Chevron Left
返回到 Machine Learning: Classification

學生對 华盛顿大学 提供的 Machine Learning: Classification 的評價和反饋

3,670 個評分


Case Studies: Analyzing Sentiment & Loan Default Prediction In our case study on analyzing sentiment, you will create models that predict a class (positive/negative sentiment) from input features (text of the reviews, user profile information,...). In our second case study for this course, loan default prediction, you will tackle financial data, and predict when a loan is likely to be risky or safe for the bank. These tasks are an examples 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. In this course, you will create classifiers that provide state-of-the-art performance on a variety of tasks. You will become familiar with the most successful techniques, which are most widely used in practice, including logistic regression, decision trees and boosting. In addition, you will be able to design and implement the underlying algorithms that can learn these models at scale, using stochastic gradient ascent. You will implement these technique on real-world, large-scale machine learning tasks. You will also address significant tasks you will face in real-world applications of ML, including handling missing data and measuring precision and recall to evaluate a classifier. This course is hands-on, action-packed, and full of visualizations and illustrations of how these techniques will behave on real data. We've also included optional content in every module, covering advanced topics for those who want to go even deeper! Learning Objectives: By the end of this course, you will be able to: -Describe the input and output of a classification model. -Tackle both binary and multiclass classification problems. -Implement a logistic regression model for large-scale classification. -Create a non-linear model using decision trees. -Improve the performance of any model using boosting. -Scale your methods with stochastic gradient ascent. -Describe the underlying decision boundaries. -Build a classification model to predict sentiment in a product review dataset. -Analyze financial data to predict loan defaults. -Use techniques for handling missing data. -Evaluate your models using precision-recall metrics. -Implement these techniques in Python (or in the language of your choice, though Python is highly recommended)....




A very deep and comprehensive course for learning some of the core fundamentals of Machine Learning. Can get a bit frustrating at times because of numerous assignments :P but a fun thing overall :)



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!


426 - Machine Learning: Classification 的 450 個評論(共 575 個)

創建者 Subikesh P S


This course was very useful for learning machine learning, as this describes classification models deeply and also about other important ML techniques like Online Learning, handling missing data, precision-recall, etc. The weekly programming assignments were elaborate and explained all the topics nicely. The classes were also made interesting by Mr. Carlos by cracking puns in between.

The only problem I face is that using turicreate over sklearn. Since turicreate is depreciated for windows, it's hard to complete programming assignments.

創建者 Anjan P


Excellent course that details important concepts in supervised classification. The programming assignments can be a little easy to complete (and consequently easy to forget later), but I believe it's a well paced course and the lecture material is at any incredibly accessible pace, with options for more advanced material.

One suggestion would be to include more papers for additional technical details in the lecture or programming assignments as you did with dealing with unbalanced data.

創建者 George P


It explains nicely a lot of useful topics and gives you the tools to build real world applications. It even explains precision recall and boosting which could be confusing in an easy to digest way.

4/5 stars because the course could include multiple levels of difficulty for the programming assignment tasks. The task by default were very guided and a keen student would like to explore and build them from scratch or at least in a less guided way.

Positive experience overall

創建者 Kamil K


Carlos (the teacher) is a fantastic guy, but for me the content of this particular course was too easy comparing to other courses in specialization (when Emily was mainly in charge). If you only look at tutorial videos duration, you will see that they are two times shorter than in remaining courses. And some of them is "very optional". But, that being said, it is still a well taught course.

I wish it'd had more advance content, then I could give full 5-star review.

創建者 Karen B


The course covers many aspects of classification, with each section building on the one before. The lectures cover the theory, with a little bit of practical information, fairly well. The instructor tries to make the lectures interesting, and they are.

The quizzes seem designed both to reinforce what the lectures taught and to expand on them. The quizzes, particularly those based on programming, could use proofreading by someone newer to the subject.

創建者 Sacha v W


The course is well structured and very well explained. The structure is step by step increasing the the complexity. The programming exercises are excellent. I really appreciate the humor and passion of Carlos in teaching the material and his ability to explain complex matters with simple examples. The only drawback is that the course uses python packages that are less familiar. That is why I audited the course and worked with pandas and sklearn.

創建者 Michael C


The course provides an overview on classification methods in machine learning.

The lectures are clear and easy to understand due to the quality of the slides and of the explanations.

The limit of this course lies in the assignments: too easy if done with the provided notebooks and tools. Sometimes impossible to do with different tools (the suggested machine learning package is free for educational purposes, but otherwise it needs a license).

創建者 Shahin S


The lectures are very well prepared and clear. With regards to the assignments: I think it will be nice to design the assignments in a way that allows people to use the language and libraries they prefer as much as possible. I would also prefer to write more of the coding assignments by myself, instead of trying to fill in the blanks in some pre-written code and complete them. That will help the students to learn a lot more.



This course is well paced. Toughness of assignment and quizzes are moderate and are very conceptual. The only thing this course lacks is it only teaches basic stuff and you need to refer other sources if you are interested to study some advance techniques. This course builds a strong foundation of math and statistics in ML field. If you are struggling to understand math behind all algorithms I do recommend this course.

創建者 Naveendhar


Last portion was a little difficult to relate to why we started this move for large datasets in the first place. I had to keep going to the fact that I am going to be handling large datasets. Like the use cases. simple and effective. The quizzes were simple and the graph questions were really helpful in gauging my understanding of math behind these models.

創建者 Stefano T


The contents are very interesting and well explained. Nevertheless, unlike the Regression module, the current one suffers of some technical problem, like slides not well formatted, noisy audio in some video, weekly work load not perfectly calibrated. Despite all this, if you are interested in the subject, you will definitely love this course!!!

創建者 Marku v d s


I loved the course. Carlos Guestrin is an excellent and engaging professor that really captivate me to work hard to accomplish the assignments.

I just suggest that the assignments should be divided into small pieces to be taken as long the week is accomplished. I felt bad some weeks that had a lot of videos to watch before the first assignment.

創建者 Lorenzo L


Good, funny and super-clear professors introduce you to the main classification techniques out there (except for neural networks). Great if you are approaching this field and want to know more before deciding if you really want to invest a lot in it. 4 stars because it would have been better with more popular python packages than GraphLab.

創建者 Craig B


Not as evenly paced as the first two courses. Also some material was covered at a very high level, whilst I found that some explanations did not immediately build on my understanding gained through the foundation course, but rather confused it. Still a worthwhile course nonetheless. I look forward to the rest in the specialisation.

創建者 Nitin K M


The course is perfect for people who want to gain in-depth knowledge of classification algorithms but exercise descriptions are vague. I found trouble understanding the flow of assignments. Also, Bagging and Gradient Boosting techniques were not covered under ensembles. Overall, the course is awesome.



The course 3 got pretty technical pretty soon. Enjoyed the first 2 courses without feeling overwhelmed. But course 3 was challenging. I suppose building the expectation of what is to come can reduce the challenge and lead to faster and more number of course completions.

創建者 Aleksander G


Just one comment about how the course could be improved: the assignments should be more hands-on with fewer pieces of code written in advance. I say this is even though I am not a skilled programmer. The assignments would be a bit harder, but also a bit more rewarding.

創建者 Jaime A C B


Sometimes is difficult to understand the concept behind Classification because some videos are more practical than theorical, I mean it could be better to start the video explaining some concepts and then show and explan some samples and theorical issues.


創建者 Nicolas S


The course itself is well structured and introduce gradually the complexity. Unfortunately, the exercises requires the use of a specific library, instead of scikit-learn and numpy. Furthermore, they also required Python 2, while Python 3 is now widely used.

創建者 Martin B


As with all the courses in this specialization: great production values, excellent tuition. Useful assignments, even though the reliance of Graphlab Create is a bit of a drag. I also would have liked to see some discussion of Support Vector Machines.

創建者 J N B P


This course covers all the core algorithms used in Classification models. If you have a basic understanding of machine learning, this course can help you build your understanding of classification on a deeper level.

創建者 Uichong D L


Using discontinued Graphlab in the programming assignment is a minus and low activities in the forum makes hard to find assistance from the communities or mentors but the course material itself is just great.

創建者 João S


Very good content, very well explained... great course. Classification its a very broad topic but i think this is great introduction.

The hands on where kinda on the easy side... but very interesting.

創建者 David F


Not as good as the previous courses in this specialization - I agree with those who have noted that this one seemed a little rushed. However, these are still the best courses I've found on Coursera.

創建者 Ahmed N


Great knowledge about machine learning fundamentals, More math illustration needed though it's great knowledge and very great basics about different machine learning algorithm used in reality