<!-- udacimak v1.2.1 -->
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta http-equiv="X-UA-Compatible" content="ie=edge">
<title>Perceptrons II</title>
<link rel="stylesheet" href="../assets/css/bootstrap.min.css">
<link rel="stylesheet" href="../assets/css/plyr.css">
<link rel="stylesheet" href="../assets/css/katex.min.css">
<link rel="stylesheet" href="../assets/css/jquery.mCustomScrollbar.min.css">
<link rel="stylesheet" href="../assets/css/styles.css">
<link rel="shortcut icon" type="image/png" href="../assets/img/udacimak.png" />
</head>
<body>
<div class="wrapper">
<nav id="sidebar">
<div class="sidebar-header">
<h3>Introduction to Neural Networks</h3>
</div>
<ul class="sidebar-list list-unstyled CTAs">
<li>
<a href="../index.html" class="article">Back to Home</a>
</li>
</ul>
<ul class="sidebar-list list-unstyled components">
<li class="">
<a href="01. Neural Network Intuition.html">01. Neural Network Intuition</a>
</li>
<li class="">
<a href="02. Introduction to Deep Learning.html">02. Introduction to Deep Learning</a>
</li>
<li class="">
<a href="03. Starting Machine Learning.html">03. Starting Machine Learning</a>
</li>
<li class="">
<a href="04. A Note on Deep Learning.html">04. A Note on Deep Learning</a>
</li>
<li class="">
<a href="05. Quiz Housing Prices.html">05. Quiz: Housing Prices</a>
</li>
<li class="">
<a href="06. Solution Housing Prices.html">06. Solution: Housing Prices</a>
</li>
<li class="">
<a href="07. Linear to Logistic Regression.html">07. Linear to Logistic Regression</a>
</li>
<li class="">
<a href="08. Classification Problems 1.html">08. Classification Problems 1</a>
</li>
<li class="">
<a href="09. Classification Problems 2.html">09. Classification Problems 2</a>
</li>
<li class="">
<a href="10. Linear Boundaries.html">10. Linear Boundaries</a>
</li>
<li class="">
<a href="11. Higher Dimensions.html">11. Higher Dimensions</a>
</li>
<li class="">
<a href="12. Perceptrons.html">12. Perceptrons</a>
</li>
<li class="">
<a href="13. Perceptrons II.html">13. Perceptrons II</a>
</li>
<li class="">
<a href="14. Why Neural Networks.html">14. Why "Neural Networks"?</a>
</li>
<li class="">
<a href="15. Perceptrons as Logical Operators.html">15. Perceptrons as Logical Operators</a>
</li>
<li class="">
<a href="16. Perceptron Trick.html">16. Perceptron Trick</a>
</li>
<li class="">
<a href="17. Perceptron Algorithm.html">17. Perceptron Algorithm</a>
</li>
<li class="">
<a href="18. Non-Linear Regions.html">18. Non-Linear Regions</a>
</li>
<li class="">
<a href="19. Error Functions.html">19. Error Functions</a>
</li>
<li class="">
<a href="20. Log-loss Error Function.html">20. Log-loss Error Function</a>
</li>
<li class="">
<a href="21. Discrete vs Continuous.html">21. Discrete vs Continuous</a>
</li>
<li class="">
<a href="22. Softmax.html">22. Softmax</a>
</li>
<li class="">
<a href="23. One-Hot Encoding.html">23. One-Hot Encoding</a>
</li>
<li class="">
<a href="24. Maximum Likelihood.html">24. Maximum Likelihood</a>
</li>
<li class="">
<a href="25. Maximizing Probabilities.html">25. Maximizing Probabilities</a>
</li>
<li class="">
<a href="26. Cross-Entropy 1.html">26. Cross-Entropy 1</a>
</li>
<li class="">
<a href="27. Cross-Entropy 2.html">27. Cross-Entropy 2</a>
</li>
<li class="">
<a href="28. Multi-Class Cross Entropy.html">28. Multi-Class Cross Entropy</a>
</li>
<li class="">
<a href="29. Logistic Regression.html">29. Logistic Regression</a>
</li>
<li class="">
<a href="30. Gradient Descent.html">30. Gradient Descent</a>
</li>
<li class="">
<a href="31. Gradient Descent The Code.html">31. Gradient Descent: The Code</a>
</li>
<li class="">
<a href="32. Perceptron vs Gradient Descent.html">32. Perceptron vs Gradient Descent</a>
</li>
<li class="">
<a href="33. Continuous Perceptrons.html">33. Continuous Perceptrons</a>
</li>
<li class="">
<a href="34. Non-linear Data.html">34. Non-linear Data</a>
</li>
<li class="">
<a href="35. Non-Linear Models.html">35. Non-Linear Models</a>
</li>
<li class="">
<a href="36. Neural Network Architecture.html">36. Neural Network Architecture</a>
</li>
<li class="">
<a href="37. Feedforward.html">37. Feedforward</a>
</li>
<li class="">
<a href="38. Multilayer Perceptrons.html">38. Multilayer Perceptrons</a>
</li>
<li class="">
<a href="39. Backpropagation.html">39. Backpropagation</a>
</li>
<li class="">
<a href="40. Further Reading.html">40. Further Reading</a>
</li>
<li class="">
<a href="41. Create Your Own NN.html">41. Create Your Own NN</a>
</li>
<li class="">
<a href="42. Summary.html">42. Summary</a>
</li>
</ul>
<ul class="sidebar-list list-unstyled CTAs">
<li>
<a href="../index.html" class="article">Back to Home</a>
</li>
</ul>
</nav>
<div id="content">
<header class="container-fluild header">
<div class="container">
<div class="row">
<div class="col-12">
<div class="align-items-middle">
<button type="button" id="sidebarCollapse" class="btn btn-toggle-sidebar">
<div></div>
<div></div>
<div></div>
</button>
<h1 style="display: inline-block">13. Perceptrons II</h1>
</div>
</div>
</div>
</div>
</header>
<main class="container">
<div class="row">
<div class="col-12">
<div class="ud-atom">
<h3></h3>
<div>
<figure class="figure">
<img src="img/hq-perceptron.png" alt="" class="img img-fluid">
<figcaption class="figure-caption">
</figcaption>
</figure>
</div>
</div>
<div class="divider"></div><div class="ud-atom">
<h3></h3>
<div>
<h1 id="perceptron">Perceptron</h1>
<p>Now you've seen how a simple neural network makes decisions: by taking in input data, processing that information, and finally, producing an output in the form of a decision! Let's take a deeper dive into the university admission example to learn more about processing the input data.</p>
<p>Data, like test scores and grades, are fed into a network of interconnected nodes. These individual nodes are called <a href="https://en.wikipedia.org/wiki/Perceptron" target="_blank">perceptrons</a>, or artificial neurons, and they are the basic unit of a neural network. <em>Each one looks at input data and decides how to categorize that data.</em> In the example above, the input either passes a threshold for grades and test scores or doesn't, and so the two categories are: yes (passed the threshold) and no (didn't pass the threshold). These categories then combine to form a decision -- for example, if both nodes produce a "yes" output, then this student gains admission into the university.</p>
</div>
</div>
<div class="divider"></div><div class="ud-atom">
<h3></h3>
<div>
<figure class="figure">
<img src="img/hq-new-plot-perceptron-combine-v2.png" alt="" class="img img-fluid">
<figcaption class="figure-caption">
</figcaption>
</figure>
</div>
</div>
<div class="divider"></div><div
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
Part 01-Module 03-Lesson 01-Introduction to Neural Networks (280个子文件)
codecogseqn-43.gif 8KB
perceptron-equation-2.gif 6KB
heaviside-step-function-2.gif 3KB
weight-label-reference.gif 3KB
codecogseqn-49.gif 2KB
sigmoid-derivative.gif 2KB
hidden-layer-weights.gif 2KB
codecogseqn-58.gif 919B
13. Perceptrons II.html 24KB
38. Multilayer Perceptrons.html 24KB
15. Perceptrons as Logical Operators.html 20KB
30. Gradient Descent.html 17KB
17. Perceptron Algorithm.html 16KB
36. Neural Network Architecture.html 13KB
22. Softmax.html 13KB
31. Gradient Descent The Code.html 13KB
39. Backpropagation.html 13KB
16. Perceptron Trick.html 13KB
27. Cross-Entropy 2.html 12KB
24. Maximum Likelihood.html 11KB
21. Discrete vs Continuous.html 11KB
25. Maximizing Probabilities.html 11KB
29. Logistic Regression.html 11KB
20. Log-loss Error Function.html 10KB
37. Feedforward.html 10KB
08. Classification Problems 1.html 10KB
05. Quiz Housing Prices.html 10KB
11. Higher Dimensions.html 10KB
28. Multi-Class Cross Entropy.html 10KB
12. Perceptrons.html 10KB
10. Linear Boundaries.html 10KB
04. A Note on Deep Learning.html 10KB
07. Linear to Logistic Regression.html 10KB
32. Perceptron vs Gradient Descent.html 9KB
01. Neural Network Intuition.html 9KB
26. Cross-Entropy 1.html 9KB
41. Create Your Own NN.html 9KB
40. Further Reading.html 9KB
09. Classification Problems 2.html 9KB
33. Continuous Perceptrons.html 9KB
14. Why Neural Networks.html 9KB
18. Non-Linear Regions.html 9KB
35. Non-Linear Models.html 9KB
23. One-Hot Encoding.html 9KB
19. Error Functions.html 9KB
34. Non-linear Data.html 9KB
03. Starting Machine Learning.html 9KB
06. Solution Housing Prices.html 9KB
02. Introduction to Deep Learning.html 9KB
42. Summary.html 9KB
index.html 7KB
perceptron-graphics.001.jpeg 233KB
1-4-introduction-to-neural-networks2x.jpg 119KB
miniflow.jpg 51KB
02. Module Introduction-uyLRFMI4HkA.mp4 15MB
03. ND013 01 L Intro To Neural Networks-UIycORUrPww.mp4 9.51MB
20. Error Functions-jfKShxGAbok.mp4 7.21MB
27. CrossEntropy V1-1BnhC6e0TFw.mp4 6.61MB
39. Backpropagation V2-1SmY3TZTyUk.mp4 6.52MB
01. 03 Deep Learning A01 Neural Network Intuition-UKEIHK5IifI.mp4 6.22MB
24. Maximum Likelihood 1-1yJx-QtlvNI.mp4 5.75MB
39. DL 46 Calculating The Gradient 2 V2 (2)-7lidiTGIlN4.mp4 5.69MB
21. Discrete vs. Continuous-Rm2KxFaPiJg.mp4 5.35MB
37. DL 41 Feedforward FIX V2-hVCuvMGOfyY.mp4 5.33MB
12. DL 06 Perceptron Definition Fix V2-hImSxZyRiOw.mp4 5.13MB
29. Error Function-V5kkHldUlVU.mp4 4.84MB
36. Combinando modelos-Boy3zHVrWB4.mp4 4.73MB
26. Cross Entropy 1-iREoPUrpXvE.mp4 4.22MB
28. DL 27 Multi-Class Cross Entropy 2 Fix-keDswcqkees.mp4 4.14MB
22. DL 18 Q Softmax V2-RC_A9Tu99y4.mp4 4.01MB
10. Linear Boundaries-X-uMlsBi07k.mp4 3.85MB
24. Maximum Likelihood 2-6nUUeQ9AeUA.mp4 3.85MB
30. Gradient Descent-rhVIF-nigrY.mp4 3.76MB
16. 07 Perceptron Algorithm Trick-lif_qPmXvWA.mp4 3.66MB
19. Error Functions-YfUUunxWIJw.mp4 3.54MB
39. Calculating The Gradient 1 -tVuZDbUrzzI.mp4 3.31MB
32. Gradient Descent Vs Perceptron Algorithm-uL5LuRPivTA.mp4 3.2MB
36. Layers-pg99FkXYK0M.mp4 3.11MB
25. Quiz - Cross 1--xxrisIvD0E.mp4 3.02MB
17. Perceptron Agorithm Pseudocode-p8Q3yu9YqYk.mp4 2.87MB
38. Multilayer perceptrons-Rs9petvTBLk.mp4 2.85MB
36. 29 Neural Network Architecture 2-FWN3Sw5fFoM.mp4 2.83MB
15. AND And OR Perceptrons-45K5N0P9wJk.mp4 2.68MB
11. 09 Higher Dimensions-eBHunImDmWw.mp4 2.59MB
21. Discrete vs Continuous-rdP-RPDFkl0.mp4 2.26MB
34. Non-Linear Data-F7ZiE8PQiSc.mp4 2.14MB
27. Formula For Cross 1-qvr_ego_d6w.mp4 2.08MB
08. Classsification Example-Dh625piH7Z0.mp4 2.07MB
22. DL 18 S Softmax-n8S-v_LCTms.mp4 1.95MB
16. Perceptron Algorithm--zhTROHtscQ.mp4 1.92MB
36. Multiclass Classification-uNTtvxwfox0.mp4 1.88MB
25. Quiz Cross Entropy-njq6bYrPqSU.mp4 1.86MB
22. Quiz - Softmax-NNoezNnAMTY.mp4 1.73MB
37. DL 42 Neural Network Error Function (1)-SC1wEW7TtKs.mp4 1.72MB
23. One-Hot Encoding-AePvjhyvsBo.mp4 1.65MB
09. Classification Example-46PywnGa_cQ.mp4 1.62MB
29. DL 29 Logistic Regression-Minimizing The Error Function-KayqiYijlzc.mp4 1.49MB
05. DLND REG 01 Quiz Housing Prices V2-8CSBiVKu35Q.mp4 1.48MB
39. Chain Rule-YAhIBOnbt54.mp4 1.46MB
42. Conclusion-m8xslYUBXYo.mp4 1.43MB
共 280 条
- 1
- 2
- 3
资源评论
智能汽车人
- 粉丝: 571
- 资源: 8
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功