☆☆☆☆☆

圖書標籤:

• NLTK
• 自然語言處理
• NLP
• 漢語處理
• 深度學習
• 機器學習
• Python
• 教程
• 書籍
• 技術

店铺： 蓝墨水图书专营店

出版社： 人民邮电出版社

ISBN：9787115452573

商品编码：13791776441

3本 NLTK基礎教程 用NLTK和Python庫構建機器學習應用+NLP漢語自然語言處理原理+深度學習:原理與應用實踐 9787115452573 9787121307652 9787121304132

於本書有任何問題，請聯係： 

• 書 號： 978-7-115-45257-3
• 頁 數： 172
• 印刷方式： 黑白印刷
• 開 本： 16開
• 齣版狀態： 正在印刷
• 原書名： 
• 原書號： 978-1784396909

NLTK基礎教程——用NLTK和Python庫構建機器學習應用[預售]

• 作者： 
• 譯者：  責編： 
• 分類： 

【預計上市時間：05月23日】
NLTK 庫是當前自然語言處理（NLP）領域·為流行、使用·為廣泛的庫之一, 同時Python語言也已逐漸成為主流的編程語言之一。
本書主要介紹如何通過NLTK庫與一些Python庫的結閤從而實現復雜的NLP任務和機器學習應用。全書共分為10章。第1章對NLP進行瞭簡單介紹。第2章、第3章和第4章主要介紹一些通用的預處理技術、專屬於NLP領域的預處理技術以及命名實體識彆技術等。第5章之後的內容側重於介紹如何構建一些NLP應用，涉及文本分類、數據科學和數據處理、社交媒體挖掘和大規模文本挖掘等方麵。
本書適閤 NLP 和機器學習領域的愛好者、對文本處理感興趣的讀者、想要快速學習NLTK的資深Python程序員以及機器學習領域的研究人員閱讀。

作 譯 者：

齣版時間：2017-01 韆 字 數：816 版    次：01-01 頁    數：544 印刷時間： 開    本：16開 印    次：01-01 裝    幀： I S B N ：9787121307652   重    印：新書 換    版：

所屬分類： >>  >>

廣告語：

紙質書定價：￥98.

 

 

本書是一本研究漢語自然語言處理方麵的基礎性、綜閤性書籍，涉及NLP的語言理論、算法和工程實踐的方方麵麵，內容繁雜。 本書包括NLP的語言理論部分、算法部分、案例部分，涉及漢語的發展曆史、傳統的句法理論、認知語言學理論。需要指齣的是，本書是迄今為止，本係統介紹認知語言學和算法設計相結閤的中文NLP書籍，並從認知語言學的視角重新認識和分析瞭NLP的句法和語義相結閤的數據結構。這也是本書的創新之處。 本書適用於所有想學習NLP的技術人員，包括各大人工智能實驗室、軟件學院等專業機構。

目  錄

第1章  中文語言的機器處理    1

1.1  曆史迴顧    2

1.1.1  從科幻到現實    2

1.1.2  早期的探索    3

1.1.3  規則派還是統計派    3

1.1.4  從機器學習到認知

計算    5

1.2  現代自然語言係統簡介    6

1.2.1  NLP流程與開源框架    6

1.2.2  哈工大NLP平颱及其

演示環境    9

1.2.3  Stanford NLP團隊及其

演示環境    11

1.2.4  NLTK開發環境    13

1.3  整閤中文分詞模塊    16

1.3.1  安裝Ltp Python組件    17

1.3.2  使用Ltp 3.3進行中文

分詞    18

1.3.3  使用結巴分詞模塊    20

1.4  整閤詞性標注模塊    22

1.4.1  Ltp 3.3詞性標注    23

1.4.2  安裝StanfordNLP並

編寫Python接口類    24

1.4.3  執行Stanford詞性

標注    28

1.5  整閤命名實體識彆模塊    29

1.5.1  Ltp 3.3命名實體識彆    29

1.5.2  Stanford命名實體

識彆    30

1.6  整閤句法解析模塊    32

1.6.1  Ltp 3.3句法依存樹    33

1.6.2  Stanford Parser類    35

1.6.3  Stanford短語結構樹    36

1.6.4  Stanford依存句法樹    37

1.7  整閤語義角色標注模塊    38

1.8  結語    40

第2章  漢語語言學研究迴顧    42

2.1  文字符號的起源    42

2.1.1  從記事談起    43

2.1.2  古文字的形成    47

2.2  六書及其他    48

2.2.1  象形    48

2.2.2  指事    50

2.2.3  會意    51

2.2.4  形聲    53

 

2.2.5  轉注    54

2.2.6  假藉    55

2.3  字形的流變    56

2.3.1  筆與墨的形成與變革    56

2.3.2  隸變的方式    58

2.3.3  漢字的符號化與結構    61

2.4  漢語的發展    67

2.4.1  完整語義的基本

形式——句子    68

2.4.2  語言的初始形態與

文言文    71

2.4.3  白話文與復音詞    73

2.4.4  白話文與句法研究    78

2.5  三個平麵中的語義研究    80

2.5.1  詞匯與本體論    81

2.5.2  格語法及其框架    84

2.6  結語    86

第3章  詞匯與分詞技術    88

3.1  中文分詞    89

3.1.1  什麼是詞與分詞規範    90

3.1.2  兩種分詞標準    93

3.1.3  歧義、機械分詞、語言

模型    94

3.1.4  詞匯的構成與未登錄

詞    97

3.2  係統總體流程與詞典結構    98

3.2.1  概述    98

3.2.2  中文分詞流程    99

3.2.3  分詞詞典結構    103

3.2.4  命名實體的詞典

結構    105

3.2.5  詞典的存儲結構    108

3.3  算法部分源碼解析    111

3.3.1  係統配置    112

3.3.2  Main方法與例句    113

3.3.3  句子切分    113

3.3.4  分詞流程    117

3.3.5  一元詞網    118

3.3.6  二元詞圖    125

3.3.7  NShort算法原理    130

3.3.8  後處理規則集    136

3.3.9  命名實體識彆    137

3.3.10  細分階段與·短

路徑    140

3.4  結語    142

第4章  NLP中的概率圖模型    143

4.1  概率論迴顧    143

4.1.1  多元概率論的幾個

基本概念    144

4.1.2  貝葉斯與樸素貝葉斯

算法    146

4.1.3  文本分類    148

4.1.4  文本分類的實現    151

4.2  信息熵    154

4.2.1  信息量與信息熵    154

4.2.2  互信息、聯閤熵、

條件熵    156

4.2.3  交叉熵和KL散度    158

4.2.4  信息熵的NLP的

意義    159

4.3  NLP與概率圖模型    160

4.3.1  概率圖模型的幾個

基本問題    161

4.3.2  産生式模型和判彆式

模型    162

4.3.3  統計語言模型與NLP

算法設計    164

4.3.4  極大似然估計    167

4.4  隱馬爾科夫模型簡介    169

4.4.1  馬爾科夫鏈    169

4.4.2  隱馬爾科夫模型    170

4.4.3  HMMs的一個實例    171

4.4.4  Viterbi算法的實現    176

4.5  ·大熵模型    179

4.5.1  從詞性標注談起    179

4.5.2  特徵和約束    181

4.5.3  ·大熵原理    183

4.5.4  公式推導    185

4.5.5  對偶問題的極大似然

估計    186

4.5.6  GIS實現    188

4.6  條件隨機場模型    193

4.6.1  隨機場    193

4.6.2  無嚮圖的團（Clique）

與因子分解    194

4.6.3  綫性鏈條件隨機場    195

4.6.4  CRF的概率計算    198

4.6.5  CRF的參數學習    199

4.6.6  CRF預測標簽    200

4.7  結語    201

第5章  詞性、語塊與命名實體

識彆    202

5.1  漢語詞性標注    203

5.1.1  漢語的詞性    203

5.1.2  賓州樹庫的詞性標注

規範    205

5.1.3  stanfordNLP標注

詞性    210

5.1.4  訓練模型文件    213

5.2  語義組塊標注    219

5.2.1  語義組塊的種類    220

5.2.2  細說NP    221

5.2.3  細說VP    223

5.2.4  其他語義塊    227

5.2.5  語義塊的抽取    229

5.2.6  CRF的使用    232

5.3  命名實體識彆    240

5.3.1  命名實體    241

5.3.2  分詞架構與專名

.............

深度學習：原理與應用實踐

叢書名 ： 著    者： 作 譯 者： 齣版時間：2016-12 韆 字 數：259 版    次：01-01 頁    數：232 印刷時間： 開    本：16開 印    次：01-01 裝    幀： I S B N ：9787121304132   重    印：新書 換    版： 所屬分類： >>  >>  廣告語：    紙質書定價：￥48

 

 

本書全麵、係統地介紹深度學習相關的技術，包括人工神經網絡，捲積神經網絡，深度學習平颱及源代碼分析，深度學習入門與進階，深度學習高級實踐，所有章節均附有源程序，所有實驗讀者均可重現，具有高度的可操作性和實用性。通過學習本書，研究人員、深度學習愛好者，能夠在3 個月內，係統掌握深度學習相關的理論和技術。

目 錄

深度學習基礎篇

第1 章 緒論 ·································································································· 2

1.1 引言 ······································································································· 2

1.1.1 Google 的深度學習成果 ···························································· 2

1.1.2 Microsoft 的深度學習成果························································· 3

1.1.3 國內公司的深度學習成果 ························································· 3

1.2 深度學習技術的發展曆程 ···································································· 4

1.3 深度學習的應用領域 ············································································ 6

1.3.1 圖像識彆領域 ············································································· 6

1.3.2 語音識彆領域 ············································································· 6

1.3.3 自然語言理解領域 ····································································· 7

1.4 如何開展深度學習的研究和應用開發 ················································· 7

本章參考文獻 ······························································································ 11

第2 章 國內外深度學習技術研發現狀及其産業化趨勢 ······························· 13

2.1 Google 在深度學習領域的研發現狀 ·················································· 13

2.1.1 深度學習在Google 的應用 ······················································ 13

2.1.2 Google 的TensorFlow 深度學習平颱 ······································ 14

2.1.3 Google 的深度學習芯片TPU ·················································· 15

2.2 Facebook 在深度學習領域的研發現狀 ·············································· 15

2.2.1 Torchnet ···················································································· 15

2.2.2 DeepText ··················································································· 16

2.3 百度在深度學習領域的研發現狀 ······················································· 17

2.3.1 光學字符識彆 ··········································································· 17

2.3.2 商品圖像搜索 ··········································································· 17

2.3.3 在綫廣告 ·················································································· 18

2.3.4 以圖搜圖 ·················································································· 18

2.3.5 語音識彆 ·················································································· 18

2.3.6 百度開源深度學習平颱MXNet 及其改進的深度語音識彆係統Warp-CTC ····· 19

2.4 阿裏巴巴在深度學習領域的研發現狀 ··············································· 19

2.4.1 拍立淘 ······················································································ 19

2.4.2 阿裏小蜜——智能客服Messenger ········································· 20

2.5 京東在深度學習領域的研發現狀 ······················································· 20

2.6 騰訊在深度學習領域的研發現狀 ······················································· 21

2.7 科創型公司（基於深度學習的人臉識彆係統） ······························· 22

2.8 深度學習的硬件支撐——NVIDIA GPU ············································ 23

本章參考文獻 ······························································································ 24

深度學習理論篇

第3 章 神經網絡 ························································································· 30

3.1 神經元的概念 ······················································································ 30

3.2 神經網絡 ····························································································· 31

3.2.1 後嚮傳播算法 ··········································································· 32

3.2.2 後嚮傳播算法推導 ··································································· 33

3.3 神經網絡算法示例 ·············································································· 36

本章參考文獻 ······························································································ 38

第4 章 捲積神經網絡 ················································································· 39

4.1 捲積神經網絡特性 ················································································ 39

4.1.1 局部連接 ·················································································· 40

4.1.2 權值共享 ·················································································· 41

4.1.3 空間相關下采樣 ······································································· 42

4.2 捲積神經網絡操作 ·············································································· 42

4.2.1 捲積操作 ·················································································· 42

4.2.2 下采樣操作 ·············································································· 44

4.3 捲積神經網絡示例：LeNet-5 ····························································· 45

本章參考文獻 ······························································································ 48

深度學習工具篇

第5 章 深度學習工具Caffe ········································································ 50

5.1 Caffe 的安裝 ························································································ 50

5.1.1 安裝依賴包 ·············································································· 51

5.1.2 CUDA 安裝 ·············································································· 51

5.1.3 MATLAB 和Python 安裝 ························································ 54

5.1.4 OpenCV 安裝（可選） ···························································· 59

5.1.5 Intel MKL 或者BLAS 安裝 ····················································· 59

5.1.6 Caffe 編譯和測試 ····································································· 59

5.1.7 Caffe 安裝問題分析 ································································· 62

5.2 Caffe 框架與源代碼解析 ···································································· 63

5.2.1 數據層解析 ·············································································· 63

5.2.2 網絡層解析 ·············································································· 74

5.2.3 網絡結構解析 ··········································································· 92

5.2.4 網絡求解解析 ········································································· 104

本章參考文獻 ···························································································· 109

第6 章 深度學習工具Pylearn2 ································································ 110

6.1 Pylearn2 的安裝 ·················································································· 110

6.1.1 相關依賴安裝 ·········································································· 110

6.1.2 安裝Pylearn2 ·········································································· 112

6.2 Pylearn2 的使用 ·················································································· 112

本章參考文獻 ····························································································· 116

深度學習實踐篇（入門與進階）

第7 章 基於深度學習的手寫數字識彆 ······················································ 118

7.1 數據介紹 ···························································································· 118

7.1.1 MNIST 數據集 ········································································ 118

7.1.2 提取MNIST 數據集圖片 ······················································· 120

7.2 手寫字體識彆流程 ············································································ 121

7.2.1 模型介紹 ················································································ 121

7.2.2 操作流程 ················································································ 126

7.3 實驗結果分析 ···················································································· 127

本章參考文獻 ···························································································· 128

第8 章 基於深度學習的圖像識彆 ····························································· 129

8.1 數據來源 ··························································································· 129

8.1.1 Cifar10 數據集介紹 ································································ 129

8.1.2 Cifar10 數據集格式 ································································ 129

8.2 Cifar10 識彆流程 ··············································································· 130

8.2.1 模型介紹 ················································································ 130

8.2.2 操作流程 ················································································ 136

8.3 實驗結果分析 ······················································································ 139

本章參考文獻 ···························································································· 140

第9 章 基於深度學習的物體圖像識彆 ······················································ 141

9.1 數據來源 ··························································································· 141

9.1.1 Caltech101 數據集 ·································································· 141

9.1.2 Caltech101 數據集處理 ·························································· 142

9.2 物體圖像識彆流程 ············································································ 143

9.2.1 模型介紹 ················································································ 143

9.2.2 操作流程 ················································································ 144

9.3 實驗結果分析 ···················································································· 150

本章參考文獻 ···························································································· 151

第10 章 基於深度學習的人臉識彆 ··························································· 152

10.1 數據來源 ························································································· 152

10.1.1 AT＆T Facedatabase 數據庫 ·················································· 152

10.1.2 數據庫處理 ··········································································· 152

10.2 人臉識彆流程 ·················································································· 154

10.2.1 模型介紹 ·············································································· 154

10.2.2 操作流程 ·············································································· 155

10.3 實驗結果分析 ·················································································· 159

本章參考文獻 ···························································································· 160

深度學習實踐篇（高級應用）

第11 章 基於深度學習的人臉識彆——DeepID 算法 ································ 162

11.1 問題定義與數據來源 ······································································ 162

11.2 算法原理 ·························································································· 163

11.2.1 數據預處理 ··········································································· 163

11.2.2 模型訓練策略 ······································································· 164

11.2.3 算法驗證和結果評估 ··························································· 164

11.3 人臉識彆步驟 ·················

。。。。

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆

评分☆☆☆☆☆