Nov 23, 2017
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.
Mar 31, 2020
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.
por Armando G•
Sep 30, 2018
This course is the most hands-on deep learning class I have seen so far... and have taken a lot. Most courses focus on the technical details of feedforward, backpropagation, activation functions, etc. but this is the only one I have seen where guidance is provided on how to tackle real-life situations. So far, the BEST course I have takes on deep learning projects tips and tricks.
por Dennis O•
Dec 17, 2017
This course is light on math and programming but loaded with great advice that I have already been able to put into practice at work. Some things are lessons I have learned by being in the field for a few years and others are lessons that might have taken a while to learn on my own. This course has extremely valuable real-world advice that will impact the work I do right away.
por Artyom K•
May 19, 2019
I understood such concepts as: evaluation metric, percentage of distributions, estimating train and dev set errors,
training a basic model first,
carrying out error analysis
on images that the algorithm got wrong,
algorithm will be able to use mislabeled example,
dev and test set should have the closest possible distribution to “real”-data, and so on.
por Sherif M•
Apr 11, 2019
This course offers insights into organizing and structuring machine learning projects. It is different than the other courses of this specialization by not going to much into technical details. I found it still very rewarding since Andrew offers some very niche tricks that can help researchers in practical application of machine learning and deep learning algorithms.
Mar 05, 2018
The topics discussed in this class are very closely associated with the title `Struturing Machine Learning Projects`. These topics are more than just concepts, I think they would be very useful in real projects (Though I haven't done one :) ). There are a lot of use cases discussed in the course. Hoping in the near future, I have an opportunity to use them in practice.
por Michalis P•
Oct 18, 2019
This course was smaller and a bit more theoretical than the previous two courses. Although the lectures give you a good insight on error analysis, things to check in order to optimize your model and finally how you can use a pre-trained model to solve a different task - of the same input data type.
Thanks both to the instructor and the crew for this great series of lectures.
por Bill A•
May 15, 2018
Really changed my thinking about how to run an ML project. I just wish my projects were the kind that could exploit these methods to the fullest. They're more like the autonomous driving example. There are parts that DL is useful for (particularly sequence learning with RNNs) but big parts that aren't (e.g. use of probabilistic graphical models). Anyway, awesome course!
por Linghao L•
Jan 03, 2018
Lots of principles and skills about how to organize machine learning projects and diagnose problems. Especially for the error analysis part, you will definitely save much more time in solving these errors than you expected by following the suggestions taught by Andrew. Thanks Andrew, I really learned a lot from your awesome deep learning courses and felt closer to industry.
por Chetan P B•
Apr 19, 2020
This course is just magical. It covers so many concepts that would require years of experience to gain. Thanks to Professor Andrew for sharing his great knowledge with us. The bias/variance and train and dev/test distribution concepts are very well explained with examples. Also, the quiz helps to practice these concepts which require a better understanding of all of these.
por Pedro H d O P•
Feb 24, 2018
Great course as always! Andrew Ng is a great teacher, and he actually can inspire all of us on being better professionals (and researchers) on the field. The idea of the case studies was great! It was very fun to experience how it is to be part of deep learning projects and the decisions associated with this. Congratulations for all of you guys from coursera! Thank you!
por Amanda W•
Sep 13, 2018
Loved this course as well. Presented very difficult material in a simple and easy to figure manner. Excited for more! Thank you to those who dedicate their time to making this course available, and taking the time to answer questions regarding the material. It is much appreciated and I highly recommend these courses to those who wish to learn about Deep Learning.
por Ventsislav Y•
Dec 22, 2018
Awesome course! I really like the explanations by Andrew Ng. This course gives you skills about how to make error analysis on your models, how to build a machine learning strategy, importance of single evaluation metric, satisficing and optimizing metrics, setting up the train/dev/test distributions and many other topics. Highly recommend this course to everyone!
por Himanshu B•
Jul 06, 2018
This course is surely gona help if planning to learn deep learning.Gaining knowledge is not the best part unless you don't know how to apply the knowledge. This course is all about how and where to apply machine learning and deep learning concepts with much more practicing in real life case studies. Thanks alot for providing such a great content and case studies.
por Mukund C•
Oct 15, 2019
Excellent course. I loved the "flight simulator". I found them challenging. However, some of the questions were worded confusingly, so I got the answers wrong. There is no point in trying to "trick" the test taker by confusing wording in the question as well as in the answers. But, I think this course provides a pragmatic approach to machine learning projects.
por Barbara T•
Dec 25, 2018
This class was well worth the time if you've already invested some effort in learning different principles of machine learning. It causes you to reflect back on different implementations, and understand better how to set up a potential problem and determine how to improve it. The many examples helped solidify items in lectures from prior courses in my mind.
Oct 29, 2017
This course imparts the real world experience that Andrew gained by working in the Industry on the bleeding edge of AI and Machine Learning. This class saves at least 2 years of painful learning on your own by trial and error. I think 2 weeks on this course will put you ahead by 2 years in your path of building neural networks for solving real world problems.
por Osdel H H•
Sep 02, 2018
This course was new for me. I only had some prior knowledge about transfer learnign because I use it on my Bachelor´s Degree Thesis on image segmentation using Imagenet pre-trained weights, but all other concepts and all those guidelines of how to structure a project and how to solve the problems for make a faster and successfull iteration was really helpful
por Mohankumar S•
Sep 02, 2017
Machine Learning Flight Simulator was an intriguing adventure, you get the feel of being inside the shoes of real life AI project leads! Words can't describe Andrew and team's efforts, brilliant guys! Keep up the good work :). Really excited to see what challenges you've got in store for us in the upcoming Convolutional and Recurrent Neural Networks courses.
por Tanuj D•
Mar 28, 2020
This was by far one of the most challenging courses in the deep learning specialization as it covered a lot of practical ml implementation. I personally think that the ideas and the strategies discussed in the course will be highly useful while implementing real-life models. The assignments are very well designed and created a real-life scenario environment
Aug 17, 2018
Andrew Ng is amazing. The way he focuses on these very often overlooked details of ML projects alone would qualify him as a professional of a different category. On top of that he has an incredible ability to explain complex things in an easy way. If he was a baseball player he would be hitting 60 HR per season while pitching 40 games with a 0.87 ERA :-)
por Rashmi N•
May 19, 2019
Thanks a real bunch, Coursera for providing financial aid and bringing up this course, truly loved each and every section, coupled with quiz section at the end, is so much helpful and of course, very thoroughly made! Thanks to all the hardworking instructors and teaching assistance, and of course, coursera team for making this course so effectively! :)
por Sikang B•
Apr 01, 2018
Generally felt this course is super useful as it helped answering several questions of "why we do things this way" rather than follow the paradigm of "it just magically works". Though there are still many magic moments while learning on ML in general, I felt this course really helped broad my view and understand the overall problem space much better.
por Luo D•
Sep 15, 2017
Having finished the first three courses in the Deeplearning.ai's specialization, I find this course is the most valuable one. It is not telling you the basic algorithms like the first two courses, but telling you how to ANALYZE you project as a whole in each step, and where to go next. The first two tell you how to build, this one tells how to THINK.
por Jay C•
Mar 20, 2018
Excellent guide work by Andrew NG,
I really like the way he delivers the intuitions or insights from deep networks. The most important think when working with these kind of project is to look below find what you missed in considering higher level extraction. I'm really inspired by his work and keep the advice to improve performance for all projects.
por Abdelrahman R•
Feb 12, 2020
Maybe its different and should help us not just thinking of Algorithms and models ,we should think out of box and think of the error from different approaches as human relative to the machine, think of the data we have, think of different distribution of the data, trying to knowing with different approaches how we should care about of these error.