Chevron Left
Вернуться к Structuring Machine Learning Projects

Отзывы учащихся о курсе Structuring Machine Learning Projects от партнера

Оценки: 40,981
Рецензии: 4,546

О курсе

You will learn how to build a successful machine learning project. If you aspire to be a technical leader in AI, and know how to set direction for your team's work, this course will show you how. Much of this content has never been taught elsewhere, and is drawn from my experience building and shipping many deep learning products. This course also has two "flight simulators" that let you practice decision-making as a machine learning project leader. This provides "industry experience" that you might otherwise get only after years of ML work experience. After 2 weeks, you will: - Understand how to diagnose errors in a machine learning system, and - Be able to prioritize the most promising directions for reducing error - Understand complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance - Know how to apply end-to-end learning, transfer learning, and multi-task learning I've seen teams waste months or years through not understanding the principles taught in this course. I hope this two week course will save you months of time. This is a standalone course, and you can take this so long as you have basic machine learning knowledge. This is the third course in the Deep Learning Specialization....

Лучшие рецензии


Jul 02, 2020

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!).


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.

Фильтр по:

3776–3800 из 4,504 отзывов о курсе Structuring Machine Learning Projects

автор: Eric S

Aug 30, 2017

Good practical advice. I would have added something about agile development and possibly practical advice on NN architectures (depth and size).

автор: Eloi T

Jul 04, 2020

Excellent content but the quizzes are badly done, many questions have several reasonable answers and very little feedback if we 'get it wrong'

автор: Sujay K

Mar 25, 2018

The course would have been more interesting if we had some programming assignments. Hands on experience into some of these cases really help.

автор: Daniel M

Jan 14, 2018

Unique course in the sense that teaches important topics that are rarely seen in the literature and are fundamental in designing AI projects.

автор: Hagay G

Apr 09, 2019

Had some pretty great info for junior Project Managers, for some reason, it's also hiding some extremely important info about end-to-end DL.

автор: Mohamed M H M A

Apr 22, 2018

Some of the videos weren't of good quality. Also, I was expecting doing a real project not to make decisions based on different scenarios.

автор: Nikolai K

Oct 03, 2017

Good course overall, would have liked to have the in-depth programming assignments though, those really made the other courses stand out.

автор: Shashank S S

Jul 08, 2019

Learned various ways to structure ML projects in industry.

It would have been great to have few programming assignments included as well.

автор: Leonid M

Oct 05, 2017

Some tips are very useful for practitioners but the same information is repeated over and over again that makes the course quite boring.

автор: aman a c

May 18, 2020

A small course with very effective tips and tricks to figure out how to start and proceed further while building a project effectively.

автор: 김진수

Feb 26, 2019

I think this lecture is very useful when we make our own ML system.

Also, it has many examples about errors we can usually meet in real.

автор: Tim S

Feb 26, 2018

Useful, practical material. I probably underappreciate the importance of someone (especially of Dr. Ng's stature) covering this for us.

автор: Bill T

Feb 25, 2018

Very practical lessons in this module that should make you and your team more efficient in implementing deep learning on real problems.

автор: Edward M

Dec 24, 2019

another great Andrew Ng course. This one gives practical insights in how to go about making your deep neural networks perform better.

автор: Mohammad H

Dec 17, 2019

I really found the pilot training quizzes are great and very helpful, but some questions one can debate if has the right answer or not

автор: Riley

Apr 08, 2019

Quizzes could be refined since some of the questions are really confusing & need weird pre-requisite knowledge about human physiology.

автор: Kalfas I

Aug 14, 2018

It was an interesting course for sure, but it was a bit stretched and the notions explained could be compressed in a much shorter one.

автор: John E M

Apr 01, 2018

I appreciate the review and hints on structuring ML projects. Just seemed a little lacking on the meat and potatoes of real practice.

автор: JEREMY S

Jun 07, 2020

Interesting to understand how to manage a problem during a ML project, really good trick and tip! Thanks Andrew and deep!

автор: Alhasan A

Jun 01, 2019

It would be more useful to give explanation why an answer is correct and others are wrong, such details enhance our learning so much.

автор: Aditya A G

Feb 21, 2018

Machine Learning Simulator & course contents well prepares you to how a machine learning project should be structured and approached

автор: Huang C H

Nov 24, 2017

Probably the least exciting of the five. This is a short course on how to approach machine learning projects, as the title suggests.

автор: Priyanka T

Oct 22, 2017

I thought this course was great content wise, but needs to improve on the errata in the content (repeated video sections), and quiz.

автор: Bingnan L

Feb 01, 2018

I think it should be useful but since I haven't got many practical experience, the course seems a little bit hard to catch up with.

автор: Zheng Z

Apr 25, 2019

I think a little bit more programming homework can help me better understand the concepts, but other than that everything is good.