掃一掃
關注中圖網(wǎng)
官方微博
本類五星書更多>
-
>
全國計算機等級考試最新真考題庫模擬考場及詳解·二級MSOffice高級應用
-
>
決戰(zhàn)行測5000題(言語理解與表達)
-
>
軟件性能測試.分析與調(diào)優(yōu)實踐之路
-
>
第一行代碼Android
-
>
JAVA持續(xù)交付
-
>
EXCEL最強教科書(完全版)(全彩印刷)
-
>
深度學習
深度學習與神經(jīng)網(wǎng)絡 版權信息
- ISBN：9787121473739
- 條形碼：9787121473739 ; 978-7-121-47373-9
- 裝幀：平塑
- 冊數(shù)：暫無
- 重量：暫無
- 所屬分類：>
深度學習與神經(jīng)網(wǎng)絡 內(nèi)容簡介
全書分為7 個章節(jié)。第1 章緒論，梳理了人工智能不同技術流派的特點、深度學習的發(fā)展及前沿技術；第2 章介紹相關預備知識，包括線性代數(shù)、概率論、優(yōu)化理論以及機器學習的基礎知識；第3 章從前饋神經(jīng)網(wǎng)絡的基礎模型――感知器出發(fā)，介紹前饋神經(jīng)網(wǎng)絡的基本結構以及涉及的激活函數(shù)、梯度下降、反向傳播等內(nèi)容；第4 章，介紹深度模型的優(yōu)化問題，討論了神經(jīng)網(wǎng)絡優(yōu)化中常見的病態(tài)問題；第5 章介紹深度學習中的正則化方法，包括范數(shù)懲罰、數(shù)據(jù)集增強與噪聲注入、提前停止等；第6 章介紹了卷積神經(jīng)網(wǎng)絡，以及卷積神經(jīng)網(wǎng)絡在計算機視覺領域的具體應用；第7 章通過實際案例介紹循環(huán)神經(jīng)網(wǎng)絡與卷積神經(jīng)網(wǎng)絡的結合應用。
深度學習與神經(jīng)網(wǎng)絡 目錄
第1 章 緒論····················································································.1
1.1 人工智能·············································································.2
1.1.1 人工智能技術的發(fā)展歷程···············································.3
1.1.2 人工智能技術的流派·····················································.9
1.2 深度學習與神經(jīng)網(wǎng)絡概述······················································.11
1.2.1 深度學習與神經(jīng)網(wǎng)絡技術的發(fā)展歷程······························.11
1.2.2 深度學習與神經(jīng)網(wǎng)絡的前沿技術····································.16
1.3 深度學習系統(tǒng)架構·······························································.17
1.4 深度學習框架·····································································.19
1.5 深度學習的應用··································································.20
1.5.1 計算機視覺·······························································.20
1.5.2 語音語義··································································.21
1.5.3 自然語言處理····························································.22
1.6 人工智能潛在的安全風險······················································.22
1.6.1 數(shù)據(jù)層面的風險·························································.23
1.6.2 算法模型層面的風險···················································.23
1.6.3 智能計算框架層面的風險·············································.23
1.6.4 基礎軟硬件層面的風險················································.24
1.6.5 應用服務層面的風險···················································.24
本章小結··················································································.24
第2 章 預備知識············································································.25
2.1 相關數(shù)學基礎·····································································.25
2.1.1 線性代數(shù)··································································.25
2.1.2 概率論·····································································.27
2.1.3 優(yōu)化理論··································································.32
2.2 機器學習基礎·····································································.34
2.2.1 機器學習算法的基本流程·············································.35
2.2.2 機器學習常用評價指標················································.36
2.2.3 典型機器學習算法······················································.41
2.3 實驗環(huán)境基礎·····································································.49
2.3.1 GPU 驅(qū)動的安裝配置··················································.49
2.3.2 依賴環(huán)境的安裝配置···················································.52
2.3.3 深度學習框架的安裝配置·············································.54
2.3.4 集成開發(fā)環(huán)境的安裝配置·············································.56
本章小結··················································································.57
第3 章 前饋神經(jīng)網(wǎng)絡······································································.58
3.1 感知器··············································································.58
3.1.1 單層感知器·······························································.58
3.1.2 多層感知器·······························································.61
3.1.3 前饋神經(jīng)網(wǎng)絡的基本結構·············································.62
3.2 激活函數(shù)···········································································.63
3.2.1 Sigmoid 函數(shù)·····························································.63
3.2.2 ReLU 函數(shù)································································.65
3.2.3 Tanh 函數(shù)·································································.67
3.2.4 Softmax 函數(shù)·····························································.68
3.3 誤差反向傳播·····································································.69
3.3.1 梯度下降法·······························································.69
3.3.2 鏈式法則··································································.70
3.3.3 反向傳播··································································.72
本章小結··················································································.75
第4 章 深度模型的優(yōu)化···································································.76
4.1 神經(jīng)網(wǎng)絡的優(yōu)化問題····························································.76
4.1.1 局部*優(yōu)和振蕩陷阱···················································.76
4.1.2 梯度爆炸和梯度消失·····································
1.1 人工智能·············································································.2
1.1.1 人工智能技術的發(fā)展歷程···············································.3
1.1.2 人工智能技術的流派·····················································.9
1.2 深度學習與神經(jīng)網(wǎng)絡概述······················································.11
1.2.1 深度學習與神經(jīng)網(wǎng)絡技術的發(fā)展歷程······························.11
1.2.2 深度學習與神經(jīng)網(wǎng)絡的前沿技術····································.16
1.3 深度學習系統(tǒng)架構·······························································.17
1.4 深度學習框架·····································································.19
1.5 深度學習的應用··································································.20
1.5.1 計算機視覺·······························································.20
1.5.2 語音語義··································································.21
1.5.3 自然語言處理····························································.22
1.6 人工智能潛在的安全風險······················································.22
1.6.1 數(shù)據(jù)層面的風險·························································.23
1.6.2 算法模型層面的風險···················································.23
1.6.3 智能計算框架層面的風險·············································.23
1.6.4 基礎軟硬件層面的風險················································.24
1.6.5 應用服務層面的風險···················································.24
本章小結··················································································.24
第2 章 預備知識············································································.25
2.1 相關數(shù)學基礎·····································································.25
2.1.1 線性代數(shù)··································································.25
2.1.2 概率論·····································································.27
2.1.3 優(yōu)化理論··································································.32
2.2 機器學習基礎·····································································.34
2.2.1 機器學習算法的基本流程·············································.35
2.2.2 機器學習常用評價指標················································.36
2.2.3 典型機器學習算法······················································.41
2.3 實驗環(huán)境基礎·····································································.49
2.3.1 GPU 驅(qū)動的安裝配置··················································.49
2.3.2 依賴環(huán)境的安裝配置···················································.52
2.3.3 深度學習框架的安裝配置·············································.54
2.3.4 集成開發(fā)環(huán)境的安裝配置·············································.56
本章小結··················································································.57
第3 章 前饋神經(jīng)網(wǎng)絡······································································.58
3.1 感知器··············································································.58
3.1.1 單層感知器·······························································.58
3.1.2 多層感知器·······························································.61
3.1.3 前饋神經(jīng)網(wǎng)絡的基本結構·············································.62
3.2 激活函數(shù)···········································································.63
3.2.1 Sigmoid 函數(shù)·····························································.63
3.2.2 ReLU 函數(shù)································································.65
3.2.3 Tanh 函數(shù)·································································.67
3.2.4 Softmax 函數(shù)·····························································.68
3.3 誤差反向傳播·····································································.69
3.3.1 梯度下降法·······························································.69
3.3.2 鏈式法則··································································.70
3.3.3 反向傳播··································································.72
本章小結··················································································.75
第4 章 深度模型的優(yōu)化···································································.76
4.1 神經(jīng)網(wǎng)絡的優(yōu)化問題····························································.76
4.1.1 局部*優(yōu)和振蕩陷阱···················································.76
4.1.2 梯度爆炸和梯度消失·····································
展開全部
深度學習與神經(jīng)網(wǎng)絡 作者簡介
趙金晶，女，1981年生，軍事科學院系統(tǒng)工程研究院高級工程師，國防科技大學計算機學院博士畢業(yè)，主要研究方向為網(wǎng)絡與信息安全、人工智能技術。先后承擔國家自然科學基金、國家973計劃、863計劃等重大項目，曾獲國家自然科學基金青年基金資助。獲省部級科技進步獎二等獎5項、三等獎1項，發(fā)明專利20余項。發(fā)表學術論文80余篇，出版學術著作2部。電子郵箱：zhjj0420@126.com李虎，男，1987年生，軍事科學院系統(tǒng)工程研究院工程師，國防科技大學計算機學院博士畢業(yè)，主要研究方向為網(wǎng)絡與信息安全。先后承擔、參與國家973計劃、863計劃、裝備預研等各類科研項目10余項。獲省部級科技進步獎二等獎2項、發(fā)明專利10余項，發(fā)表論文20余篇。電子郵箱：lihu@nudt.edu.cn張明，男，1990年生，軍事科學院系統(tǒng)工程研究院工程師，北京系統(tǒng)工程研究所碩士畢業(yè)，主要研究方向為機器學習和人工智能安全。先后參與、主持國家自然科學基金、重點實驗室基金、國家973重大項目、裝備預研和國防科技創(chuàng)新特區(qū)等各類科研項目10余項。獲省部級科技進步獎一等獎1項，二等獎2項。發(fā)表學術論文20余篇，其中SCI檢索5篇，EI檢索10余篇。電子郵箱：zm_stiss@163.com
書友推薦
- >
李白與唐代文化
- >
隨園食單
- >
經(jīng)典常談
- >
姑媽的寶刀
- >
山海經(jīng)
- >
小考拉的故事-套裝共3冊
- >
伊索寓言-世界文學名著典藏-全譯本
- >
伯納黛特,你要去哪(2021新版)
本類暢銷
