Machine Learning Foundations

I really like the case-study approach very great course in a case study approach, you will be familiar with all basic algorithms and ML methods.

I enjoyed the course and the fact that it uses Python for the exercises I like the case study approach.

Very interesting way of exposing concepts using case study approach which makes it more engaging and useful.

The concepts were very easy to grasp and I endorse the case study approach as a effective introduction to complex topics.

But overal very good course I really liked case study approach.

The best thing for the course was the case study approach.

ok Awesome Course for starting out very Basics of Machine Learning with an easy going approach- Case Study Approach.

Loved the case study approach and how it relates to real world problems.

the case study approach is better for understanding the material.

I love case study approach for the machine learning foundation.

I do like the case study approach which allows a grasp on the real application of ML methods.

I think this is because this is a case study approach and like an introductory course.

I am looking forward to the next course to begin implementing and of course, understanding more thoroughly these concepts.

Looking forward to dig deeper into it.

Looking forward to the other 3 courses in this series.

Looking forward to the next courses in the specialization!

Good introduction to machine learning concepts and I'm looking forward to a deeper dive in later courses.

Looking forward to the rest of the specialization for a deeper work with the math and algorithms behind the various techniques covered.

looking forward for the next courses in this specialization.

I am looking forward to complete my specialization Great course for starting ML A good introduction to ML applications, but not as detailed and thorough as I expected.

I'm looking forward to the following of the specialization.

Looking forward to the next courses in the Specialization.

Looking forward to the next course in ML specialization!

I'm looking forward to complete the specialization.

The learning methodology based on study cases is amazing and gripping and the ipython notebooks used in the practical sessions are very instructive.

Really enjoyed working through the IPython notebooks!

Nice Experience Learned iPython Notebook which is good for Machine Learning.Helped me to understand the basics of all the ML techniques and helped me understand where to apply which ML model.

I really enjoyed this course and found it fun to use the iPython notebook to play around with the ML models.

Found the Turi APIs and iPython Notebook approach very effective in getting acquainted to machine learning algorithms.

Very practical by using iPython Notebook Ótimos instrutores e material.

One gets a hang of the ipython notebook and graphlab create environment too.

This course is a greate introduction towards machine learning and the package used graphlab create is really easy to use as well This is a great course i do recommend it for students ready to learn the new way of working with data and not bunch of IF..Else statements Course combines Real Word Applications with simple implementation via IPython Notebooks.

it is an amazing course and a good gate for Machine Learning Good overview of ML methods combined with a gentle introductions to Python and iPython notebook A really good course for beginners who want to understand the concepts and not the underlying algorithms I really liked the case study approach.

I thought it was friendly enough to be appropriate for this kind of intro class, and I really enjoy iPython notebooks for interactive teaching.

IPython notebook and graphlab are amazing tools.

It is really well done, that you have a theory part and a practical "case study" part, were you can follow along with the provided IPython Notebooks.

I have learned the basics about Machine Learning in a simple way :) Highly recommended.

also, there are some errors that make it hard to understand the last week's material, but other than that, it's ok. highly recommended This course gives the kick start needed to start a data science career.

Highly, highly recommended.FYI: the Python level required is really minimal, and the total time commitment is around 4 hours per week.

Highly Recommended!

Highly Recommended!!

Highly recommended for beginners!

Interesting real-world problems on real-world data.Highly recommended.

Excellent course, highly recommended.

Great class overall and highly recommended for those with some basic Python skills and a desire to see what machine learning is capable of.

Highly recommended!

Real life applications....thrust them till the end (even if I'm not comfortable learning from such good but branded teachers) Highly recommended.

Its highly recommended for the students who are completely new to the Machine Learning.

Thanks to Course era and University of Washington for providing a wonderful opportunity.

I am Jun Qi, a Ph.D. student in the department of Electrical Engineering at University of Washington.

I enjoyed learning with good content of videos and do Enhance my knowledge in ML and skilled me to do best Research in my MS Study, Thanks to COURSERA and University of Washington to give financial aid to learn Machine Learning.

Regards, Pratyush Excellent course on the basics of Machine Learning by University of Washington Awesome course will maximum practical applications Good start for ML beginners Very interesting course.

primitive course, didn't expect this low standard from university of Washington One of the best in the business covering all the basics in a very concise and understandable way.

The GraphLabCreate software was neat to see and easy to use, but ultimately I preferred the more first principles approach of Andrew Ng.

However, if you look at some background and practical implementations, Andrew Ng's course is the one to go.

If you are considering this specialization I would recommend the Andrew Ng course instead and the main reason is that it isn't depend on proprietary ML framework.

If you already attended the Machine learning course from Andrew Ng or you have some idea of what is Machine learning about, this is the perfect next step.

You'll be much better off taking Andrew Ng's course, which is significantly more in depth and forces you to write your own solutions to problems instead of relying on a proprietary library.

Big plus for the use of python + notebooks but otherwise, if one is interested just in the overview and not in all the specialization, maybe the Andrew NG course is more detailed.

Having followed several Machine Learning courses, this is now definitely my favourite new course, replacing Andrew Ng's famous course here on Coursera (which was also very good & especially complete, but required too often a leap of faith - this course provides really more details on the "why").

).If you wish to learn machine learning, take the Stanford course on Machine Learning for Andrew Ng.

I appreciate this course that is one of the best mooc courses I ever done.Being a computer science engineer, I found the "hands on" approach particularly amazing, it lets you immediately start applying the topics with real use cases.I started this course after completing the Machine Learning course of Andrew NG (Stanford University), and this made a perfect companion.I think that if I didn't have followed the NG course, probably I would miss something from the theory, particularly maths and statistic that in this course are missing.

This stream along with Andrew NGs is the best ML course available in Coursera.

The course covers wide range of topics along with the real world examples in simple language , The assignments are superb, they help you to grasp the concepts in much detail and sets a strong foundation .

Easy and simple... perfectly explained.Thank you very good for one who has no idea about machine learning , but I dont like dato Good primer to Machine Learning - uses real world examples to introduce different machine learning concepts in an interesting way.

Kudos to the instructors Emily and Carlos for providing a well laid out syllabus with an approach that was grounded on practical concepts and demonstrating hands on with real world examples.

Course was pretty easy to follow and the real world examples helped to visualize the applications of Machine Learning.

Using real world examples was amazing.

Very simple black box approach to ML.

Ok, the platform offered makes things easier, but if you really want to learn machine learning, you can not be limited to a platform, acting as a robot just using pre-written functions in a black box.

But it was an alright introduction to machine learning but not enough if you want to know what makes the 'black box' work.

All algorithms were black boxed.

Makes sense to approach it as a black box and then take deep dives in later series.

By using graphlab as a black box and focusing on specific applications, I really understood why these techniques are useful.

However, the exercises are very general and use 'black box' ML algorithms for most of the solutions.

The machine learning methods covered aren’t necessarily treated as complete black boxes, but the course intentionally avoids getting too deep into the details, putting the emphasis on conceptual understanding.

I wish you to provide us with at least IPYNB for the capstone project because that will help us a lot.

But just wondering why the capstone project is removed from the course specialization?

Actually you could even skip this specialization since they canceled the capstone project so investing any money and time here is a waste.

I am interested to continue in this specialization and conduct the Capstone project.

would be perfect if it didnt lie to me saying there is a capstone project and courses 5 and 6, i wish Amazing Learning approach.

good without the missing course and capstone projects The Deep Learning part needs to be improved Great course and best wishes for Carlos and Emily!

Need some more practical Capstone Projects... Had a blast.

Will continue the course and get my certification and enroll for capstone project as well.

I am really looking forward to complete this specialization with the Capstone project.I know how hard it can be to prepare an entire specialization like this.

Great course Very nice overview of the field Excellent overview of machine learning technique !Even if the subject is complexe, it's easy to understand, and a good starting point to go deeper, as a deep human learning can be ;) Great overview with some implementations of what will be covered through the specialization.

The course is really very basic but can be a good starting point.

Good Starting point for freshers who got interest towards Machine Learning The instructions to download GraphLab don't work and even when you sign to use the AWS platform the instructions are also old and I haven't been able to start any of the assignments because of that!

The tools they provide to examine the material are useful and they stretch you out just far enough.My only regret/negative is that they were unable to complete the full syllabus promised for this specialization, which included recommender systems and deep learning.

For example the recommender systems quiz and programming assignment have nothing about factorization except a single superficial question.

Because anyways, after 4 months in the specialization, if somebody continues to the recommender systems module for example, he/she would have forgotten the basics of this so they would need to cover again the recommender systems week in this course.

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.

jaccardian similarities, recommender systems (precision/recall, AUC), deep learning via transfer learning (not having to explicitly build a model for the problem).

I am giving a 3-star rating as i) the lectures need to be updated with correct data or need to provide guidance as to when one should expect individual difference when following along with the notebook, ii) instructor / mentor response in the discussion forums is lacking, iii) graphlab is now an outdated tool as it is not commercially available.

Excellent presentation of material Good for ML newbie Instructors or TAs are not available in discussion forums.

There are lot more statisticians out there who are heaps better than myself and it was excellent experience to read the questions and answers in the discussion forum.

However, I would have preferred something more challenging, even for a survey course.Though the discussion forums were generally very active (I posted at least one question that was answered by a TA very promptly), there was a question I had towards the end of the course that never got answered.

I thoroughly enjoyed the course and discussion forum was very helpful to progress.

However few improvements is required to have better user experience 1) The content should be upgraded to latest python 2) Since the course recommends Graphlab, there should be up to date detailed instructions to install the same ( disclaimer that this course is not about software....is not helpful to progress) 3) No response is discussion forum - there's no responses provided to the queries.

I do understand many questions in discussion forum is repetitive and someone may find the answer by scrolling through long unstructured hundreds of responses, however this is not efficient.

Recent comments on the discussion forum no longer receive a response.