<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8">
<meta name="generator" content="pdf2htmlEX">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<link rel="stylesheet" href="https://static.pudn.com/base/css/base.min.css">
<link rel="stylesheet" href="https://static.pudn.com/base/css/fancy.min.css">
<link rel="stylesheet" href="https://static.pudn.com/prod/directory_preview_static/62befa63502ed3121a70f0dc/raw.css">
<script src="https://static.pudn.com/base/js/compatibility.min.js"></script>
<script src="https://static.pudn.com/base/js/pdf2htmlEX.min.js"></script>
<script>
try{
pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({});
}catch(e){}
</script>
<title></title>
</head>
<body>
<div id="sidebar" style="display: none">
<div id="outline">
</div>
</div>
<div id="pf1" class="pf w0 h0" data-page-no="1"><div class="pc pc1 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62befa63502ed3121a70f0dc/bg1.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x1 h3 y2 ff1 fs0 fc0 sc0 ls0 ws0">浅谈深度学习</div><div class="t m0 x2 h4 y3 ff2 fs1 fc1 sc1 ls0 ws0">1</div></div></div><div class="pi" data-data='{"ctm":[1.333333,0.000000,0.000000,1.333333,0.000000,0.000000]}'></div></div>
</body>
</html>
<div id="pf2" class="pf w0 h0" data-page-no="2"><div class="pc pc2 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62befa63502ed3121a70f0dc/bg2.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x3 h5 y4 ff1 fs2 fc2 sc2 ls0 ws0">主要内容</div><div class="t m0 x4 h6 y5 ff3 fs3 fc3 sc1 ls0 ws0"> <span class="_ _0"></span>2006<span class="_ _1"> </span><span class="ff1 sc3">年以来,机器学习领域中一个叫“深度学习”的</span></div><div class="t m0 x5 h6 y6 ff1 fs3 fc3 sc3 ls0 ws0">课题开始受到学术界广泛关注,如今拥有大数据的互联网</div><div class="t m0 x5 h6 y7 ff1 fs3 fc3 sc3 ls0 ws0">公司争相投入大量资源研发深度学习技术。</div><div class="t m0 x4 h7 y8 ff4 fs4 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h6 y9 ff1 fs3 fc3 sc3 ls0 ws0">为什么有<span class="_ _1"> </span><span class="ff3 sc1">deep learn<span class="_ _0"></span>ing<span class="_ _1"> </span><span class="ff1 sc3">?<span class="_ _1"> </span></span>Why</span></div><div class="t m0 x4 h7 ya ff4 fs4 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h6 yb ff1 fs3 fc3 sc3 ls0 ws0">什么是<span class="_ _1"> </span><span class="ff3 sc1">deep lea<span class="_ _0"></span>rning<span class="_ _1"> </span><span class="ff1 sc3">?<span class="_ _1"> </span></span>What</span></div><div class="t m0 x4 h7 yc ff4 fs4 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h6 yd ff1 fs3 fc3 sc3 ls0 ws0">怎么来的?</div><div class="t m0 x4 h7 ye ff4 fs4 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h6 yf ff3 fs3 fc3 sc1 ls0 ws0">Deep l<span class="_ _0"></span>earnin<span class="_ _0"></span>g<span class="_ _1"> </span><span class="ff1 sc3">与神经网络的异同</span></div><div class="t m0 x2 h4 y3 ff2 fs1 fc5 sc1 ls0 ws0">2</div></div></div><div class="pi" data-data='{"ctm":[1.333333,0.000000,0.000000,1.333333,0.000000,0.000000]}'></div></div>
<div id="pf3" class="pf w0 h0" data-page-no="3"><div class="pc pc3 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/62befa63502ed3121a70f0dc/bg3.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x3 h5 y10 ff1 fs2 fc2 sc2 ls0 ws0">机器学习</div><div class="t m0 x4 h8 y11 ff4 fs5 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h9 y12 ff1 fs6 fc6 sc4 ls0 ws0">机器学习(<span class="_ _1"> </span><span class="ff3 sc1">Machine Learning<span class="_ _2"> </span></span>)<span class="fc3 sc3">是一门专门研究计算</span></div><div class="t m0 x5 h9 y13 ff1 fs6 fc3 sc3 ls0 ws0">机怎样模拟或实现人类的学习行为,<span class="_ _3"></span>以获取新的知识或技能,</div><div class="t m0 x5 h9 y14 ff1 fs6 fc3 sc3 ls0 ws0">重新组织已有的知识结构使之不断改<span class="_ _3"></span>善自身的性能的学科。</div><div class="t m0 x4 h8 y15 ff4 fs5 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h9 y16 ff1 fs6 fc3 sc3 ls0 ws0">简单的说,机器学习就是通过算法,<span class="_ _3"></span>使得机器能从大量的历</div><div class="t m0 x5 h9 y17 ff1 fs6 fc3 sc3 ls0 ws0">史数据中学习规律,从而对新的样本<span class="_ _3"></span>做智能识别或预测未来。</div><div class="t m0 x4 h8 y18 ff4 fs5 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h9 y19 ff3 fs6 fc3 sc1 ls0 ws0">1959<span class="_ _1"> </span><span class="ff1 sc3">年美国的<span class="fc6 sc4">塞缪尔<span class="_ _1"> </span></span></span><span class="fc6">(Samuel)<span class="_ _1"> </span></span><span class="ff1 sc3">设计了一个下棋程序<span class="_ _3"></span>,这</span></div><div class="t m0 x5 h9 y1a ff1 fs6 fc3 sc3 ls0 ws0">个程序具有学习能力,它可以在不断<span class="_ _3"></span>的对弈中改善自己的棋</div><div class="t m0 x5 h9 y1b ff1 fs6 fc3 sc3 ls0 ws0">艺。<span class="_ _1"> </span><span class="ff3 sc1">4<span class="_ _1"> </span></span>年后,这个程序战胜了设计者本人。又过了<span class="_ _2"> </span><span class="ff3 sc1">3<span class="_ _1"> </span></span>年,</div><div class="t m0 x5 h9 y1c ff1 fs6 fc3 sc3 ls0 ws0">这个程序战胜了美国一个保持<span class="_ _1"> </span><span class="ff3 sc1">8<span class="_ _1"> </span></span>年之久的常胜不<span class="_ _3"></span>败的冠军。</div><div class="t m0 x4 h8 y1d ff4 fs5 fc4 sc1 ls0 ws0"></div><div class="t m0 x5 h9 y1e ff1 fs6 fc3 sc3 ls0 ws0">这个程序向人们展示了<span class="fc6 sc4">机<span class="_ _3"></span>器学习的能力,</span>提出了许多令人深</div><div class="t m0 x5 h9 y1f ff1 fs6 fc3 sc3 ls0 ws0">思的社会问题与哲学问题。</div><div class="t m0 x2 h4 y3 ff2 fs1 fc5 sc1 ls0 ws0">3</div></div></div><div class="pi" data-data='{"ctm":[1.333333,0.000000,0.000000,1.333333,0.000000,0.000000]}'></div></div>