Coursera
Explorar
  • Navegar
  • Pesquisar
  • For Enterprise
  • Entrar
  • Criar conta

Fundações do aprendizado de máquina: uma abordagem por estudo de caso

Visão geralProgramaPerguntas frequentesDesenvolvedoresCustoClassificações e avaliações

Página inicialCiência de DadosAprendizagem Automática

Fundações do aprendizado de máquina: uma abordagem por estudo de caso

Universidade de Washington

Informações sobre o curso: Do you have data and wonder what it can tell you? Do you need a deeper understanding of the core ways in which machine learning can improve your business? Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems? In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images. Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains. This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications. Learning Outcomes: By the end of this course, you will be able to: -Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering. -Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning. -Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task. -Utilize a dataset to fit a model to analyze new data. -Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python.


Desenvolvido por:  Universidade de Washington
Universidade de Washington

  • Carlos Guestrin

    Ministrado por:  Carlos Guestrin, Amazon Professor of Machine Learning

    Computer Science and Engineering

  • Emily Fox

    Ministrado por:  Emily Fox, Amazon Professor of Machine Learning

    Statistics
Informações básicas
Curso 1 de 4 no Aprendizagem Automática Specialization
Compromisso6 weeks of study, 5-8 hours/week
Idioma
English, Legendas: Korean, Vietnamese, Chinese (Simplified)
Como ser aprovadoSeja aprovado em todas as tarefas para concluir o curso.
Classificação do usuário
4.6 estrelas
Classificação média do usuário 4.6Veja o que os aprendizes disseram
Programa
SEMANA 1
Welcome
Machine learning is everywhere, but is often operating behind the scenes. <p>This introduction to the specialization provides you with insights into the power of machine learning, and the multitude of intelligent applications you personally will be able to develop and deploy upon completion.</p>We also discuss who we are, how we got here, and our view of the future of intelligent applications.
18 vídeos, 6 leituras
  1. Leyendo: Important Update regarding the Machine Learning Specialization
  2. Leyendo: Slides presented in this module
  3. Vídeo: Welcome to this course and specialization
  4. Vídeo: Who we are
  5. Vídeo: Machine learning is changing the world
  6. Vídeo: Why a case study approach?
  7. Vídeo: Specialization overview
  8. Vídeo: How we got into ML
  9. Vídeo: Who is this specialization for?
  10. Vídeo: What you'll be able to do
  11. Vídeo: The capstone and an example intelligent application
  12. Vídeo: The future of intelligent applications
  13. Leyendo: Reading: Getting started with Python, IPython Notebook & GraphLab Create
  14. Leyendo: Reading: where should my files go?
  15. Leyendo: Download the IPython Notebook used in this lesson to follow along
  16. Vídeo: Starting an IPython Notebook
  17. Vídeo: Creating variables in Python
  18. Vídeo: Conditional statements and loops in Python
  19. Vídeo: Creating functions and lambdas in Python
  20. Leyendo: Download the IPython Notebook used in this lesson to follow along
  21. Vídeo: Starting GraphLab Create & loading an SFrame
  22. Vídeo: Canvas for data visualization
  23. Vídeo: Interacting with columns of an SFrame
  24. Vídeo: Using .apply() for data transformation
SEMANA 2
Regression: Predicting House Prices
This week you will build your first intelligent application that makes predictions from data.<p>We will explore this idea within the context of our first case study, predicting house prices, where you will create models that predict a continuous value (price) from input features (square footage, number of bedrooms and bathrooms,...). <p>This is just one of the many places where regression can be applied.Other applications range from predicting health outcomes in medicine, stock prices in finance, and power usage in high-performance computing, to analyzing which regulators are important for gene expression.</p>You will also examine how to analyze the performance of your predictive model and implement regression in practice using an iPython notebook.
19 vídeos, 3 leituras
  1. Leyendo: Slides presented in this module
  2. Vídeo: Predicting house prices: A case study in regression
  3. Vídeo: What is the goal and how might you naively address it?
  4. Vídeo: Linear Regression: A Model-Based Approach
  5. Vídeo: Adding higher order effects
  6. Vídeo: Evaluating overfitting via training/test split
  7. Vídeo: Training/test curves
  8. Vídeo: Adding other features
  9. Vídeo: Other regression examples
  10. Vídeo: Regression ML block diagram
  11. Leyendo: Download the IPython Notebook used in this lesson to follow along
  12. Vídeo: Loading & exploring house sale data
  13. Vídeo: Splitting the data into training and test sets
  14. Vídeo: Learning a simple regression model to predict house prices from house size
  15. Vídeo: Evaluating error (RMSE) of the simple model
  16. Vídeo: Visualizing predictions of simple model with Matplotlib
  17. Vídeo: Inspecting the model coefficients learned
  18. Vídeo: Exploring other features of the data
  19. Vídeo: Learning a model to predict house prices from more features
  20. Vídeo: Applying learned models to predict price of an average house
  21. Vídeo: Applying learned models to predict price of two fancy houses
  22. Leyendo: Reading: Predicting house prices assignment
Nota atribuída: Regression
Nota atribuída: Predicting house prices
SEMANA 3
Classification: Analyzing Sentiment
How do you guess whether a person felt positively or negatively about an experience, just from a short review they wrote?<p>In our second case study, analyzing sentiment, you will create models that predict a class (positive/negative sentiment) from input features (text of the reviews, user profile information,...).This task is an example of classification, one of the most widely used areas of machine learning, with a broad array of applications, including ad targeting, spam detection, medical diagnosis and image classification.</p>You will analyze the accuracy of your classifier, implement an actual classifier in an iPython notebook, and take a first stab at a core piece of the intelligent application you will build and deploy in your capstone.
19 vídeos, 3 leituras
  1. Leyendo: Slides presented in this module
  2. Vídeo: Analyzing the sentiment of reviews: A case study in classification
  3. Vídeo: What is an intelligent restaurant review system?
  4. Vídeo: Examples of classification tasks
  5. Vídeo: Linear classifiers
  6. Vídeo: Decision boundaries
  7. Vídeo: Training and evaluating a classifier
  8. Vídeo: What's a good accuracy?
  9. Vídeo: False positives, false negatives, and confusion matrices
  10. Vídeo: Learning curves
  11. Vídeo: Class probabilities
  12. Vídeo: Classification ML block diagram
  13. Leyendo: Download the IPython Notebook used in this lesson to follow along
  14. Vídeo: Loading & exploring product review data
  15. Vídeo: Creating the word count vector
  16. Vídeo: Exploring the most popular product
  17. Vídeo: Defining which reviews have positive or negative sentiment
  18. Vídeo: Training a sentiment classifier
  19. Vídeo: Evaluating a classifier & the ROC curve
  20. Vídeo: Applying model to find most positive & negative reviews for a product
  21. Vídeo: Exploring the most positive & negative aspects of a product
  22. Leyendo: Reading: Analyzing product sentiment assignment
Nota atribuída: Classification
Nota atribuída: Analyzing product sentiment
SEMANA 4
Clustering and Similarity: Retrieving Documents
A reader is interested in a specific news article and you want to find a similar articles to recommend. What is the right notion of similarity? How do I automatically search over documents to find the one that is most similar? How do I quantitatively represent the documents in the first place?<p>In this third case study, retrieving documents, you will examine various document representations and an algorithm to retrieve the most similar subset. You will also consider structured representations of the documents that automatically group articles by similarity (e.g., document topic).</p>You will actually build an intelligent document retrieval system for Wikipedia entries in an iPython notebook.
17 vídeos, 3 leituras
  1. Leyendo: Slides presented in this module
  2. Vídeo: Document retrieval: A case study in clustering and measuring similarity
  3. Vídeo: What is the document retrieval task?
  4. Vídeo: Word count representation for measuring similarity
  5. Vídeo: Prioritizing important words with tf-idf
  6. Vídeo: Calculating tf-idf vectors
  7. Vídeo: Retrieving similar documents using nearest neighbor search
  8. Vídeo: Clustering documents task overview
  9. Vídeo: Clustering documents: An unsupervised learning task
  10. Vídeo: k-means: A clustering algorithm
  11. Vídeo: Other examples of clustering
  12. Vídeo: Clustering and similarity ML block diagram
  13. Leyendo: Download the IPython Notebook used in this lesson to follow along
  14. Vídeo: Loading & exploring Wikipedia data
  15. Vídeo: Exploring word counts
  16. Vídeo: Computing & exploring TF-IDFs
  17. Vídeo: Computing distances between Wikipedia articles
  18. Vídeo: Building & exploring a nearest neighbors model for Wikipedia articles
  19. Vídeo: Examples of document retrieval in action
  20. Leyendo: Reading: Retrieving Wikipedia articles assignment
Nota atribuída: Clustering and Similarity
Nota atribuída: Retrieving Wikipedia articles
SEMANA 5
Recommending Products
Ever wonder how Amazon forms its personalized product recommendations? How Netflix suggests movies to watch? How Pandora selects the next song to stream? How Facebook or LinkedIn finds people you might connect with? Underlying all of these technologies for personalized content is something called collaborative filtering. <p>You will learn how to build such a recommender system using a variety of techniques, and explore their tradeoffs.</p> One method we examine is matrix factorization, which learns features of users and products to form recommendations. In an iPython notebook, you will use these techniques to build a real song recommender system.
19 vídeos, 3 leituras
  1. Leyendo: Slides presented in this module
  2. Vídeo: Recommender systems overview
  3. Vídeo: Where we see recommender systems in action
  4. Vídeo: Building a recommender system via classification
  5. Vídeo: Collaborative filtering: People who bought this also bought...
  6. Vídeo: Effect of popular items
  7. Vídeo: Normalizing co-occurrence matrices and leveraging purchase histories
  8. Vídeo: The matrix completion task
  9. Vídeo: Recommendations from known user/item features
  10. Vídeo: Predictions in matrix form
  11. Vídeo: Discovering hidden structure by matrix factorization
  12. Vídeo: Bringing it all together: Featurized matrix factorization
  13. Vídeo: A performance metric for recommender systems
  14. Vídeo: Optimal recommenders
  15. Vídeo: Precision-recall curves
  16. Vídeo: Recommender systems ML block diagram
  17. Leyendo: Download the IPython Notebook used in this lesson to follow along
  18. Vídeo: Loading and exploring song data
  19. Vídeo: Creating & evaluating a popularity-based song recommender
  20. Vídeo: Creating & evaluating a personalized song recommender
  21. Vídeo: Using precision-recall to compare recommender models
  22. Leyendo: Reading: Recommending songs assignment
Nota atribuída: Recommender Systems
Nota atribuída: Recommending songs
SEMANA 6
Deep Learning: Searching for Images
You’ve probably heard that Deep Learning is making news across the world as one of the most promising techniques in machine learning. Every industry is dedicating resources to unlock the deep learning potential, including for tasks such as image tagging, object recognition, speech recognition, and text analysis.<p>In our final case study, searching for images, you will learn how layers of neural networks provide very descriptive (non-linear) features that provide impressive performance in image classification and retrieval tasks. You will then construct deep features, a transfer learning technique that allows you to use deep learning very easily, even when you have little data to train the model.</p>Using iPhython notebooks, you will build an image classifier and an intelligent image retrieval system with deep learning.
18 vídeos, 4 leituras
  1. Leyendo: Slides presented in this module
  2. Vídeo: Searching for images: A case study in deep learning
  3. Vídeo: What is a visual product recommender?
  4. Vídeo: Learning very non-linear features with neural networks
  5. Vídeo: Application of deep learning to computer vision
  6. Vídeo: Deep learning performance
  7. Vídeo: Demo of deep learning model on ImageNet data
  8. Vídeo: Other examples of deep learning in computer vision
  9. Vídeo: Challenges of deep learning
  10. Vídeo: Deep Features
  11. Vídeo: Deep learning ML block diagram
  12. Leyendo: Download the IPython Notebook used in this lesson to follow along
  13. Vídeo: Loading image data
  14. Vídeo: Training & evaluating a classifier using raw image pixels
  15. Vídeo: Training & evaluating a classifier using deep features
  16. Leyendo: Download the IPython Notebook used in this lesson to follow along
  17. Vídeo: Loading image data
  18. Vídeo: Creating a nearest neighbors model for image retrieval
  19. Vídeo: Querying the nearest neighbors model to retrieve images
  20. Vídeo: Querying for the most similar images for car image
  21. Vídeo: Displaying other example image retrievals with a Python lambda
  22. Leyendo: Reading: Deep features for image retrieval assignment
Nota atribuída: Deep Learning
Nota atribuída: Deep features for image retrieval
Closing Remarks
In the conclusion of the course, we will describe the final stage in turning our machine learning tools into a service: deployment.<p>We will also discuss some open challenges that the field of machine learning still faces, and where we think machine learning is heading. We conclude with an overview of what's in store for you in the rest of the specialization, and the amazing intelligent applications that are ahead for us as we evolve machine learning.
7 vídeos, 1 leitura
  1. Leyendo: Slides presented in this module
  2. Vídeo: You've made it!
  3. Vídeo: Deploying an ML service
  4. Vídeo: What happens after deployment?
  5. Vídeo: Open challenges in ML
  6. Vídeo: Where is ML going?
  7. Vídeo: What's ahead in the specialization
  8. Vídeo: Thank you!

Perguntas frequentes
Como funciona
Trabajo del curso
Trabajo del curso

Cada curso es como un libro de texto interactivo, con videos pregrabados, cuestionarios y proyectos.

Ayuda de tus compañeros
Ayuda de tus compañeros

Conéctate con miles de estudiantes y debate ideas y materiales del curso, y obtén ayuda para dominar los conceptos.

Certificados
Certificados

Obtén reconocimiento oficial por tu trabajo y comparte tu éxito con amigos, compañeros y empleadores.

Desenvolvedores
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.
Custo
Comprar curso
Acesso aos materiais do curso

Disponível

Acesso a materiais valendo nota

Disponível

Receba uma nota final

Disponível

Obtenha um Certificado de Curso compartilhável

Disponível

Classificações e avaliações
Avaliado em 4.6 de 5 decorrente de 6,918 avaliações

AJ

Great course for a beginning in the Machine Learning World

Frank Zhu

Very Great machine learning Class!

RR

Very well presented and organised

DA

Well taught, info really sinks in. For python could we of used pandas.



Talvez você também goste de
Universidade de Washington
Machine Learning: Regression
1 curso
Universidade de Washington
Machine Learning: Regression
Visualizar curso
Universidade de Washington
Machine Learning: Classification
1 curso
Universidade de Washington
Machine Learning: Classification
Visualizar curso
Universidade de Washington
Machine Learning: Clustering & Retrieval
1 curso
Universidade de Washington
Machine Learning: Clustering & Retrieval
Visualizar curso
University of Michigan
Using Python to Access Web Data
1 curso
University of Michigan
Using Python to Access Web Data
Visualizar curso
University of Michigan
Applied Machine Learning in Python
1 curso
University of Michigan
Applied Machine Learning in Python
Visualizar curso
Coursera
O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.
© 2018 Coursera Inc. Todos os direitos reservados.
Baixar na App StoreBaixar no Google Play
  • Coursera
  • Sobre
  • Liderança
  • Carreiras
  • Lista de cursos
  • Certificados
  • Notas
  • Para negócios
  • For Government
  • Comunidade
  • parceiros
  • Orientadores
  • Tradutores
  • Desenvolvedores
  • Testadores beta
  • Conectar
  • Blog
  • Facebook
  • LinkedIn
  • Twitter
  • Google+
  • Tech Blog
  • Mais
  • Termos
  • Privacidade
  • Ajuda
  • Acessibilidade
  • Imprensa
  • Contato
  • Diretório
  • Afiliados