While the information from this course was awesome I would've liked some hand on projects to get the information running. Nonetheless, the two simulation task were the best (more would've been neat!).
I learned so many things in this module. I learned that how to do error analysys and different kind of the learning techniques. Thanks Professor Andrew Ng to provide such a valuable and updated stuff.
By Asad A•
Really good insights into the practical aspects of structuring projects. Large scale deep learning/ ML is as much about people management and strategic prioritization as it is about complex algorithms and big data handling
This is a very useful course since that you can get an impotant instruction to build your own project. You can reduce your time cost and iterate quickly to produce more value by using the knowladges taught by this course.
Good. However, understanding the importance of strategy, either additional scenario quiz (the simulation type quiz is good) or a programming assignment would reinforce the understanding (given short duration of the course)
By Henderika V B•
I loved the translation of all the different succesfactors to the daily practice and examples in the course. It gave me an general idea of what to look out for when identifying my own AI problems and defining a NN for it.
By Abhishek R•
This was probably the most useful course of the entire specialization with real-world examples, tips, tricks and techniques on how to approach the problems in Machine Learning world as a whole and Deep Learning in general
By Francisco R•
Even though it's a short course and it doesn't have programming assignments, which I love doing, it has though these case study, which are quite fun and educative, helping you to get started in a Machine Learning project.
By Andrés S•
I liked this course because I gave me an idea of real situations I could face working on Machine Learning, but I think a little code would've been helpful, for example, to better understand how to do a transfer knowledge
By Ladislav Š•
This part of Deep learning specialization is similar to Machine Learning Yearning written by prof. Andrew Ng. I read the whole book and for me this was mostly a repetitive information - however, very useful and relevant.
a lot of value for the minimal time invested, and the case study approach was the main reason I would give it 5 stars. Some parts in the videos could be fleshed out more with more real world examples where it was vauge.
By Naresh K P•
This course helped me understand how to prioritize problems that we encounter in Machine Learning space. On the surface this might look simple, but I think this course will have a huge impact as I implement ML problems.
By TANVEER M•
The course taught me about errors how to minimise the errors .How we can improve model performance.satisficing and optimising metrics.Overall the course was quite good.The case studies I found more interesting to solve.
By Akshat A•
Amazing Course! I generally don't feel like I gain much from lectures and would prefer reading but I'm really glad I took this course, gave me lots of insights into how one would go about improving performance quickly.
By Madalena R•
I really enjoyed this course, I think Andrew has a lot of knowledge on the subject matter and he is able to explain it in a very detailed and understandable manner. The interviews were a plus and also very interesting!
By Bedirhan Ç•
Videos were really help me understand the decision making and strategies for machine learning projects and quizzes were quite good real life simulations of what decisions i could make. I learnt a lor from this course.
By Utsav A•
This case was useful for getting an experienced way of approaching the real-world problems of ML. The quizzes further added to the application of the basics learnt throughout the course. Overall, it was a good course!
very much wonderful. especially the simulation process, which extracts the pure logic decision process during implementing DNN without actually experiencing all the detailed procedures which are not really challenging
By Lewis C•
Good course. Very interesting!
Having done the course, most of the ideas seem fairly obvious. However, the chances of me coming up with them on my own are almost 0.
Therefore I think the training has been successful.
By Muhammad S K•
It was an amazing experience and I learn a lot of new Machine Learning strategies and error analysis techniques that will help me a lot in my future research work. Thanks a lot, Mr. Andrew, you are an awesome speaker.
By Luiz A N J•
Excellent course, give great practical advice of how to structure projects and to make decisions to improve you models. Those insights are hard to find elsewhere and it's the most valuable contribution of this course.
By Guillermo A M G•
I found very useful this course. It is different of what you'll find anywhere because of its focusing in the strategies for developing deep learning projects. Andrew share his experience in a short but unique course.
By Md. S R•
I really loved the learning of different ways of error analysis and solving issues based on the outcomes of the analysis. This is really a ready to use knowledge for me to implement in my job life. Thank you so much!
By Aaron B•
I would give 4 and 1/2 star because I don't understand some of the questions I missed. I will ask in the forums for more detailed explanation. This is a nice course for a simpler break in the middle of the AI course.
By Joseph F•
Very nice to get the advices from NG. Wu, But I think it's better to learn this lesson in the last stage when you have a basic understanding of DL and the strategy should be useful when you debug with your DL model.
By Francis C W I•
Excellent. This class gives an overall perspective on how to approach ML projects to ensure that efforts are focused in the right areas to solve problems where the solutions will have the most impact on performance.
By Jess T•
Dr. Ng set the bar very high in the previous two courses of the specialization. This course is also excellent with very useful practical advice, but maybe a little less polished and streamlined than the previous two.