Informações sobre o curso
4.9
102,428 classificações
25,453 avaliações

100% online

Comece imediatamente e aprenda em seu próprio cronograma.

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.

Aprox. 55 horas para completar

Inglês

Legendas: Chinês (simplificado), Inglês, Hebraico, Espanhol, Hindi, Japonês...

Habilidades que você terá

Logistic RegressionArtificial Neural NetworkMachine Learning (ML) AlgorithmsMachine Learning

100% online

Comece imediatamente e aprenda em seu próprio cronograma.

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.

Aprox. 55 horas para completar

Inglês

Legendas: Chinês (simplificado), Inglês, Hebraico, Espanhol, Hindi, Japonês...

Programa - O que você aprenderá com este curso

Semana
1
2 horas para concluir

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 vídeos (total de (Total 42 mín.) min), 9 leituras, 1 teste
5 videos
Welcome6min
What is Machine Learning?7min
Supervised Learning12min
Unsupervised Learning14min
9 leituras
Machine Learning Honor Code8min
What is Machine Learning?5min
How to Use Discussion Forums4min
Supervised Learning4min
Unsupervised Learning3min
Who are Mentors?3min
Get to Know Your Classmates8min
Frequently Asked Questions11min
Lecture Slides20min
1 exercício prático
Introduction10min
2 horas para concluir

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 vídeos (total de (Total 70 mín.) min), 8 leituras, 1 teste
7 videos
Cost Function8min
Cost Function - Intuition I11min
Cost Function - Intuition II8min
Gradient Descent11min
Gradient Descent Intuition11min
Gradient Descent For Linear Regression10min
8 leituras
Model Representation3min
Cost Function3min
Cost Function - Intuition I4min
Cost Function - Intuition II3min
Gradient Descent3min
Gradient Descent Intuition3min
Gradient Descent For Linear Regression6min
Lecture Slides20min
1 exercício prático
Linear Regression with One Variable10min
2 horas para concluir

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 vídeos (total de (Total 61 mín.) min), 7 leituras, 1 teste
6 videos
Addition and Scalar Multiplication6min
Matrix Vector Multiplication13min
Matrix Matrix Multiplication11min
Matrix Multiplication Properties9min
Inverse and Transpose11min
7 leituras
Matrices and Vectors2min
Addition and Scalar Multiplication3min
Matrix Vector Multiplication2min
Matrix Matrix Multiplication2min
Matrix Multiplication Properties2min
Inverse and Transpose3min
Lecture Slides10min
1 exercício prático
Linear Algebra10min
Semana
2
3 horas para concluir

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 vídeos (total de (Total 65 mín.) min), 16 leituras, 1 teste
8 videos
Gradient Descent for Multiple Variables5min
Gradient Descent in Practice I - Feature Scaling8min
Gradient Descent in Practice II - Learning Rate8min
Features and Polynomial Regression7min
Normal Equation16min
Normal Equation Noninvertibility5min
Working on and Submitting Programming Assignments3min
16 leituras
Setting Up Your Programming Assignment Environment8min
Access MATLAB Online and Upload the Exercise Files3min
Installing Octave on Windows3min
Installing Octave on Mac OS X (10.10 Yosemite and 10.9 Mavericks and Later)10min
Installing Octave on Mac OS X (10.8 Mountain Lion and Earlier)3min
Installing Octave on GNU/Linux7min
More Octave/MATLAB resources10min
Multiple Features3min
Gradient Descent For Multiple Variables2min
Gradient Descent in Practice I - Feature Scaling3min
Gradient Descent in Practice II - Learning Rate4min
Features and Polynomial Regression3min
Normal Equation3min
Normal Equation Noninvertibility2min
Programming tips from Mentors10min
Lecture Slides20min
1 exercício prático
Linear Regression with Multiple Variables10min
5 horas para concluir

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 vídeos (total de (Total 80 mín.) min), 1 leitura, 2 testes
6 videos
Moving Data Around16min
Computing on Data13min
Plotting Data9min
Control Statements: for, while, if statement12min
Vectorization13min
1 leituras
Lecture Slides10min
1 exercício prático
Octave/Matlab Tutorial10min
Semana
3
2 horas para concluir

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 vídeos (total de (Total 71 mín.) min), 8 leituras, 1 teste
7 videos
Hypothesis Representation7min
Decision Boundary14min
Cost Function10min
Simplified Cost Function and Gradient Descent10min
Advanced Optimization14min
Multiclass Classification: One-vs-all6min
8 leituras
Classification2min
Hypothesis Representation3min
Decision Boundary3min
Cost Function3min
Simplified Cost Function and Gradient Descent3min
Advanced Optimization3min
Multiclass Classification: One-vs-all3min
Lecture Slides10min
1 exercício prático
Logistic Regression10min
4 horas para concluir

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 vídeos (total de (Total 39 mín.) min), 5 leituras, 2 testes
4 videos
Cost Function10min
Regularized Linear Regression10min
Regularized Logistic Regression8min
5 leituras
The Problem of Overfitting3min
Cost Function3min
Regularized Linear Regression3min
Regularized Logistic Regression3min
Lecture Slides10min
1 exercício prático
Regularization10min
Semana
4
5 horas para concluir

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 vídeos (total de (Total 63 mín.) min), 6 leituras, 2 testes
7 videos
Neurons and the Brain7min
Model Representation I12min
Model Representation II11min
Examples and Intuitions I7min
Examples and Intuitions II10min
Multiclass Classification3min
6 leituras
Model Representation I6min
Model Representation II6min
Examples and Intuitions I2min
Examples and Intuitions II3min
Multiclass Classification3min
Lecture Slides10min
1 exercício prático
Neural Networks: Representation10min
Semana
5
5 horas para concluir

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 vídeos (total de (Total 78 mín.) min), 8 leituras, 2 testes
8 videos
Backpropagation Algorithm11min
Backpropagation Intuition12min
Implementation Note: Unrolling Parameters7min
Gradient Checking11min
Random Initialization6min
Putting It Together13min
Autonomous Driving6min
8 leituras
Cost Function4min
Backpropagation Algorithm10min
Backpropagation Intuition4min
Implementation Note: Unrolling Parameters3min
Gradient Checking3min
Random Initialization3min
Putting It Together4min
Lecture Slides10min
1 exercício prático
Neural Networks: Learning10min
Semana
6
5 horas para concluir

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 vídeos (total de (Total 63 mín.) min), 7 leituras, 2 testes
7 videos
Evaluating a Hypothesis7min
Model Selection and Train/Validation/Test Sets12min
Diagnosing Bias vs. Variance7min
Regularization and Bias/Variance11min
Learning Curves11min
Deciding What to Do Next Revisited6min
7 leituras
Evaluating a Hypothesis4min
Model Selection and Train/Validation/Test Sets3min
Diagnosing Bias vs. Variance3min
Regularization and Bias/Variance3min
Learning Curves3min
Deciding What to do Next Revisited3min
Lecture Slides10min
1 exercício prático
Advice for Applying Machine Learning10min
1 hora para concluir

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 vídeos (total de (Total 60 mín.) min), 3 leituras, 1 teste
5 videos
Error Analysis13min
Error Metrics for Skewed Classes11min
Trading Off Precision and Recall14min
Data For Machine Learning11min
3 leituras
Prioritizing What to Work On3min
Error Analysis3min
Lecture Slides10min
1 exercício prático
Machine Learning System Design10min
Semana
7
5 horas para concluir

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 vídeos (total de (Total 98 mín.) min), 1 leitura, 2 testes
6 videos
Large Margin Intuition10min
Mathematics Behind Large Margin Classification19min
Kernels I15min
Kernels II15min
Using An SVM21min
1 leituras
Lecture Slides10min
1 exercício prático
Support Vector Machines10min
Semana
8
1 hora para concluir

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 vídeos (total de (Total 39 mín.) min), 1 leitura, 1 teste
5 videos
K-Means Algorithm12min
Optimization Objective7min
Random Initialization7min
Choosing the Number of Clusters8min
1 leituras
Lecture Slides10min
1 exercício prático
Unsupervised Learning10min
4 horas para concluir

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 vídeos (total de (Total 67 mín.) min), 1 leitura, 2 testes
7 videos
Motivation II: Visualization5min
Principal Component Analysis Problem Formulation9min
Principal Component Analysis Algorithm15min
Reconstruction from Compressed Representation3min
Choosing the Number of Principal Components10min
Advice for Applying PCA12min
1 leituras
Lecture Slides10min
1 exercício prático
Principal Component Analysis10min
Semana
9
2 horas para concluir

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 vídeos (total de (Total 91 mín.) min), 1 leitura, 1 teste
8 videos
Gaussian Distribution10min
Algorithm12min
Developing and Evaluating an Anomaly Detection System13min
Anomaly Detection vs. Supervised Learning7min
Choosing What Features to Use12min
Multivariate Gaussian Distribution13min
Anomaly Detection using the Multivariate Gaussian Distribution14min
1 leituras
Lecture Slides10min
1 exercício prático
Anomaly Detection10min
4 horas para concluir

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 vídeos (total de (Total 58 mín.) min), 1 leitura, 2 testes
6 videos
Content Based Recommendations14min
Collaborative Filtering10min
Collaborative Filtering Algorithm8min
Vectorization: Low Rank Matrix Factorization8min
Implementational Detail: Mean Normalization8min
1 leituras
Lecture Slides10min
1 exercício prático
Recommender Systems10min
Semana
10
1 hora para concluir

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 vídeos (total de (Total 64 mín.) min), 1 leitura, 1 teste
6 videos
Stochastic Gradient Descent13min
Mini-Batch Gradient Descent6min
Stochastic Gradient Descent Convergence11min
Online Learning12min
Map Reduce and Data Parallelism14min
1 leituras
Lecture Slides10min
1 exercício prático
Large Scale Machine Learning10min
Semana
11
1 hora para concluir

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 vídeos (total de (Total 57 mín.) min), 1 leitura, 1 teste
5 videos
Sliding Windows14min
Getting Lots of Data and Artificial Data16min
Ceiling Analysis: What Part of the Pipeline to Work on Next13min
Summary and Thank You4min
1 leituras
Lecture Slides10min
1 exercício prático
Application: Photo OCR10min
4.9
25,453 avaliaçõesChevron Right

40%

comecei uma nova carreira após concluir estes cursos

37%

consegui um benefício significativo de carreira com este curso

Melhores avaliações

por NNOct 15th 2016

It's a good introduction - not too complicated and covers a wide range of topics. The programming exercises are well put together and significantly help understanding. The free Matlab license is nice.

por AANov 11th 2017

Great teaching style , Presentation is lucid, Assignments are at right difficulty level for the beginners to get an under the hood understanding without getting bogged down by the superfluous details.

Instrutores

Avatar

Andrew Ng

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

Sobre Universidade de Stanford

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....

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 adquire o Certificado, ganha acesso a todo o material do curso, incluindo avaliações com nota atribuída. Após concluir o curso, 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.