Acerca de este Curso
98,910 vistas recientes

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Aprox. 36 horas para completar

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

Inglés (English)

Subtítulos: Inglés (English), Coreano, Árabe (Arabic)

Habilidades que obtendrás

Linear RegressionRidge RegressionLasso (Statistics)Regression Analysis

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Aprox. 36 horas para completar

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

Inglés (English)

Subtítulos: Inglés (English), Coreano, Árabe (Arabic)

Programa - Qué aprenderás en este curso

1 hora para completar


Regression is one of the most important and broadly used machine learning and statistics tools out there. It allows you to make predictions from data by learning the relationship between features of your data and some observed, continuous-valued response. Regression is used in a massive number of applications ranging from predicting stock prices to understanding gene regulatory networks.<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.

5 videos (Total 20 minutos), 3 readings
5 videos
What is the course about?3m
Outlining the first half of the course5m
Outlining the second half of the course5m
Assumed background4m
3 lecturas
Important Update regarding the Machine Learning Specialization10m
Slides presented in this module10m
Reading: Software tools you'll need10m
3 horas para completar

Simple Linear Regression

Our course starts from the most basic regression model: Just fitting a line to data. This simple model for forming predictions from a single, univariate feature of the data is appropriately called "simple linear regression".<p> In this module, we describe the high-level regression task and then specialize these concepts to the simple linear regression case. You will learn how to formulate a simple regression model and fit the model to data using both a closed-form solution as well as an iterative optimization algorithm called gradient descent. Based on this fitted function, you will interpret the estimated model parameters and form predictions. You will also analyze the sensitivity of your fit to outlying observations.<p> You will examine all of these concepts in the context of a case study of predicting house prices from the square feet of the house.

25 videos (Total 122 minutos), 5 readings, 2 quizzes
25 videos
Regression fundamentals: data & model8m
Regression fundamentals: the task2m
Regression ML block diagram4m
The simple linear regression model2m
The cost of using a given line6m
Using the fitted line6m
Interpreting the fitted line6m
Defining our least squares optimization objective3m
Finding maxima or minima analytically7m
Maximizing a 1d function: a worked example2m
Finding the max via hill climbing6m
Finding the min via hill descent3m
Choosing stepsize and convergence criteria6m
Gradients: derivatives in multiple dimensions5m
Gradient descent: multidimensional hill descent6m
Computing the gradient of RSS7m
Approach 1: closed-form solution5m
Approach 2: gradient descent7m
Comparing the approaches1m
Influence of high leverage points: exploring the data4m
Influence of high leverage points: removing Center City7m
Influence of high leverage points: removing high-end towns3m
Asymmetric cost functions3m
A brief recap1m
5 lecturas
Slides presented in this module10m
Optional reading: worked-out example for closed-form solution10m
Optional reading: worked-out example for gradient descent10m
Download notebooks to follow along10m
Reading: Fitting a simple linear regression model on housing data10m
2 ejercicios de práctica
Simple Linear Regression14m
Fitting a simple linear regression model on housing data8m
3 horas para completar

Multiple Regression

The next step in moving beyond simple linear regression is to consider "multiple regression" where multiple features of the data are used to form predictions. <p> More specifically, in this module, you will learn how to build models of more complex relationship between a single variable (e.g., 'square feet') and the observed response (like 'house sales price'). This includes things like fitting a polynomial to your data, or capturing seasonal changes in the response value. You will also learn how to incorporate multiple input variables (e.g., 'square feet', '# bedrooms', '# bathrooms'). You will then be able to describe how all of these models can still be cast within the linear regression framework, but now using multiple "features". Within this multiple regression framework, you will fit models to data, interpret estimated coefficients, and form predictions. <p>Here, you will also implement a gradient descent algorithm for fitting a multiple regression model.

19 videos (Total 87 minutos), 5 readings, 3 quizzes
19 videos
Polynomial regression3m
Modeling seasonality8m
Where we see seasonality3m
Regression with general features of 1 input2m
Motivating the use of multiple inputs4m
Defining notation3m
Regression with features of multiple inputs3m
Interpreting the multiple regression fit7m
Rewriting the single observation model in vector notation6m
Rewriting the model for all observations in matrix notation4m
Computing the cost of a D-dimensional curve9m
Computing the gradient of RSS3m
Approach 1: closed-form solution3m
Discussing the closed-form solution4m
Approach 2: gradient descent2m
Feature-by-feature update9m
Algorithmic summary of gradient descent approach4m
A brief recap1m
5 lecturas
Slides presented in this module10m
Optional reading: review of matrix algebra10m
Reading: Exploring different multiple regression models for house price prediction10m
Numpy tutorial10m
Reading: Implementing gradient descent for multiple regression10m
3 ejercicios de práctica
Multiple Regression18m
Exploring different multiple regression models for house price prediction16m
Implementing gradient descent for multiple regression10m
2 horas para completar

Assessing Performance

Having learned about linear regression models and algorithms for estimating the parameters of such models, you are now ready to assess how well your considered method should perform in predicting new data. You are also ready to select amongst possible models to choose the best performing. <p> This module is all about these important topics of model selection and assessment. You will examine both theoretical and practical aspects of such analyses. You will first explore the concept of measuring the "loss" of your predictions, and use this to define training, test, and generalization error. For these measures of error, you will analyze how they vary with model complexity and how they might be utilized to form a valid assessment of predictive performance. This leads directly to an important conversation about the bias-variance tradeoff, which is fundamental to machine learning. Finally, you will devise a method to first select amongst models and then assess the performance of the selected model. <p>The concepts described in this module are key to all machine learning problems, well-beyond the regression setting addressed in this course.

14 videos (Total 93 minutos), 2 readings, 2 quizzes
14 videos
What do we mean by "loss"?4m
Training error: assessing loss on the training set7m
Generalization error: what we really want8m
Test error: what we can actually compute4m
Defining overfitting2m
Training/test split1m
Irreducible error and bias6m
Variance and the bias-variance tradeoff6m
Error vs. amount of data6m
Formally defining the 3 sources of error14m
Formally deriving why 3 sources of error20m
Training/validation/test split for model selection, fitting, and assessment7m
A brief recap1m
2 lecturas
Slides presented in this module10m
Reading: Exploring the bias-variance tradeoff10m
2 ejercicios de práctica
Assessing Performance26m
Exploring the bias-variance tradeoff8m
3 horas para completar

Ridge Regression

You have examined how the performance of a model varies with increasing model complexity, and can describe the potential pitfall of complex models becoming overfit to the training data. In this module, you will explore a very simple, but extremely effective technique for automatically coping with this issue. This method is called "ridge regression". You start out with a complex model, but now fit the model in a manner that not only incorporates a measure of fit to the training data, but also a term that biases the solution away from overfitted functions. To this end, you will explore symptoms of overfitted functions and use this to define a quantitative measure to use in your revised optimization objective. You will derive both a closed-form and gradient descent algorithm for fitting the ridge regression objective; these forms are small modifications from the original algorithms you derived for multiple regression. To select the strength of the bias away from overfitting, you will explore a general-purpose method called "cross validation". <p>You will implement both cross-validation and gradient descent to fit a ridge regression model and select the regularization constant.

16 videos (Total 85 minutos), 5 readings, 3 quizzes
16 videos
Overfitting demo7m
Overfitting for more general multiple regression models3m
Balancing fit and magnitude of coefficients7m
The resulting ridge objective and its extreme solutions5m
How ridge regression balances bias and variance1m
Ridge regression demo9m
The ridge coefficient path4m
Computing the gradient of the ridge objective5m
Approach 1: closed-form solution6m
Discussing the closed-form solution5m
Approach 2: gradient descent9m
Selecting tuning parameters via cross validation3m
K-fold cross validation5m
How to handle the intercept6m
A brief recap1m
5 lecturas
Slides presented in this module10m
Download the notebook and follow along10m
Download the notebook and follow along10m
Reading: Observing effects of L2 penalty in polynomial regression10m
Reading: Implementing ridge regression via gradient descent10m
3 ejercicios de práctica
Ridge Regression18m
Observing effects of L2 penalty in polynomial regression14m
Implementing ridge regression via gradient descent16m
3 horas para completar

Feature Selection & Lasso

A fundamental machine learning task is to select amongst a set of features to include in a model. In this module, you will explore this idea in the context of multiple regression, and describe how such feature selection is important for both interpretability and efficiency of forming predictions. <p> To start, you will examine methods that search over an enumeration of models including different subsets of features. You will analyze both exhaustive search and greedy algorithms. Then, instead of an explicit enumeration, we turn to Lasso regression, which implicitly performs feature selection in a manner akin to ridge regression: A complex model is fit based on a measure of fit to the training data plus a measure of overfitting different than that used in ridge. This lasso method has had impact in numerous applied domains, and the ideas behind the method have fundamentally changed machine learning and statistics. You will also implement a coordinate descent algorithm for fitting a Lasso model. <p>Coordinate descent is another, general, optimization technique, which is useful in many areas of machine learning.

22 videos (Total 126 minutos), 4 readings, 3 quizzes
22 videos
All subsets6m
Complexity of all subsets3m
Greedy algorithms7m
Complexity of the greedy forward stepwise algorithm2m
Can we use regularization for feature selection?3m
Thresholding ridge coefficients?4m
The lasso objective and its coefficient path7m
Visualizing the ridge cost7m
Visualizing the ridge solution6m
Visualizing the lasso cost and solution7m
Lasso demo5m
What makes the lasso objective different3m
Coordinate descent5m
Normalizing features3m
Coordinate descent for least squares regression (normalized features)8m
Coordinate descent for lasso (normalized features)5m
Assessing convergence and other lasso solvers2m
Coordinate descent for lasso (unnormalized features)1m
Deriving the lasso coordinate descent update19m
Choosing the penalty strength and other practical issues with lasso5m
A brief recap3m
4 lecturas
Slides presented in this module10m
Download the notebook and follow along10m
Reading: Using LASSO to select features10m
Reading: Implementing LASSO using coordinate descent10m
3 ejercicios de práctica
Feature Selection and Lasso14m
Using LASSO to select features12m
Implementing LASSO using coordinate descent16m
2 horas para completar

Nearest Neighbors & Kernel Regression

Up to this point, we have focused on methods that fit parametric functions---like polynomials and hyperplanes---to the entire dataset. In this module, we instead turn our attention to a class of "nonparametric" methods. These methods allow the complexity of the model to increase as more data are observed, and result in fits that adapt locally to the observations. <p> We start by considering the simple and intuitive example of nonparametric methods, nearest neighbor regression: The prediction for a query point is based on the outputs of the most related observations in the training set. This approach is extremely simple, but can provide excellent predictions, especially for large datasets. You will deploy algorithms to search for the nearest neighbors and form predictions based on the discovered neighbors. Building on this idea, we turn to kernel regression. Instead of forming predictions based on a small set of neighboring observations, kernel regression uses all observations in the dataset, but the impact of these observations on the predicted value is weighted by their similarity to the query point. You will analyze the theoretical performance of these methods in the limit of infinite training data, and explore the scenarios in which these methods work well versus struggle. You will also implement these techniques and observe their practical behavior.

13 videos (Total 63 minutos), 2 readings, 2 quizzes
13 videos
1-Nearest neighbor regression approach8m
Distance metrics4m
1-Nearest neighbor algorithm3m
k-Nearest neighbors regression7m
k-Nearest neighbors in practice3m
Weighted k-nearest neighbors4m
From weighted k-NN to kernel regression6m
Global fits of parametric models vs. local fits of kernel regression6m
Performance of NN as amount of data grows7m
Issues with high-dimensions, data scarcity, and computational complexity3m
k-NN for classification1m
A brief recap1m
2 lecturas
Slides presented in this module10m
Reading: Predicting house prices using k-nearest neighbors regression10m
2 ejercicios de práctica
Nearest Neighbors & Kernel Regression14m
Predicting house prices using k-nearest neighbors regression16m
1 hora para completar

Closing Remarks

In the conclusion of the course, we will recap what we have covered. This represents both techniques specific to regression, as well as foundational machine learning concepts that will appear throughout the specialization. We also briefly discuss some important regression techniques we did not cover in this course.<p> We conclude with an overview of what's in store for you in the rest of the specialization.

5 videos (Total 23 minutos), 1 reading
5 videos
Assessing performance and ridge regression7m
Feature selection, lasso, and nearest neighbor regression4m
What we covered and what we didn't cover5m
Thank you!1m
1 lectura
Slides presented in this module10m
795 revisionesChevron Right


comenzó una nueva carrera después de completar estos cursos


consiguió un beneficio tangible en su carrera profesional gracias a este curso


consiguió un aumento de sueldo o ascenso

Principales revisiones sobre Machine Learning: Regression

por PDMar 17th 2016

I really enjoyed all the concepts and implementations I did along this course....except during the Lasso module. I found this module harder than the others but very interesting as well. Great course!

por CMJan 27th 2016

I really like the top-down approach of this specialization. The iPython code assignments are very well structured. They are presented in a step-by-step manner while still being challenging and fun!



Emily Fox

Amazon Professor of Machine Learning

Carlos Guestrin

Amazon Professor of Machine Learning
Computer Science and Engineering

Acerca de Universidad 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....

Acerca del programa especializado Aprendizaje Automático

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....
Aprendizaje Automático

Preguntas Frecuentes

  • Una vez que te inscribes para obtener un Certificado, tendrás acceso a todos los videos, cuestionarios y tareas de programación (si corresponde). Las tareas calificadas por compañeros solo pueden enviarse y revisarse una vez que haya comenzado tu sesión. Si eliges explorar el curso sin comprarlo, es posible que no puedas acceder a determinadas tareas.

  • Cuando te inscribes en un curso, obtienes acceso a todos los cursos que forman parte del Programa especializado y te darán un Certificado cuando completes el trabajo. Se añadirá tu Certificado electrónico a la página Logros. Desde allí, puedes imprimir tu Certificado o añadirlo a tu perfil de LinkedIn. Si solo quieres leer y visualizar el contenido del curso, puedes auditar el curso sin costo.

¿Tienes más preguntas? Visita el Centro de Ayuda al Alumno.