Об этом курсе
Недавно просмотрено: 66,870

100% онлайн

Начните сейчас и учитесь по собственному графику.

Гибкие сроки

Назначьте сроки сдачи в соответствии со своим графиком.

Прибл. 42 часа на выполнение

Предполагаемая нагрузка: 7 weeks of study, 5-8 hours/week...


Субтитры: Английский, Корейский, Арабский

Приобретаемые навыки

Logistic RegressionStatistical ClassificationClassification AlgorithmsDecision Tree

100% онлайн

Начните сейчас и учитесь по собственному графику.

Гибкие сроки

Назначьте сроки сдачи в соответствии со своим графиком.

Прибл. 42 часа на выполнение

Предполагаемая нагрузка: 7 weeks of study, 5-8 hours/week...


Субтитры: Английский, Корейский, Арабский

Программа курса: что вы изучите

1 ч. на завершение


Classification is one of the most widely used techniques in machine learning, with a broad array of applications, including sentiment analysis, ad targeting, spam detection, risk assessment, medical diagnosis and image classification. The core goal of classification is to predict a category or class y from some inputs x. Through this course, you will become familiar with the fundamental models and algorithms used in classification, as well as a number of core machine learning concepts. Rather than covering all aspects of classification, you will focus on a few core techniques, which are widely used in the real-world to get state-of-the-art performance. By following our hands-on approach, you will implement your own algorithms on multiple real-world tasks, and deeply grasp the core techniques needed to be successful with these approaches in practice. 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.

8 видео ((всего 27 мин.)), 3 материалов для самостоятельного изучения
8 видео
What is this course about?6мин
Impact of classification1мин
Course overview3мин
Outline of first half of course5мин
Outline of second half of course5мин
Assumed background3мин
Let's get started!45
3 материала для самостоятельного изучения
Important Update regarding the Machine Learning Specialization10мин
Slides presented in this module10мин
Reading: Software tools you'll need10мин
2 ч. на завершение

Linear Classifiers & Logistic Regression

Linear classifiers are amongst the most practical classification methods. For example, in our sentiment analysis case-study, a linear classifier associates a coefficient with the counts of each word in the sentence. In this module, you will become proficient in this type of representation. You will focus on a particularly useful type of linear classifier called logistic regression, which, in addition to allowing you to predict a class, provides a probability associated with the prediction. These probabilities are extremely useful, since they provide a degree of confidence in the predictions. In this module, you will also be able to construct features from categorical inputs, and to tackle classification problems with more than two class (multiclass problems). You will examine the results of these techniques on a real-world product sentiment analysis task.

18 видео ((всего 78 мин.)), 2 материалов для самостоятельного изучения, 2 тестов
18 видео
Intuition behind linear classifiers3мин
Decision boundaries3мин
Linear classifier model5мин
Effect of coefficient values on decision boundary2мин
Using features of the inputs2мин
Predicting class probabilities1мин
Review of basics of probabilities6мин
Review of basics of conditional probabilities8мин
Using probabilities in classification2мин
Predicting class probabilities with (generalized) linear models5мин
The sigmoid (or logistic) link function4мин
Logistic regression model5мин
Effect of coefficient values on predicted probabilities7мин
Overview of learning logistic regression models2мин
Encoding categorical inputs4мин
Multiclass classification with 1 versus all7мин
Recap of logistic regression classifier1мин
2 материала для самостоятельного изучения
Slides presented in this module10мин
Predicting sentiment from product reviews10мин
2 практического упражнения
Linear Classifiers & Logistic Regression10мин
Predicting sentiment from product reviews24мин
2 ч. на завершение

Learning Linear Classifiers

Once familiar with linear classifiers and logistic regression, you can now dive in and write your first learning algorithm for classification. In particular, you will use gradient ascent to learn the coefficients of your classifier from data. You first will need to define the quality metric for these tasks using an approach called maximum likelihood estimation (MLE). You will also become familiar with a simple technique for selecting the step size for gradient ascent. An optional, advanced part of this module will cover the derivation of the gradient for logistic regression. You will implement your own learning algorithm for logistic regression from scratch, and use it to learn a sentiment analysis classifier.

18 видео ((всего 83 мин.)), 2 материалов для самостоятельного изучения, 2 тестов
18 видео
Intuition behind maximum likelihood estimation4мин
Data likelihood8мин
Finding best linear classifier with gradient ascent3мин
Review of gradient ascent6мин
Learning algorithm for logistic regression3мин
Example of computing derivative for logistic regression5мин
Interpreting derivative for logistic regression5мин
Summary of gradient ascent for logistic regression2мин
Choosing step size5мин
Careful with step sizes that are too large4мин
Rule of thumb for choosing step size3мин
(VERY OPTIONAL) Deriving gradient of logistic regression: Log trick4мин
(VERY OPTIONAL) Expressing the log-likelihood3мин
(VERY OPTIONAL) Deriving probability y=-1 given x2мин
(VERY OPTIONAL) Rewriting the log likelihood into a simpler form8мин
(VERY OPTIONAL) Deriving gradient of log likelihood8мин
Recap of learning logistic regression classifiers1мин
2 материала для самостоятельного изучения
Slides presented in this module10мин
Implementing logistic regression from scratch10мин
2 практического упражнения
Learning Linear Classifiers12мин
Implementing logistic regression from scratch16мин
2 ч. на завершение

Overfitting & Regularization in Logistic Regression

As we saw in the regression course, overfitting is perhaps the most significant challenge you will face as you apply machine learning approaches in practice. This challenge can be particularly significant for logistic regression, as you will discover in this module, since we not only risk getting an overly complex decision boundary, but your classifier can also become overly confident about the probabilities it predicts. In this module, you will investigate overfitting in classification in significant detail, and obtain broad practical insights from some interesting visualizations of the classifiers' outputs. You will then add a regularization term to your optimization to mitigate overfitting. You will investigate both L2 regularization to penalize large coefficient values, and L1 regularization to obtain additional sparsity in the coefficients. Finally, you will modify your gradient ascent algorithm to learn regularized logistic regression classifiers. You will implement your own regularized logistic regression classifier from scratch, and investigate the impact of the L2 penalty on real-world sentiment analysis data.

13 видео ((всего 66 мин.)), 2 материалов для самостоятельного изучения, 2 тестов
13 видео
Review of overfitting in regression3мин
Overfitting in classification5мин
Visualizing overfitting with high-degree polynomial features3мин
Overfitting in classifiers leads to overconfident predictions5мин
Visualizing overconfident predictions4мин
(OPTIONAL) Another perspecting on overfitting in logistic regression8мин
Penalizing large coefficients to mitigate overfitting5мин
L2 regularized logistic regression4мин
Visualizing effect of L2 regularization in logistic regression5мин
Learning L2 regularized logistic regression with gradient ascent7мин
Sparse logistic regression with L1 regularization7мин
Recap of overfitting & regularization in logistic regression58
2 материала для самостоятельного изучения
Slides presented in this module10мин
Logistic Regression with L2 regularization10мин
2 практического упражнения
Overfitting & Regularization in Logistic Regression16мин
Logistic Regression with L2 regularization16мин
2 ч. на завершение

Decision Trees

Along with linear classifiers, decision trees are amongst the most widely used classification techniques in the real world. This method is extremely intuitive, simple to implement and provides interpretable predictions. In this module, you will become familiar with the core decision trees representation. You will then design a simple, recursive greedy algorithm to learn decision trees from data. Finally, you will extend this approach to deal with continuous inputs, a fundamental requirement for practical problems. In this module, you will investigate a brand new case-study in the financial sector: predicting the risk associated with a bank loan. You will implement your own decision tree learning algorithm on real loan data.

13 видео ((всего 47 мин.)), 3 материалов для самостоятельного изучения, 3 тестов
13 видео
Intuition behind decision trees1мин
Task of learning decision trees from data3мин
Recursive greedy algorithm4мин
Learning a decision stump3мин
Selecting best feature to split on6мин
When to stop recursing4мин
Making predictions with decision trees1мин
Multiclass classification with decision trees2мин
Threshold splits for continuous inputs6мин
(OPTIONAL) Picking the best threshold to split on3мин
Visualizing decision boundaries5мин
Recap of decision trees56
3 материала для самостоятельного изучения
Slides presented in this module10мин
Identifying safe loans with decision trees10мин
Implementing binary decision trees10мин
3 практического упражнения
Decision Trees22мин
Identifying safe loans with decision trees14мин
Implementing binary decision trees14мин
2 ч. на завершение

Preventing Overfitting in Decision Trees

Out of all machine learning techniques, decision trees are amongst the most prone to overfitting. No practical implementation is possible without including approaches that mitigate this challenge. In this module, through various visualizations and investigations, you will investigate why decision trees suffer from significant overfitting problems. Using the principle of Occam's razor, you will mitigate overfitting by learning simpler trees. At first, you will design algorithms that stop the learning process before the decision trees become overly complex. In an optional segment, you will design a very practical approach that learns an overly-complex tree, and then simplifies it with pruning. Your implementation will investigate the effect of these techniques on mitigating overfitting on our real-world loan data set.

8 видео ((всего 40 мин.)), 2 материалов для самостоятельного изучения, 2 тестов
8 видео
Overfitting in decision trees5мин
Principle of Occam's razor: Learning simpler decision trees5мин
Early stopping in learning decision trees6мин
(OPTIONAL) Motivating pruning8мин
(OPTIONAL) Pruning decision trees to avoid overfitting6мин
(OPTIONAL) Tree pruning algorithm3мин
Recap of overfitting and regularization in decision trees1мин
2 материала для самостоятельного изучения
Slides presented in this module10мин
Decision Trees in Practice10мин
2 практического упражнения
Preventing Overfitting in Decision Trees22мин
Decision Trees in Practice28мин
1 ч. на завершение

Handling Missing Data

Real-world machine learning problems are fraught with missing data. That is, very often, some of the inputs are not observed for all data points. This challenge is very significant, happens in most cases, and needs to be addressed carefully to obtain great performance. And, this issue is rarely discussed in machine learning courses. In this module, you will tackle the missing data challenge head on. You will start with the two most basic techniques to convert a dataset with missing data into a clean dataset, namely skipping missing values and inputing missing values. In an advanced section, you will also design a modification of the decision tree learning algorithm that builds decisions about missing data right into the model. You will also explore these techniques in your real-data implementation.

6 видео ((всего 25 мин.)), 1 материал для самостоятельного изучения, 1 тест
6 видео
Strategy 1: Purification by skipping missing data4мин
Strategy 2: Purification by imputing missing data4мин
Modifying decision trees to handle missing data4мин
Feature split selection with missing data5мин
Recap of handling missing data1мин
1 материал для самостоятельного изучения
Slides presented in this module10мин
1 практическое упражнение
Handling Missing Data14мин
Рецензии: 463Chevron Right


начал новую карьеру, пройдя эти курсы


получил значимые преимущества в карьере благодаря этому курсу


стал больше зарабатывать или получил повышение

Лучшие отзывы о курсе Machine Learning: Classification

автор: SSOct 16th 2016

Hats off to the team who put the course together! Prof Guestrin is a great teacher. The course gave me in-depth knowledge regarding classification and the math and intuition behind it. It was fun!

автор: CJJan 25th 2017

Very impressive course, I would recommend taking course 1 and 2 in this specialization first since they skip over some things in this course that they have explained thoroughly in those courses



Carlos Guestrin

Amazon Professor of Machine Learning
Computer Science and Engineering

Emily Fox

Amazon Professor of Machine Learning

О Вашингтонский университет

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....

О специализации ''Машинное обучение'

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....
Машинное обучение

Часто задаваемые вопросы

  • Зарегистрировавшись на сертификацию, вы получите доступ ко всем видео, тестам и заданиям по программированию (если они предусмотрены). Задания по взаимной оценке сокурсниками можно сдавать и проверять только после начала сессии. Если вы проходите курс без оплаты, некоторые задания могут быть недоступны.

  • Записавшись на курс, вы получите доступ ко всем курсам в специализации, а также возможность получить сертификат о его прохождении. После успешного прохождения курса на странице ваших достижений появится электронный сертификат. Оттуда его можно распечатать или прикрепить к профилю LinkedIn. Просто ознакомиться с содержанием курса можно бесплатно.

Остались вопросы? Посетите Центр поддержки учащихся.