Informações sobre o curso
38,015 visualizações recentes

100% online

Comece imediatamente e aprenda em seu próprio cronograma.

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.

Aprox. 48 horas para completar

Sugerido: 6 weeks of study, 5-8 hours/week...


Legendas: Inglês, Coreano, Árabe

Habilidades que você terá

Data Clustering AlgorithmsK-Means ClusteringMachine LearningK-D Tree

100% online

Comece imediatamente e aprenda em seu próprio cronograma.

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.

Aprox. 48 horas para completar

Sugerido: 6 weeks of study, 5-8 hours/week...


Legendas: Inglês, Coreano, Árabe

Programa - O que você aprenderá com este curso

1 hora para concluir


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.

4 vídeos ((Total 25 mín.)), 4 leituras
4 videos
Course overview3min
Module-by-module topics covered8min
Assumed background6min
4 leituras
Important Update regarding the Machine Learning Specialization10min
Slides presented in this module10min
Software tools you'll need for this course10min
A big week ahead!10min
4 horas para concluir

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.

22 vídeos ((Total 137 mín.)), 4 leituras, 5 testes
22 videos
1-NN algorithm2min
k-NN algorithm6min
Document representation5min
Distance metrics: Euclidean and scaled Euclidean6min
Writing (scaled) Euclidean distance using (weighted) inner products4min
Distance metrics: Cosine similarity9min
To normalize or not and other distance considerations6min
Complexity of brute force search1min
KD-tree representation9min
NN search with KD-trees7min
Complexity of NN search with KD-trees5min
Visualizing scaling behavior of KD-trees4min
Approximate k-NN search using KD-trees7min
Limitations of KD-trees3min
LSH as an alternative to KD-trees4min
Using random lines to partition points5min
Defining more bins3min
Searching neighboring bins8min
LSH in higher dimensions4min
(OPTIONAL) Improving efficiency through multiple tables22min
A brief recap2min
4 leituras
Slides presented in this module10min
Choosing features and metrics for nearest neighbor search10min
(OPTIONAL) A worked-out example for KD-trees10min
Implementing Locality Sensitive Hashing from scratch10min
5 exercícios práticos
Representations and metrics12min
Choosing features and metrics for nearest neighbor search10min
Locality Sensitive Hashing10min
Implementing Locality Sensitive Hashing from scratch10min
2 horas para concluir

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.

13 vídeos ((Total 79 mín.)), 2 leituras, 3 testes
13 videos
An unsupervised task6min
Hope for unsupervised learning, and some challenge cases4min
The k-means algorithm7min
k-means as coordinate descent6min
Smart initialization via k-means++4min
Assessing the quality and choosing the number of clusters9min
Motivating MapReduce8min
The general MapReduce abstraction5min
MapReduce execution overview and combiners6min
MapReduce for k-means7min
Other applications of clustering7min
A brief recap1min
2 leituras
Slides presented in this module10min
Clustering text data with k-means10min
3 exercícios práticos
Clustering text data with K-means16min
MapReduce for k-means10min
3 horas para concluir

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.

15 vídeos ((Total 91 mín.)), 4 leituras, 3 testes
15 videos
Aggregating over unknown classes in an image dataset6min
Univariate Gaussian distributions2min
Bivariate and multivariate Gaussians7min
Mixture of Gaussians6min
Interpreting the mixture of Gaussian terms5min
Scaling mixtures of Gaussians for document clustering5min
Computing soft assignments from known cluster parameters7min
(OPTIONAL) Responsibilities as Bayes' rule5min
Estimating cluster parameters from known cluster assignments6min
Estimating cluster parameters from soft assignments8min
EM iterates in equations and pictures6min
Convergence, initialization, and overfitting of EM9min
Relationship to k-means3min
A brief recap1min
4 leituras
Slides presented in this module10min
(OPTIONAL) A worked-out example for EM10min
Implementing EM for Gaussian mixtures10min
Clustering text data with Gaussian mixtures10min
3 exercícios práticos
EM for Gaussian mixtures18min
Implementing EM for Gaussian mixtures12min
Clustering text data with Gaussian mixtures8min
290 avaliaçõesChevron Right


comecei uma nova carreira após concluir estes cursos


consegui um benefício significativo de carreira com este curso

Principais avaliações do Machine Learning: Clustering & Retrieval

por BKAug 25th 2016

excellent material! It would be nice, however, to mention some reading material, books or articles, for those interested in the details and the theories behind the concepts presented in the course.

por 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.



Emily Fox

Amazon Professor of Machine Learning

Carlos Guestrin

Amazon Professor of Machine Learning
Computer Science and Engineering

Sobre Universidade de 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....

Sobre o Programa de cursos integrados Aprendizagem Automática

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....
Aprendizagem Automática

Perguntas Frequentes – FAQ

  • Ao se inscrever para um Certificado, você terá acesso a todos os vídeos, testes e tarefas de programação (se aplicável). Tarefas avaliadas pelos colegas apenas podem ser enviadas e avaliadas após o início da sessão. Caso escolha explorar o curso sem adquiri-lo, talvez você não consiga acessar certas tarefas.

  • Quando você se inscreve no curso, tem acesso a todos os cursos na Especialização e pode obter um certificado quando concluir o trabalho. Seu Certificado eletrônico será adicionado à sua página de Participações e você poderá imprimi-lo ou adicioná-lo ao seu perfil no LinkedIn. Se quiser apenas ler e assistir o conteúdo do curso, você poderá frequentá-lo como ouvinte sem custo.

Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.