I learned so many things in this module. I learned that how to do error analysis and different kind of the learning techniques. Thanks Professor Andrew Ng to provide such a valuable and updated stuff.
It is very nice to have a very experienced deep learning practitioner showing you the "magic" of making DNN works. That is usually passed from Professor to graduate student, but is available here now.
by Muhammad A•
Although, this course of specialization was simple with no assignment still the case studies were quite informative. I would suggest to include a case study related to google machine learning for navigation and voice recognition. We youth can easily relate to this case study. Overall this course was a full package.
by Yuezhe L•
This is a very helpful class. I have been working on machine learning projects for years. This course provides methods to systematically trouble shoot problems in a machine learning project. Despite all the samples are using neural networks, the methodology can be applied to improve other machine learning projects.
by Danial A•
Andrew NG has a peculiar style when it comes to teaching data science. I have never seen someone explaining the terms this effectively. The material in this course is a direct revelation of his years of experience and entails the unique feature of being the lessons learned from the experience. Really great course.
by Bernard O•
Excellent course on managing through the thick of bias/variance tradeoffs. Been doing a lot just based on things I have picked up through experience, but this course puts a the quantitative rigor and discipline behind the art. The sections on transfer and end to end deep learning were eye opening sections for me.
by Gema P•
This course is strategically very important so congrats on making it
I would add a programming assignment including transfer learning or multi-task learning implementation due to the multiple cases of use that are today in the industry.
Thanks again for making this Wonderfull material available to the community ^^
by BAZIL F•
Very useful course for understanding nuances of AI and different useful techniques in strategizing the approaches. Extremely useful in architecting, designing and delivery of the complex solutions involving AI (even as a sub-component). Prof. Andrew Ng is always a pleasure and honor to learn from. Thank You Sir!
by Harvey Q•
Really inspiring course, and UNIQUE. No other class, I think, provide these suggestions on the big question "what's next?" in ML projects. The videos are a bit weirdly sequenced. But they provide very systematic ways of project starting, data splitting, model evaluating, problem finding and tuning. Great course!
by Pedro B M•
This a course on key practices one should have when developing a ML project. Once again Andrew Ng is very pedagogical, teaching sometimes complex concepts in a easy to understand and practical way. I particularly liked the case studies, where the learned concepts had to be put into practice for decision taking.
by Niyas M•
What a great session! Full of practical advice and strategies to help you iterate fast. Prof. Andrew draws on his years of hands-on experience at top companies to put together the best practices for structuring your machine learning projects. This has been the most valuable course in this series for me so far!
by Nikhil K•
super helpful! something that's really valuable in-terms of optimally organizing the thought process i should use to approach an issue i want to solve with Deep Learning.
also, the Quizzes in this course (in-particular) were very important for me because it helped ingrain the tenets of this course in my mind.
by Zebin C•
In the course, I learned how to divide train set, dev set, and test set, and how to solve the problem of different distributions of train set and test set. Impressive is the transfer learning. Transfer learning is a very effective way to help me provide a completely different approach to solving new problems.
by Swapnil T•
What can be better than this, a highly qualified and passionate individual explaining what he has observed and learnt from the mistakes of other professionals , those who themselves are one of the smartest brains so that we don't make mistakes or waste our time realizing that we were hitting something wrong.
by Jeel R•
It was really helpful to get the knowledge about, how difficulties are tackled when working on real project. As sir said in the starting of the course, otherwise it would have taken 2 years to gain all this knowledge. This course helped me a lot about how to pursue certain approach while handling a project.
by Hardik G•
A very useful and important course for this specialization. Downloading datasets and simply applying machine learning algorithm is not the right way. The quality and distribution of data along with the requirement of the project has to kept in mind and this course gives the perfect intuition about the same.
by Jiri L•
This is a really good course and material applicable to deep learning and, to an extent, also to machine learning. The course gives you a very good diagnostic and problem solving methodology for various issues with algorithm performance. So far I'd consider this to be the best course in the specialisation,
by Vishnu V•
Excellent course to understand the ML project pipeline and then to analyse the various problems that could pop up during an ML project. The tips and tricks that we obtain from this course to address those problems are really valuable and unmatched. It is truly one of its kind course from the master itself!
This is a good course to get a feel of real projects and insights on how to go about executing them.I got some good tips to approach a deeplearning project.I don't know if this is too short of a course but I would trust Andrew Ng if he thinks this is fine to get a sense of deep learning projects.
by Fahad S•
The content is very unique and extremely insightful in how to structure a machine learning project. As a machine learning practitioner, I can personally vouch for the usefulness of the suggestions made by Andrew NG. Had I known all of this before, it would have saved me a lot of time on numerous projects.
by Tushar M•
This is the best ML course I have taken so far. A lot of ideas around train/dev/test sets, bias variance trade-off and difference of data distributions between train and dev sets snapped into place for me. I am sure it will take me a while to internalize this content but I feel like I have found the path.
by Edward D•
Brings a lot of useful insight of how to tune the model more from the data point instead of the model or algorithms. This could be super helpful in solving real world problems. Also the two case study homework helped me a lot to get a better understanding of what Andrew meant in his lecture. Great course.
by Shivam S•
The thing is to get started, sir Andrew has given huge insights in working of Neural Networks and driven us through the different parts of the journey. This is not just a course but a story that every Deep Learning enthusiast must go through to see the difference. Eye opening Experience.
by Smail K•
Another amazing course on deep learning and machine learning in general! This course gives you amazing insight into how you could strategize while running a machine learning project. I enjoyed going through the content of this course a lot, but not as much as the case studies! they seemed very realistic.
by Hari K•
Very practical advice for a beginning deep learning engineer on what to do to avoid getting lost in the hyperspace of all the parameters one could change to train a better neural network model. I do wish however there was more explanation of why the different heuristics work, that Prof. Andrew suggests.
by Ashwin K•
Good practical tips for planning out your machine learning projects. Every machine learning engineer should check out this course as it will be really helpful in planning your machine learning projects and allocating time for tasks in the project. And as usual, great, lucid instruction by Andrew Sir! :)
by Carlos A L P•
Very interesting to see a transversal course of how to model and manage ML and DL projects, I am happy to learn new tricks to deal with train/dev/test sets with different distributions, dealing with small datasets and new techniques to apply transfer learning and lastly, how multi-task work in general