课程信息
4.6
1,471 个评分
260 个审阅
专项课程

第 4 门课程(共 4 门),位于

100% online

100% online

立即开始,按照自己的计划学习。
可灵活调整截止日期

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(小时)

完成时间大约为21 小时

建议:6 weeks of study, 5-8 hours/week...
可选语言

英语(English)

字幕:英语(English)...

您将获得的技能

Data Clustering AlgorithmsK-Means ClusteringMachine LearningK-D Tree
专项课程

第 4 门课程(共 4 门),位于

100% online

100% online

立即开始,按照自己的计划学习。
可灵活调整截止日期

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(小时)

完成时间大约为21 小时

建议:6 weeks of study, 5-8 hours/week...
可选语言

英语(English)

字幕:英语(English)...

教学大纲 - 您将从这门课程中学到什么

1
完成时间(小时)
完成时间为 1 小时

Welcome

Clustering and retrieval are some of the most high-impact machine learning tools out there. Retrieval is used in almost every applications and device we interact with, like in providing a set of products related to one a shopper is currently considering, or a list of people you might want to connect with on a social media platform. Clustering can be used to aid retrieval, but is a more broadly useful tool for automatically discovering structure in data, like uncovering groups of similar patients.<p>This introduction to the course provides you with an overview of the topics we will cover and the background knowledge and resources we assume you have....
Reading
4 个视频(共 25 分钟), 4 个阅读材料
Video4 个视频
Course overview3分钟
Module-by-module topics covered8分钟
Assumed background6分钟
Reading4 个阅读材料
Important Update regarding the Machine Learning Specialization10分钟
Slides presented in this module10分钟
Software tools you'll need for this course10分钟
A big week ahead!10分钟
2
完成时间(小时)
完成时间为 4 小时

Nearest Neighbor Search

We start the course by considering a retrieval task of fetching a document similar to one someone is currently reading. We cast this problem as one of nearest neighbor search, which is a concept we have seen in the Foundations and Regression courses. However, here, you will take a deep dive into two critical components of the algorithms: the data representation and metric for measuring similarity between pairs of datapoints. You will examine the computational burden of the naive nearest neighbor search algorithm, and instead implement scalable alternatives using KD-trees for handling large datasets and locality sensitive hashing (LSH) for providing approximate nearest neighbors, even in high-dimensional spaces. You will explore all of these ideas on a Wikipedia dataset, comparing and contrasting the impact of the various choices you can make on the nearest neighbor results produced....
Reading
22 个视频(共 137 分钟), 4 个阅读材料, 5 个测验
Video22 个视频
1-NN algorithm2分钟
k-NN algorithm6分钟
Document representation5分钟
Distance metrics: Euclidean and scaled Euclidean6分钟
Writing (scaled) Euclidean distance using (weighted) inner products4分钟
Distance metrics: Cosine similarity9分钟
To normalize or not and other distance considerations6分钟
Complexity of brute force search1分钟
KD-tree representation9分钟
NN search with KD-trees7分钟
Complexity of NN search with KD-trees5分钟
Visualizing scaling behavior of KD-trees4分钟
Approximate k-NN search using KD-trees7分钟
Limitations of KD-trees3分钟
LSH as an alternative to KD-trees4分钟
Using random lines to partition points5分钟
Defining more bins3分钟
Searching neighboring bins8分钟
LSH in higher dimensions4分钟
(OPTIONAL) Improving efficiency through multiple tables22分钟
A brief recap2分钟
Reading4 个阅读材料
Slides presented in this module10分钟
Choosing features and metrics for nearest neighbor search10分钟
(OPTIONAL) A worked-out example for KD-trees10分钟
Implementing Locality Sensitive Hashing from scratch10分钟
Quiz5 个练习
Representations and metrics12分钟
Choosing features and metrics for nearest neighbor search10分钟
KD-trees10分钟
Locality Sensitive Hashing10分钟
Implementing Locality Sensitive Hashing from scratch10分钟
3
完成时间(小时)
完成时间为 2 小时

Clustering with k-means

In clustering, our goal is to group the datapoints in our dataset into disjoint sets. Motivated by our document analysis case study, you will use clustering to discover thematic groups of articles by "topic". These topics are not provided in this unsupervised learning task; rather, the idea is to output such cluster labels that can be post-facto associated with known topics like "Science", "World News", etc. Even without such post-facto labels, you will examine how the clustering output can provide insights into the relationships between datapoints in the dataset. The first clustering algorithm you will implement is k-means, which is the most widely used clustering algorithm out there. To scale up k-means, you will learn about the general MapReduce framework for parallelizing and distributing computations, and then how the iterates of k-means can utilize this framework. You will show that k-means can provide an interpretable grouping of Wikipedia articles when appropriately tuned....
Reading
13 个视频(共 79 分钟), 2 个阅读材料, 3 个测验
Video13 个视频
An unsupervised task6分钟
Hope for unsupervised learning, and some challenge cases4分钟
The k-means algorithm7分钟
k-means as coordinate descent6分钟
Smart initialization via k-means++4分钟
Assessing the quality and choosing the number of clusters9分钟
Motivating MapReduce8分钟
The general MapReduce abstraction5分钟
MapReduce execution overview and combiners6分钟
MapReduce for k-means7分钟
Other applications of clustering7分钟
A brief recap1分钟
Reading2 个阅读材料
Slides presented in this module10分钟
Clustering text data with k-means10分钟
Quiz3 个练习
k-means18分钟
Clustering text data with K-means16分钟
MapReduce for k-means10分钟
4
完成时间(小时)
完成时间为 3 小时

Mixture Models

In k-means, observations are each hard-assigned to a single cluster, and these assignments are based just on the cluster centers, rather than also incorporating shape information. In our second module on clustering, you will perform probabilistic model-based clustering that provides (1) a more descriptive notion of a "cluster" and (2) accounts for uncertainty in assignments of datapoints to clusters via "soft assignments". You will explore and implement a broadly useful algorithm called expectation maximization (EM) for inferring these soft assignments, as well as the model parameters. To gain intuition, you will first consider a visually appealing image clustering task. You will then cluster Wikipedia articles, handling the high-dimensionality of the tf-idf document representation considered....
Reading
15 个视频(共 91 分钟), 4 个阅读材料, 3 个测验
Video15 个视频
Aggregating over unknown classes in an image dataset6分钟
Univariate Gaussian distributions2分钟
Bivariate and multivariate Gaussians7分钟
Mixture of Gaussians6分钟
Interpreting the mixture of Gaussian terms5分钟
Scaling mixtures of Gaussians for document clustering5分钟
Computing soft assignments from known cluster parameters7分钟
(OPTIONAL) Responsibilities as Bayes' rule5分钟
Estimating cluster parameters from known cluster assignments6分钟
Estimating cluster parameters from soft assignments8分钟
EM iterates in equations and pictures6分钟
Convergence, initialization, and overfitting of EM9分钟
Relationship to k-means3分钟
A brief recap1分钟
Reading4 个阅读材料
Slides presented in this module10分钟
(OPTIONAL) A worked-out example for EM10分钟
Implementing EM for Gaussian mixtures10分钟
Clustering text data with Gaussian mixtures10分钟
Quiz3 个练习
EM for Gaussian mixtures18分钟
Implementing EM for Gaussian mixtures12分钟
Clustering text data with Gaussian mixtures8分钟
4.6
职业方向

32%

完成这些课程后已开始新的职业生涯
工作福利

83%

通过此课程获得实实在在的工作福利

热门审阅

创建者 JMJan 17th 2017

Excellent course, well thought out lectures and problem sets. The programming assignments offer an appropriate amount of guidance that allows the students to work through the material on their own.

创建者 AGSep 25th 2017

Nice course with all the practical stuffs and nice analysis about each topic but practical part of LDA was restricted for GraphLab users only which is a weak fallback and rest everything is fine.

讲师

Avatar

Emily Fox

Amazon Professor of Machine Learning
Statistics
Avatar

Carlos Guestrin

Amazon Professor of Machine Learning
Computer Science and Engineering

关于 University of Washington

Founded in 1861, the University of Washington is one of the oldest state-supported institutions of higher education on the West Coast and is one of the preeminent research universities in the world....

关于 Machine Learning 专项课程

This Specialization from leading researchers at the University of Washington introduces you to the exciting, high-demand field of Machine Learning. Through a series of practical case studies, you will gain applied experience in major areas of Machine Learning including Prediction, Classification, Clustering, and Information Retrieval. You will learn to analyze large and complex datasets, create systems that adapt and improve over time, and build intelligent applications that can make predictions from data....
Machine Learning

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。

  • 您注册课程后,将有权访问专项课程中的所有课程,并且会在完成课程后获得证书。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