the most commonly used Python packages. It will also cover the needed background in probability and information theory that is must for Data Scientists.
The second section shows how to develop large-scale predictive analytics pipelines using supervised (classification/regression) and unsupervised (clustering) learning algorithms. It'll then demonstrate how to develop predictive models for NLP. Finally, reinforcement learning and recommendation system will be used for developing predictive models.
The third section covers practical mastery of deep learning architectures for advanced predictive analytics: including Deep Neural Networks (MLP & DBN) and Recurrent Neural Networks for high-dimensional and sequence data. Finally, it'll show how to develop Convolutional Neural Networks- based predictive models for emotion recognition, image classification, and sentiment analysis.
So in total, this book will help you control the power of deep learning in diverse fields, providing best practices and tips from the real world use cases and helps you in decision making based on predictive analytics.
What you will learn
- Get solid and theoretical understanding of linear algebra, statistics, and probability theory for predictive analytics
- Learn practical predictive analytics using machine learning algorithms (classification, regression, and clustering) in order to avoid pitfalls and fallacies
- Discern how to develop predictive models for NLP
- Get practical know-how of deep learning architectures for advanced predictive analytics using Deep Neural Networks (MLP and DBN) for predictive analytics
- Emotion recognition, image classification, and sentiment analysis using convolutional neural networks
- Use Recurrent Neural Networks and reinforcement learning for predictive analytics
- Develop recommendation systems for predictive analytics
商品描述(中文翻譯)
主要特點
- 快速指南,以深度學習在不同領域(如數字/圖像分類和文本)獲得實踐經驗
- 使用書中提到的易於遵循的方法,使用TensorFlow構建自己的智能預測模型
- 了解深度學習和預測分析以及其挑戰和最佳實踐
書籍描述
預測性決策正成為全球的一個巨大趨勢,為各個行業提供預測哪些決策可能產生最大結果的服務。數據挖掘、統計學和機器學習使用戶能夠通過揭示模式並展示結構化和非結構化數據之間的關係來發現預測性智能。本書將幫助您構建能夠自動化決策的解決方案。最後,借助TensorFlow的幫助,調整並構建自己的預測分析模型。
本書將分為三個主要部分。
第一部分-應用數學、統計學和預測分析基礎,將介紹線性代數,以實際方式開始進行數據科學,使用最常用的Python套件。它還將涵蓋數據科學家必須具備的概率和信息理論背景知識。
第二部分展示了如何使用監督(分類/回歸)和無監督(聚類)學習算法開發大規模的預測分析流程。然後,它將演示如何為NLP開發預測模型。最後,將使用強化學習和推薦系統來開發預測模型。
第三部分涵蓋了高級預測分析的深度學習架構的實際掌握:包括用於高維和序列數據的深度神經網絡(MLP和DBN)和循環神經網絡。最後,它將展示如何開發基於卷積神經網絡的預測模型,用於情感識別、圖像分類和情感分析。
總之,本書將幫助您在不同領域中掌握深度學習的力量,提供來自實際用例的最佳實踐和技巧,並幫助您基於預測分析做出決策。
你將學到什麼
- 獲得線性代數、統計學和概率論的堅實理論基礎,以進行預測分析
- 學習使用機器學習算法(分類、回歸和聚類)進行實際的預測分析,以避免陷阱和謬誤
- 了解如何為NLP開發預測模型
- 獲得使用深度神經網絡(MLP和DBN)進行高級預測分析的實際知識
- 使用卷積神經網絡進行情感識別、圖像分類和情感分析
- 使用循環神經網絡和強化學習進行預測分析
- 開發預測分析的推薦系統