课程信息
7,088,471 次近期查看

100% 在线

立即开始,按照自己的计划学习。

可灵活调整截止日期

根据您的日程表重置截止日期。

完成时间大约为55 小时

英语(English)

字幕:中文(简体), 英语(English), 希伯来语, 西班牙语(Spanish), 印地语, 日语...

您将获得的技能

Logistic RegressionArtificial Neural NetworkMachine Learning (ML) AlgorithmsMachine Learning

100% 在线

立即开始,按照自己的计划学习。

可灵活调整截止日期

根据您的日程表重置截止日期。

完成时间大约为55 小时

英语(English)

字幕:中文(简体), 英语(English), 希伯来语, 西班牙语(Spanish), 印地语, 日语...

教学大纲 - 您将从这门课程中学到什么

1
完成时间为 2 小时

Introduction

Welcome to Machine Learning! In this module, we introduce the core idea of teaching a computer to learn concepts using data—without being explicitly programmed. The Course Wiki is under construction. Please visit the resources tab for the most complete and up-to-date information....
5 个视频 (总计 42 分钟), 9 个阅读材料, 1 个测验
5 个视频
Welcome6分钟
What is Machine Learning?7分钟
Supervised Learning12分钟
Unsupervised Learning14分钟
9 个阅读材料
Machine Learning Honor Code8分钟
What is Machine Learning?5分钟
How to Use Discussion Forums4分钟
Supervised Learning4分钟
Unsupervised Learning3分钟
Who are Mentors?3分钟
Get to Know Your Classmates8分钟
Frequently Asked Questions11分钟
Lecture Slides20分钟
1 个练习
Introduction10分钟
完成时间为 2 小时

Linear Regression with One Variable

Linear regression predicts a real-valued output based on an input value. We discuss the application of linear regression to housing price prediction, present the notion of a cost function, and introduce the gradient descent method for learning....
7 个视频 (总计 70 分钟), 8 个阅读材料, 1 个测验
7 个视频
Cost Function8分钟
Cost Function - Intuition I11分钟
Cost Function - Intuition II8分钟
Gradient Descent11分钟
Gradient Descent Intuition11分钟
Gradient Descent For Linear Regression10分钟
8 个阅读材料
Model Representation3分钟
Cost Function3分钟
Cost Function - Intuition I4分钟
Cost Function - Intuition II3分钟
Gradient Descent3分钟
Gradient Descent Intuition3分钟
Gradient Descent For Linear Regression6分钟
Lecture Slides20分钟
1 个练习
Linear Regression with One Variable10分钟
完成时间为 2 小时

Linear Algebra Review

This optional module provides a refresher on linear algebra concepts. Basic understanding of linear algebra is necessary for the rest of the course, especially as we begin to cover models with multiple variables....
6 个视频 (总计 61 分钟), 7 个阅读材料, 1 个测验
6 个视频
Addition and Scalar Multiplication6分钟
Matrix Vector Multiplication13分钟
Matrix Matrix Multiplication11分钟
Matrix Multiplication Properties9分钟
Inverse and Transpose11分钟
7 个阅读材料
Matrices and Vectors2分钟
Addition and Scalar Multiplication3分钟
Matrix Vector Multiplication2分钟
Matrix Matrix Multiplication2分钟
Matrix Multiplication Properties2分钟
Inverse and Transpose3分钟
Lecture Slides10分钟
1 个练习
Linear Algebra10分钟
2
完成时间为 3 小时

Linear Regression with Multiple Variables

What if your input has more than one value? In this module, we show how linear regression can be extended to accommodate multiple input features. We also discuss best practices for implementing linear regression....
8 个视频 (总计 65 分钟), 16 个阅读材料, 1 个测验
8 个视频
Gradient Descent for Multiple Variables5分钟
Gradient Descent in Practice I - Feature Scaling8分钟
Gradient Descent in Practice II - Learning Rate8分钟
Features and Polynomial Regression7分钟
Normal Equation16分钟
Normal Equation Noninvertibility5分钟
Working on and Submitting Programming Assignments3分钟
16 个阅读材料
Setting Up Your Programming Assignment Environment8分钟
Access MATLAB Online and Upload the Exercise Files3分钟
Installing Octave on Windows3分钟
Installing Octave on Mac OS X (10.10 Yosemite and 10.9 Mavericks and Later)10分钟
Installing Octave on Mac OS X (10.8 Mountain Lion and Earlier)3分钟
Installing Octave on GNU/Linux7分钟
More Octave/MATLAB resources10分钟
Multiple Features3分钟
Gradient Descent For Multiple Variables2分钟
Gradient Descent in Practice I - Feature Scaling3分钟
Gradient Descent in Practice II - Learning Rate4分钟
Features and Polynomial Regression3分钟
Normal Equation3分钟
Normal Equation Noninvertibility2分钟
Programming tips from Mentors10分钟
Lecture Slides20分钟
1 个练习
Linear Regression with Multiple Variables10分钟
完成时间为 5 小时

Octave/Matlab Tutorial

This course includes programming assignments designed to help you understand how to implement the learning algorithms in practice. To complete the programming assignments, you will need to use Octave or MATLAB. This module introduces Octave/Matlab and shows you how to submit an assignment....
6 个视频 (总计 80 分钟), 1 个阅读材料, 2 个测验
6 个视频
Moving Data Around16分钟
Computing on Data13分钟
Plotting Data9分钟
Control Statements: for, while, if statement12分钟
Vectorization13分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Octave/Matlab Tutorial10分钟
3
完成时间为 2 小时

Logistic Regression

Logistic regression is a method for classifying data into discrete outcomes. For example, we might use logistic regression to classify an email as spam or not spam. In this module, we introduce the notion of classification, the cost function for logistic regression, and the application of logistic regression to multi-class classification. ...
7 个视频 (总计 71 分钟), 8 个阅读材料, 1 个测验
7 个视频
Hypothesis Representation7分钟
Decision Boundary14分钟
Cost Function10分钟
Simplified Cost Function and Gradient Descent10分钟
Advanced Optimization14分钟
Multiclass Classification: One-vs-all6分钟
8 个阅读材料
Classification2分钟
Hypothesis Representation3分钟
Decision Boundary3分钟
Cost Function3分钟
Simplified Cost Function and Gradient Descent3分钟
Advanced Optimization3分钟
Multiclass Classification: One-vs-all3分钟
Lecture Slides10分钟
1 个练习
Logistic Regression10分钟
完成时间为 4 小时

Regularization

Machine learning models need to generalize well to new examples that the model has not seen in practice. In this module, we introduce regularization, which helps prevent models from overfitting the training data. ...
4 个视频 (总计 39 分钟), 5 个阅读材料, 2 个测验
4 个视频
Cost Function10分钟
Regularized Linear Regression10分钟
Regularized Logistic Regression8分钟
5 个阅读材料
The Problem of Overfitting3分钟
Cost Function3分钟
Regularized Linear Regression3分钟
Regularized Logistic Regression3分钟
Lecture Slides10分钟
1 个练习
Regularization10分钟
4
完成时间为 5 小时

Neural Networks: Representation

Neural networks is a model inspired by how the brain works. It is widely used today in many applications: when your phone interprets and understand your voice commands, it is likely that a neural network is helping to understand your speech; when you cash a check, the machines that automatically read the digits also use neural networks. ...
7 个视频 (总计 63 分钟), 6 个阅读材料, 2 个测验
7 个视频
Neurons and the Brain7分钟
Model Representation I12分钟
Model Representation II11分钟
Examples and Intuitions I7分钟
Examples and Intuitions II10分钟
Multiclass Classification3分钟
6 个阅读材料
Model Representation I6分钟
Model Representation II6分钟
Examples and Intuitions I2分钟
Examples and Intuitions II3分钟
Multiclass Classification3分钟
Lecture Slides10分钟
1 个练习
Neural Networks: Representation10分钟
5
完成时间为 5 小时

Neural Networks: Learning

In this module, we introduce the backpropagation algorithm that is used to help learn parameters for a neural network. At the end of this module, you will be implementing your own neural network for digit recognition. ...
8 个视频 (总计 78 分钟), 8 个阅读材料, 2 个测验
8 个视频
Backpropagation Algorithm11分钟
Backpropagation Intuition12分钟
Implementation Note: Unrolling Parameters7分钟
Gradient Checking11分钟
Random Initialization6分钟
Putting It Together13分钟
Autonomous Driving6分钟
8 个阅读材料
Cost Function4分钟
Backpropagation Algorithm10分钟
Backpropagation Intuition4分钟
Implementation Note: Unrolling Parameters3分钟
Gradient Checking3分钟
Random Initialization3分钟
Putting It Together4分钟
Lecture Slides10分钟
1 个练习
Neural Networks: Learning10分钟
6
完成时间为 5 小时

Advice for Applying Machine Learning

Applying machine learning in practice is not always straightforward. In this module, we share best practices for applying machine learning in practice, and discuss the best ways to evaluate performance of the learned models. ...
7 个视频 (总计 63 分钟), 7 个阅读材料, 2 个测验
7 个视频
Evaluating a Hypothesis7分钟
Model Selection and Train/Validation/Test Sets12分钟
Diagnosing Bias vs. Variance7分钟
Regularization and Bias/Variance11分钟
Learning Curves11分钟
Deciding What to Do Next Revisited6分钟
7 个阅读材料
Evaluating a Hypothesis4分钟
Model Selection and Train/Validation/Test Sets3分钟
Diagnosing Bias vs. Variance3分钟
Regularization and Bias/Variance3分钟
Learning Curves3分钟
Deciding What to do Next Revisited3分钟
Lecture Slides10分钟
1 个练习
Advice for Applying Machine Learning10分钟
完成时间为 1 小时

Machine Learning System Design

To optimize a machine learning algorithm, you’ll need to first understand where the biggest improvements can be made. In this module, we discuss how to understand the performance of a machine learning system with multiple parts, and also how to deal with skewed data. ...
5 个视频 (总计 60 分钟), 3 个阅读材料, 1 个测验
5 个视频
Error Analysis13分钟
Error Metrics for Skewed Classes11分钟
Trading Off Precision and Recall14分钟
Data For Machine Learning11分钟
3 个阅读材料
Prioritizing What to Work On3分钟
Error Analysis3分钟
Lecture Slides10分钟
1 个练习
Machine Learning System Design10分钟
7
完成时间为 5 小时

Support Vector Machines

Support vector machines, or SVMs, is a machine learning algorithm for classification. We introduce the idea and intuitions behind SVMs and discuss how to use it in practice. ...
6 个视频 (总计 98 分钟), 1 个阅读材料, 2 个测验
6 个视频
Large Margin Intuition10分钟
Mathematics Behind Large Margin Classification19分钟
Kernels I15分钟
Kernels II15分钟
Using An SVM21分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Support Vector Machines10分钟
8
完成时间为 1 小时

Unsupervised Learning

We use unsupervised learning to build models that help us understand our data better. We discuss the k-Means algorithm for clustering that enable us to learn groupings of unlabeled data points....
5 个视频 (总计 39 分钟), 1 个阅读材料, 1 个测验
5 个视频
K-Means Algorithm12分钟
Optimization Objective7分钟
Random Initialization7分钟
Choosing the Number of Clusters8分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Unsupervised Learning10分钟
完成时间为 4 小时

Dimensionality Reduction

In this module, we introduce Principal Components Analysis, and show how it can be used for data compression to speed up learning algorithms as well as for visualizations of complex datasets. ...
7 个视频 (总计 67 分钟), 1 个阅读材料, 2 个测验
7 个视频
Motivation II: Visualization5分钟
Principal Component Analysis Problem Formulation9分钟
Principal Component Analysis Algorithm15分钟
Reconstruction from Compressed Representation3分钟
Choosing the Number of Principal Components10分钟
Advice for Applying PCA12分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Principal Component Analysis10分钟
9
完成时间为 2 小时

Anomaly Detection

Given a large number of data points, we may sometimes want to figure out which ones vary significantly from the average. For example, in manufacturing, we may want to detect defects or anomalies. We show how a dataset can be modeled using a Gaussian distribution, and how the model can be used for anomaly detection. ...
8 个视频 (总计 91 分钟), 1 个阅读材料, 1 个测验
8 个视频
Gaussian Distribution10分钟
Algorithm12分钟
Developing and Evaluating an Anomaly Detection System13分钟
Anomaly Detection vs. Supervised Learning7分钟
Choosing What Features to Use12分钟
Multivariate Gaussian Distribution13分钟
Anomaly Detection using the Multivariate Gaussian Distribution14分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Anomaly Detection10分钟
完成时间为 4 小时

Recommender Systems

When you buy a product online, most websites automatically recommend other products that you may like. Recommender systems look at patterns of activities between different users and different products to produce these recommendations. In this module, we introduce recommender algorithms such as the collaborative filtering algorithm and low-rank matrix factorization....
6 个视频 (总计 58 分钟), 1 个阅读材料, 2 个测验
6 个视频
Content Based Recommendations14分钟
Collaborative Filtering10分钟
Collaborative Filtering Algorithm8分钟
Vectorization: Low Rank Matrix Factorization8分钟
Implementational Detail: Mean Normalization8分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Recommender Systems10分钟
10
完成时间为 1 小时

Large Scale Machine Learning

Machine learning works best when there is an abundance of data to leverage for training. In this module, we discuss how to apply the machine learning algorithms with large datasets....
6 个视频 (总计 64 分钟), 1 个阅读材料, 1 个测验
6 个视频
Stochastic Gradient Descent13分钟
Mini-Batch Gradient Descent6分钟
Stochastic Gradient Descent Convergence11分钟
Online Learning12分钟
Map Reduce and Data Parallelism14分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Large Scale Machine Learning10分钟
11
完成时间为 1 小时

Application Example: Photo OCR

Identifying and recognizing objects, words, and digits in an image is a challenging task. We discuss how a pipeline can be built to tackle this problem and how to analyze and improve the performance of such a system. ...
5 个视频 (总计 57 分钟), 1 个阅读材料, 1 个测验
5 个视频
Sliding Windows14分钟
Getting Lots of Data and Artificial Data16分钟
Ceiling Analysis: What Part of the Pipeline to Work on Next13分钟
Summary and Thank You4分钟
1 个阅读材料
Lecture Slides10分钟
1 个练习
Application: Photo OCR10分钟
4.9
25,415 个审阅Chevron Right

40%

完成这些课程后已开始新的职业生涯

38%

通过此课程获得实实在在的工作福利

热门审阅

创建者 OKApr 18th 2018

You need to know, what do you want to get out of this course. It gives you a lot of information, but be prepared to work hard with linear algeabra and make efforts to compute things in Mathlab/Octave.

创建者 SKOct 26th 2017

Amazing course for people looking to understand few important aspects of machine learning in terms of linear algebra and how the algorithms work! Definitely will help me in my future modelling efforts

讲师

Avatar

Andrew Ng

CEO/Founder Landing AI; Co-founder, Coursera; Adjunct Professor, Stanford University; formerly Chief Scientist,Baidu and founding lead of Google Brain

关于 斯坦福大学

The Leland Stanford Junior University, commonly referred to as Stanford University or Stanford, is an American private research university located in Stanford, California on an 8,180-acre (3,310 ha) campus near Palo Alto, California, United States....

常见问题

  • 注册以便获得证书后,您将有权访问所有视频、测验和编程作业(如果适用)。只有在您的班次开课之后,才可以提交和审阅同学互评作业。如果您选择在不购买的情况下浏览课程,可能无法访问某些作业。

  • 您购买证书后,将有权访问所有课程材料,包括评分作业。完成课程后,您的电子课程证书将添加到您的成就页中,您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容,可以免费旁听课程。

还有其他问题吗?请访问 学生帮助中心