Chevron Left
Retour à Machine Learning Foundations: A Case Study Approach

Avis et commentaires pour d'étudiants pour Machine Learning Foundations: A Case Study Approach par Université de Washington

13,084 évaluations

À propos du cours

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? In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images. Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains. This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications. Learning Outcomes: By the end of this course, you will be able to: -Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering. -Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning. -Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task. -Utilize a dataset to fit a model to analyze new data. -Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python....

Meilleurs avis


18 août 2019

The course was well designed and delivered by all the trainers with the help of case study and great examples.

The forums and discussions were really useful and helpful while doing the assignments.


16 oct. 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

Filtrer par :

176 - 200 sur 3,043 Avis pour Machine Learning Foundations: A Case Study Approach

par Dave G

17 déc. 2021

Overall this course was fantastic! The material was taught in an intuitive way with pictures and diagrams that were explained step by step.

My only complaint is that the earlier videos in the course were recorded using graphlab and so there is a little bit of translation to turicreate that needs to be done by the student. It seems that the teachers made a point to update the downloadable notebook files though, so this was not a big issue for me.

par Louis U

15 nov. 2017

Absolutely awesome! I am really appreciative of the time and efforts on the part of the instructors and the University of Washington to make Machine Learning very accessible. The concepts were very easy to grasp and I endorse the case study approach as a effective introduction to complex topics. Obviously, it will get more detailed and complex in upcoming courses in the specializations but I feel very prepared and excited to learn. Thank you.

par Syed M Z H K

5 août 2017

Thanks alot for this awesome course. As because of it, I was able to learn python (otherwise I used to hate it, when I started learning it with OpenCV) and ipyhon (which is an awesome tool). Furthermore, thanks alot course era for providing me with this amazing fee waiver (since I can't afford this course) , as because of this I am hoping to excel in this field after completing this specialization, in order to later land good job. Thank you!

par Prachur B

27 déc. 2016

A very practical approach for learning and get excited about Machine Learning. The python notebook exercises really help if you do them diligently (though sometimes it was too easy because of hints, may be hide them and who when someone asks for it). The mention of so many concepts and algorithms can be overwhelming, so a clear guideline on how to leverage the material specifically in this foundation course in the closing remarks would help.

par Aman M

18 déc. 2018

I was totally new to the machine learning, but this course helped me to understand what is it? What is the importance of it ? where it can be used and what will be the future of it ? There was also enough exercise work to check our understanding to the topic learnt. I think it will be more interesting if they provide a console for code snippet for the assignment... It was very nice experience with Carlos Guestrin Sir and Emily Fox Ma'am

par Tobi L

6 déc. 2015

I appreciate that the first course focused on applications, I've got plenty of math and programming experience, but I took this specialization to really grok machine learning and its applications. By using graphlab as a black box and focusing on specific applications, I really understood why these techniques are useful. Once I've got the why, I feel much more motivated to dig deeper into the how, which I feel confident enough that I can do.

par Aleksander S

1 févr. 2019

This is a great course. The content is delivered at a very good pace even for people with little prior knowledge of statistics or computer science — not too fast (would be too difficult) and not too slow (could become boring). Additionally, the assignment model is perfect — it requires completing hands-on exercises, but then the solution is assessed using simple quizzes. Thanks to that the answers and the grades are immediately available.

par George C

26 déc. 2015

The case study approach and the reliance on GraphLab library makes it easier to get your head around the concepts before going into the detail later in the specialization. I learn better when I have a working understanding of the high-level concepts and the use for a new area of study. This course provides that high-level understanding and the later specializations provides the deep dive. Also, the course seemed well paced and structured.

par Chengcheng L

27 déc. 2015

This is a wonderful course to get you into the door of machine learning. It covers several key concepts in ML. The videos are easy to follow. The assignments are not difficult to complete if you do the "follow along" exercises. You won't be able to understand the theoretical background of the algorithm very well after taking this course, but you can apply Grahphlab functions to whatever data you have and generate quick and dirty results.

par Evan S

11 mars 2019

This course was a great balance between lecture (and lecture quiz) & iPython lecture (and iPython lecture quiz). I like that the answers are multiple choice as opposed to copying and pasting code. That way, any coding errors can be played around with in the notebook first without using up any submission attempts. Emily and Carlos did a great job of keeping the course fun while sticking to the easy-to-understand case-study approach.

par Divyansh S

25 déc. 2018

I found this course advantageous for me. I found the case study approach of teaching the various concepts of Machine Learning quite helpful. Case Study approach gives us the idea of practical implementaton of these concepts in real life. The quality of the teaching content was very good. Moreover the assignments helped a lot in understanding some of the key concepts. Ideal course for newbies to start learning Machine Learning.

par Matthew S

7 janv. 2020

A well rounded and not intimidating approach to machine learning. The concepts are introduced clearly and succinctly. The exercises are relevant and digestible. I feel like I have a much better understanding of the concepts to build upon. The only thing I would have liked to see is more outside reading on things that were introduced, but that's also in the next courses of the specialization or just a google away.

par Dhananjay M

7 févr. 2016

It is an amazing course being taught by professor Emily and professor Carlos. What sets this course apart from any other MOOCs or classes is the case study approach to explain the algorithms. Learning is most productive when a person can visualize what he is taught. This is exactly what this course does by helping students see what they can do with the algorithms they learning with this case-study based approach.

par Allen C L

17 juin 2016

A very nice introductory course that uses real-world use case examples to illustrate foundational concepts in machine learning. If, like me, you have only an inkling about what is machine learning, this is a good course to give you a broad overview. Along the way, you'll pick up some very useful Python skills for use in data analysis. You'll also learn to use the nice Python tool, the iPython (Jupyter) Notebook.

par Christopher M

6 déc. 2018

This was a great course. The instructors were fun and knowledgeable and the assignments were well-written. I loved the flexibility of being allowed to use whatever software I wanted to solve the ML assignments since the quizzes were based on the results of the modeling rather than submitted code. For some assignments I used sklearn and for others I used the software recommended by the instructors (graphlab).

par Joseph C

5 déc. 2015

Excellent overview course, introducing the ideas of regression, classification, clustering, recommender systems, and a sort of 'short cut' of using the early layers pretrained deep neural network for image recognition as feature inputs into a classifier. Don't expect to get into the 'details' of implementation in this overview course; I believe that level of detail will be covered in the subsequent courses.

par Mitkumar P

27 août 2017

This is a very well designed foundation course in the field of Machine-Learning. This course covers all the important topics of machine learning and data science from classification to deep learning and also consists of fun and interactive assignments. The instructors are very good and they have designed this course very well, I recommend people interested in machine learning field to take up this course.

par Siddharth M

18 déc. 2015

An excellent introduction to different machine learning algorithms. As expected from an introductory course, this deals with only a top level overview of the tools, without getting bogged down with the details and mathematics of the underlying algorithms. I would recommend this course for those who want to familiarise themselves with using out of the box algorithms provided by different software packages.

par Ferenc F P

10 janv. 2018

I was hesitating during the review between the 4 and 5 star. The only reason was that in some cases one could obtain different results with scikit learn than with Graphlab. But in the end I gave 5 stars because the course material was good and the exercises were made with real (pre-processed) data. This course is very good for both beginners and those who already have some knowledge in machine learning.

par Parag K

23 mai 2021

Excellent structure of course - presented core concepts in very easy chunks for professionals to ingest, as well as gave real-world scenarios how knowledge can be used. The course dived deep enough to get hands dirty without delving too much into theory which might become useful as student gets overall understanding and then dive further. In all, fun approach with lot of potential for students to grow.

par Sauvage F

18 déc. 2015

Very enjoyable course! Emily and Carlos actually succeed in giving a more than useful overview about so many kinds of tasks, algorithms and concepts of machine learning in very short time (given the material to cover!). I really loved the topics of the hands on assignments.

New to Python (I'm a R user most of the time) I also learned a lot about "the other language" of Data Science. Thanks a lot!

par Christine S

9 nov. 2015

Course is well organized, lectures explain learning concepts very well. And using python notebook examples to show machine learning uses are very unique and quite easy to follow. The assignments may not have been as challenging as some other school's courses, but overall, this is a great course for those who would like to have a practical approach to apply machine learning to solve data problems.

par Christopher O

2 juin 2017

The course is very organized and begins as a good introductory module. The difficulty increases throughout the course, but you are given all of the information and tools you need to respond to questions, unlike some other ML and engineering related MOOCs. You also learn some techniques that are actually useful and entertaining, like scouring wikipedia to find how similar people or articles are.


11 avr. 2016

This is course is great and the way its been taught by professors is very cool :)

I am getting to know the use case and than how we are going to do it, rather than conventional other way round. I am so happy that we first come to know about the application and its so important for a student to know that.

Thank you so much, only problem I see is that this course should have been started earlier :)

par jackytu256

15 déc. 2015

Its a course that provides a basic concept of what the ML is such as linear regression, classification, clustering and etc. This course not only offers the general idea for students but also implements Python-based code ( based on the all of case studies), which is an efficient approach to let me real know what the lectures talk about. Its a real nice course for the ML entry-level students.