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?
Этот курс входит в специализацию ''Специализация Машинное обучение'
Machine Learning Foundations: A Case Study Approach
от партнера
Об этом курсе
Недавно просмотрено: 244,444
Карьерные результаты учащихся
32%
начал новую карьеру, пройдя эти курсы
30%
получил значимые преимущества в карьере благодаря этому курсу
Приобретаемые навыки
Python ProgrammingMachine Learning ConceptsMachine LearningDeep Learning
Карьерные результаты учащихся
32%
начал новую карьеру, пройдя эти курсы
30%
получил значимые преимущества в карьере благодаря этому курсу
100% онлайн
Начните сейчас и учитесь по собственному графику.
Курс 1 из 4 в программе
Гибкие сроки
Назначьте сроки сдачи в соответствии со своим графиком.
Прибл. 24 часа на выполнение
Предполагаемая нагрузка: 6 weeks of study, 5-8 hours/week
Английский
Субтитры: Английский, Корейский, Вьетнамский, Китайский (упрощенное письмо)
от партнера
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.
Программа курса: что вы изучите
3 ч. на завершение
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.
3 ч. на завершение
18 видео ((всего 84 мин.)), 8 материалов для самостоятельного изучения, 1 тест
18 видео
Who we are5мин
Machine learning is changing the world3мин
Why a case study approach?7мин
Specialization overview6мин
How we got into ML3мин
Who is this specialization for?4мин
What you'll be able to do57
The capstone and an example intelligent application6мин
The future of intelligent applications2мин
Starting a Jupyter Notebook5мин
Creating variables in Python7мин
Conditional statements and loops in Python8мин
Creating functions and lambdas in Python3мин
Starting Turi Create & loading an SFrame4мин
Canvas for data visualization4мин
Interacting with columns of an SFrame4мин
Using .apply() for data transformation5мин
8 материала для самостоятельного изучения
Important Update regarding the Machine Learning Specialization10мин
Slides presented in this module10мин
Getting started with Python, Jupyter Notebook, & Turi Create10мин
Where should my files go?10мин
Important changes from previous courses10мин
Download the Jupyter Notebook used in this lesson to follow along10мин
Download the Jupyter Notebook used in this lesson to follow along10мин
Download Wiki People Data10мин
1 практическое упражнение
SFrames15мин
2 ч. на завершение
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 a Jupyter notebook.
2 ч. на завершение
19 видео ((всего 82 мин.)), 3 материалов для самостоятельного изучения, 2 тестов
19 видео
What is the goal and how might you naively address it?3мин
Linear Regression: A Model-Based Approach5мин
Adding higher order effects4мин
Evaluating overfitting via training/test split6мин
Training/test curves4мин
Adding other features2мин
Other regression examples3мин
Regression ML block diagram5мин
Loading & exploring house sale data7мин
Splitting the data into training and test sets2мин
Learning a simple regression model to predict house prices from house size3мин
Evaluating error (RMSE) of the simple model2мин
Visualizing predictions of simple model with Matplotlib4мин
Inspecting the model coefficients learned1мин
Exploring other features of the data6мин
Learning a model to predict house prices from more features3мин
Applying learned models to predict price of an average house5мин
Applying learned models to predict price of two fancy houses7мин
3 материала для самостоятельного изучения
Slides presented in this module10мин
Download the Jupyter Notebook used in this lesson to follow along10мин
Predicting house prices assignment10мин
2 практического упражнения
Regression18мин
Predicting house prices6мин
2 ч. на завершение
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 a Jupyter notebook, and take a first stab at a core piece of the intelligent application you will build and deploy in your capstone.
2 ч. на завершение
19 видео ((всего 75 мин.)), 3 материалов для самостоятельного изучения, 2 тестов
19 видео
What is an intelligent restaurant review system?4мин
Examples of classification tasks4мин
Linear classifiers5мин
Decision boundaries3мин
Training and evaluating a classifier4мин
What's a good accuracy?3мин
False positives, false negatives, and confusion matrices6мин
Learning curves5мин
Class probabilities1мин
Classification ML block diagram3мин
Loading & exploring product review data2мин
Creating the word count vector2мин
Exploring the most popular product4мин
Defining which reviews have positive or negative sentiment4мин
Training a sentiment classifier3мин
Evaluating a classifier & the ROC curve4мин
Applying model to find most positive & negative reviews for a product4мин
Exploring the most positive & negative aspects of a product4мин
3 материала для самостоятельного изучения
Slides presented in this module10мин
Download the Jupyter Notebook used in this lesson to follow along10мин
Analyzing product sentiment assignment10мин
2 практического упражнения
Classification14мин
Analyzing product sentiment22мин
2 ч. на завершение
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 Jupyter notebook.
2 ч. на завершение
17 видео ((всего 76 мин.)), 3 материалов для самостоятельного изучения, 2 тестов
17 видео
What is the document retrieval task?1мин
Word count representation for measuring similarity6мин
Prioritizing important words with tf-idf3мин
Calculating tf-idf vectors5мин
Retrieving similar documents using nearest neighbor search2мин
Clustering documents task overview2мин
Clustering documents: An unsupervised learning task4мин
k-means: A clustering algorithm3мин
Other examples of clustering6мин
Clustering and similarity ML block diagram7мин
Loading & exploring Wikipedia data5мин
Exploring word counts5мин
Computing & exploring TF-IDFs7мин
Computing distances between Wikipedia articles5мин
Building & exploring a nearest neighbors model for Wikipedia articles3мин
Examples of document retrieval in action4мин
3 материала для самостоятельного изучения
Slides presented in this module10мин
Download the Jupyter Notebook used in this lesson to follow along10мин
Retrieving Wikipedia articles assignment10мин
2 практического упражнения
Clustering and Similarity12мин
Retrieving Wikipedia articles18мин
Рецензии
Лучшие отзывы о курсе MACHINE LEARNING FOUNDATIONS: A CASE STUDY APPROACH
от партнера PMAug 18, 2019
The course was well designed and delivered by all the trainers with the help of case study and great examples.\n\nThe forums and discussions were really useful and helpful while doing the assignments.
от партнера BLOct 16, 2016
Very good overview of ML. The GraphLab api wasn't that bad, and also it was very wise of the instructors to allow the use of other ML packages. Overall i enjoyed it very much and also leaned very much
от партнера SZDec 19, 2016
Great course!\n\nEmily and Carlos teach this class in a very interest way. They try to let student understand machine learning by some case study. That worked well on me. I like this course very much.
от партнера MKJul 20, 2019
A great course, really designed to understand the underlying core concepts of machine learning using real-life examples which takes you through all that with little to no programming skills required!
от партнера CLOct 7, 2019
This was good introductory course with challenging programming assignments that expanded and grounded the lecture materials. The forums also proved great support when needed, overall very satisfied.
от партнера DSSep 27, 2015
Excellent course, with really good lectures, material and assignment. Plus the professors are really amazing and their enthusiasm is really refreshing and makes the class more interesting. Loved it!
от партнера DPFeb 14, 2016
With a funny and welcoming look and feel, this course introduces machine learning through a hands-on approach, that enables the student to properly understand what ML is all about. Very nicely done!
от партнера DMApr 1, 2017
The Course was very neatly presented, although we used lots of predefined functions to work around Machine Learning Algorithms it was good to know about the concepts that was thought extremely well.
от партнера HVMay 21, 2016
Good for a introductory course if someone is getting started with machine learning, but as part of an specialization i think is useless (for people who are planning to take all the specialization).
от партнера GGJun 4, 2017
This course is very helpful for people who are novice in machine learning. The course uses Graphlab Create which is different from scikit or R-libraries, but the tool(Graphlab) is excellent to use.
от партнера GSNov 7, 2016
One of the best courses available online. Actually got to know how to apply theoretical knowledge in designing systems. You people are the best and made concepts and things really easy. Hats off!!
от партнера RHJun 8, 2017
I felt this course did a good job introducing the student to Machine Learning. The examples and hands on assignments brought the concepts home. I was able to use the knowledge immediately at work.
от партнера BGMar 27, 2020
This course foundation for those who want to do specialization in Machine Learning. It's really very useful course, I recommend do this course If you want to do specialization in Machine Learning.
от партнера AANov 13, 2016
Really liked the course and the teachers. Would have preferred more detail on the quizzes so I didn't feel as lost as I did some of the times while trying to piece together what a question meant.
от партнера SAOct 6, 2017
really like the instructor and the course. it was very hands on specially for me who is coming from Bigdata (python and hadoop) background . thanks for this cool and amazing learning opportunity
от партнера NBMay 31, 2017
Course contents are good - however the forums are not active and there is no follow up from faculty to update the course specialization following the change in course structure (eg. no capstone)
от партнера KMDec 26, 2018
A good course to understand the basics of Machine Learning. The only issue is the use of Graphlab library. Since it only works on Python 2.7, it is not convenient for people who prefer Python 3
от партнера AHJun 19, 2018
The course Content is very good and also the instructors .graphLab tool is also good toolI wish there was a hint for scikitlearn but it is a good course for beginners and i Recommend it for all
от партнера MMNov 16, 2017
Good course, a tiles a litte coursory, but a decent introduction to the concepts and vocabulary of machine learning. Something like this should be required for anyone who works with data today.
от партнера JKOct 28, 2015
Great survey course for main topics in machine learning without going too much into detail. The professors do a great job of keeping the topics relevant to modern-day uses of machine learning.
Специализация Машинное обучение: общие сведения
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.
Часто задаваемые вопросы
Когда я получу доступ к лекциям и заданиям?
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.
Что я получу, оформив подписку на специализацию?
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.
Какие правила возврата средств?
Можно ли получить финансовую помощь?
Остались вопросы? Посетите Центр поддержки учащихся.
