Chevron Left
Вернуться к Machine Learning: Regression

Отзывы учащихся о курсе Machine Learning: Regression от партнера Вашингтонский университет

4.8
звезд
Оценки: 4,536
Рецензии: 847

О курсе

Case Study - Predicting Housing Prices In our first case study, predicting house prices, you will create models that predict a continuous value (price) from input features (square footage, number of bedrooms and bathrooms,...). 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. In this course, you will explore regularized linear regression models for the task of prediction and feature selection. You will be able to handle very large sets of features and select between models of various complexity. You will also analyze the impact of aspects of your data -- such as outliers -- on your selected models and predictions. To fit these models, you will implement optimization algorithms that scale to large datasets. Learning Outcomes: By the end of this course, you will be able to: -Describe the input and output of a regression model. -Compare and contrast bias and variance when modeling data. -Estimate model parameters using optimization algorithms. -Tune parameters with cross validation. -Analyze the performance of the model. -Describe the notion of sparsity and how LASSO leads to sparse solutions. -Deploy methods to select between models. -Exploit the model to form predictions. -Build a regression model to predict prices using a housing dataset. -Implement these techniques in Python....

Лучшие рецензии

PD

Mar 17, 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!

CM

Jan 27, 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!

Фильтр по:

51–75 из 816 отзывов о курсе Machine Learning: Regression

автор: Samuel d Z

Jun 27, 2017

Awesome. You need a little bit of experience but things are explained really well. So glad I took this course, I tried another one from another university, it was disastrous. It certainly helps when you know how to do programming as this takes a lot of time and can be frustrating if you are new at it. Still worth learning it this way. Would recommend to use the GraphLab and maybe later redo it with standard Python tools.

автор: Tanmay G

Feb 21, 2016

Fantastic course in regression, taught with the mathematical rigor necessary to really understand (not just use) the concepts. The instructors both do an amazing job introducing the concepts piece by piece in a logical and easy to follow manner. In addition, several modules have *optional* in depth derivations of key formulae for those who want to understand the mathematical underpinnings of the regression methods

автор: Nsair A

Mar 03, 2017

this course offers so much that by the time you are going through the lecture videos and the reading material, you do all the tasks along and you don't want the lecture to end. In fact by the time a lecture is finished, you want to do more and you click on the next one. the course gives a very good understanding of machine learning models and the skills gained can be used in a lot of different situations.

автор: Pawan K S

Feb 13, 2016

This course is very detailed and have lot of information about regression, should be taken by anyone who wants to become master in it. But each lesson should be given a week, otherwise it becomes over whelming. Assignments are good as well, though some of them should have better instruction.

There should have been a programming assignment on kernal regression as well, as it is one of the upcoming technique.

автор: Stephane F

Dec 31, 2015

Professor Fox is explaining the main algorithms (gradient / coordinate descent) in a clear and understandable way. Quite often, in blogs and reviews, Andrew Ng's course (at Stanford) is mentioned as the reference, to me it looks like these series of courses can match Ng's course on machine learning (using Octave). Being based on Python I would give the advantage to this course and recommend it.

автор: Olexandra Z

Feb 05, 2017

Really great explanations for complex and important principles as well as math approaches and tools. Being a mathematician, I thought that in this math aspect there would be nothing new for me, but still it was a great refreshment and very useful explanations to understand how those methods actually work for machine learning tasks. Great balance of theory and practical applications! Thank you!

автор: Gabor S

Jan 17, 2017

This a well thought out course. From the simple concepts it gradually takes you to the more complex ones. The quizzes and programming assignments help you to really understand the problems that were introduced in the videos. The video slides of every module can be downloaded as a pdf document which makes the material easily searchable. And last but not least Emily Fox is a great instructor.

автор: Leon W

Jun 16, 2016

I learned quite a lot during this which I can use in practice. Everything is well explained in the video's. If I had to call a down side then I would say that I had a hard time with the math. This is because I never did something matrices and linear algebra. For those people who miss this background info I would like to say: if you're dedicated then you should be able to survive this course!

автор: Stefan K

Dec 29, 2015

Very good course with detailed explanations, both great lecturers, lets you choose environment of your liking for the assignments(python and graphlab are preferred). The explanations are detailed and clear and assignments are very practical. One of the best courses and Specializations on the Coursera I have taken so far. If you contribute lot of time and effort, you will learn a lot.

автор: Asim I

Dec 19, 2015

Awesome. Pure awesome. Great presentation on the theory and all the assignments force you to code solutions from scratch, you're not dependent on Graphlab. Very detailed presentation of advanced topics not covered in other superficial introductions to regression. And practical advice from the instructors shows that they are imparting practical real-world advice on running regression.

автор: David H

May 31, 2016

Congrats to Carlos and Emily on producing a great course. As a humble software developer with no statistics background (and someone who hasn't used calculus since they left school nearly 30 years ago) I found this course to be very accessible, the concepts clearly explained, and the results of the course work have been rewarding. Thanks for kick-starting my little grey cells again.

автор: Jens K

May 28, 2018

Great course that guides you to coding regression (linear, polynomial and ridge regression with gradient descend, lasso with coordinate descend, and linear-average kNN), as well as demonstrating key statistical concepts in the slides and while doing the exercises. This code deepens understanding of key regression algorithms through a hands-on, learning-by-coding approach.

автор: Carlos F A

Jun 09, 2016

I already knew how to do linear regression before taking this course; however, I had always struggled to understand how ridge and lasso regression worked and what their usefulness was; thanks to this course I was finally able to understand those concepts very well. The visual explanation of how the ridge and lasso regression work made this course well worth its time.

автор: Marcio R

Feb 23, 2016

This module is very rich in pratical assignments, as well as quizzes to force you to understand what you are doing. Everything is really well balanced, and all the materials are very complete. Is clear the passion from the tutors and teachers in this course. This really gives you the necessary will to proceed, and don't give up, even when things get pretty hard.

автор: Fahad S

Jan 31, 2018

I thoroughly enjoyed the course and learned important machine learning concepts through it. The case study approach truly helps in building intuition for the concepts and methods we learn. Emily Ross explains complex ideas in an easy to understand intuitive manners and the visualizations are great. Looking forward to complete the rest of the specialization.

автор: Matthew B

Jun 05, 2016

This is a great class! Highly recommended. Emily and Carlos are a great team. The videos are polished, the progression through the material is well organized and everything just fits together very well in this specialization. The assignments are challenging enough to be worth the effort. Great specialization... I look forward to completing every class.

автор: Christopher M

Jan 26, 2019

Great course. You get to write the algorithms for OLS regressions, ridge regression, lasso regression, and for k-nearest neighbor models. The instruction even includes some optional graduate-level videos on with more detailed explanations of how more advanced algorithms for solving the regressions may be developed (eg, subgradients for lasso regression).

автор: Sander v d O

Mar 16, 2016

Superb course, very well explained! The best I've taken so far!

You do need to know some Linear Algebra and Python as a prerequisite, but as a result, after hard work, I have now finally developed some true understanding of a wide range of regression algorithms.

Minor downside: i find the activity in the forum quite low, so not to useful in this course.

автор: Mohamed A H

Nov 27, 2018

This course is extremely awesome!

The instructors are really professional and straight to the point. The topics are explained clearly and the assignments are crucially useful because you get to implement the concepts and algorithms in hand. Actually, you can't find a thing that's not nice about this course, at least I couldn't ;)

Very recommended!

автор: Theodore G

Oct 23, 2016

A really interesting, course in the important topic of (linear) regression. The case study approach followed by the instructors makes it ideal to learn how these ideas used in real-life problems. The programming language used is Python (GraphLab Create or Open Sourced libraries), which is most probably the best choice for newcomers in the field.

автор: Charlie Q

Aug 11, 2018

Very clear and detailed presentation of concepts and techniques of the traditional regression approach that are most relevant in today's machine learning world. The assignments are well designed and may take some efforts to complete, but they are worth the time as they certainly reinforce the understanding of materials covered in the lectures.

автор: Joseph K

Dec 05, 2015

I've studied machine learning quite a bit in school as well as on my own, but I wish this class was how I learned the first time around. Everything is explained so clearly and well-balanced between practical understanding vs underlying theory. Definitely serves as a good review for those of us who are looking to get back into machine learning!

автор: Phil O

Dec 10, 2018

4.9 Stars really but had to round. Really enjoyable course and extremely well presented. As a working statistician/analyst this stuff hits on a lot of the import underlying logic that needs to be in your head when looking at real world projects. The 0.1 star drop is because some of the language in the questions can be confusing, an easy fix.

автор: Ridhwanul H

Oct 16, 2017

Was also a great course, but personally found myself a bit confused at the last two module - lasso regression and kernel regression. Somehow managed to pass the course but I dont yet feel clear on it so I do plan on doing further studies in it, but it would be great if in future they bring in more materials for these in a much simpler way.

автор: Francisco J

Jan 20, 2019

A great curse focused on understanding the mathematics of the algorithms, clearly explained and detailed. Contains "advanced" optional topics for further learning and forces you to program you own algorithms.

Do not forget to save up the results and functions programmed in previous sections, as they might be required later in the course.