Chevron Left
Voltar para Structuring Machine Learning Projects

Comentários e feedback de alunos de Structuring Machine Learning Projects da instituição deeplearning.ai

4.8
estrelas
47,534 classificações
5,451 avaliações

Sobre o curso

In the third course of the Deep Learning Specialization, you will learn how to build a successful machine learning project and get to practice decision-making as a machine learning project leader. By the end, you will be able to diagnose errors in a machine learning system; prioritize strategies for reducing errors; understand complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance; and apply end-to-end learning, transfer learning, and multi-task learning. This is also a standalone course for learners who have basic machine learning knowledge. This course draws on Andrew Ng’s experience building and shipping many deep learning products. If you aspire to become a technical leader who can set the direction for an AI team, this course provides the "industry experience" that you might otherwise get only after years of ML work experience. The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI....

Melhores avaliações

MG
30 de Mar de 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.

TG
1 de Dez de 2020

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.

Filtrar por:

501 — 525 de 5,412 Avaliações para o Structuring Machine Learning Projects

por Aaron B

31 de Out de 2018

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.

por Joseph F

27 de Mai de 2018

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.

por Francis C W I

16 de Nov de 2017

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.

por Jess T

9 de Nov de 2017

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.

por Amin N s

14 de Jul de 2019

This course is unique in content and you cant find anything like it anywhere else.

The amount of experience that Andrew conveys is enormous and practical tips that only can come from a real professional like Andrew.

por Nikhil V K

11 de Out de 2019

The course by prof.Andrew Ng gives us a great insight on error analysis and strategies to apply when building a machine learning project to achieve or surpass human level performance in applied deep learning tasks.

por Onkar M

9 de Ago de 2018

I have learnt lots of things on how to structure my machine learning project. I hope that the course wold indeed be very helpful for me in future in my endeavors into fields that are using DL as core technologies.

por Liutov A

26 de Jun de 2018

Thank you very much, Andrew Ng. Your course is very cool. It helps to understand better how to handle different tough things and learn very fast. I recommend this course for learning and getting into Deep Learning.

por Mo R

13 de Nov de 2019

I think it is a really nice qualitative course which really broadens your perspective about various dimensions of a NN project. It is very eye-opening and very conceptual and honestly, very practical. Thanks Andew

por Shubham G

3 de Nov de 2018

thank you for this course, your efforts help me achieve my goal of understanding machine learning and how to apply it to real world and ways of teaching is constantly building my interest in this field. thank-you

por Sinan G

12 de Mai de 2018

Valuable insights into how to structure ai projects with the respect to data, new data, buggy data, synthesized data, mismatched data, and much more such as error analysis and how to use pretrained neural network.

por Marco M

4 de Set de 2020

A great course where Andrew set the bases for a new way of doing machine learning. Aiming to standardization and improvment of ML life cycle to bring Deep Learning model in production much faster and with method.

por Akella N

1 de Set de 2020

A very informative course. Many unknown concepts to improve an NN are covered. I have gained a lot of clarity about the various levels of error fixing and proper training of DL models. Wonderful job by Andrew Ng.

por Devansh K

17 de Jul de 2020

Great course! Content was very interesting and did a good job building upon the previous courses. Enjoyed the assessment in the for of the simulator, gave me a good sense of real world Deep Learning applications.

por Pablo T

13 de Fev de 2018

Teaches how to debug a lot of design and implementation issues that happen when going from theory to practice. This is is the kind of knowledge that you can get from Prof. Ng's experience, but not in a text book.

por Sampath T

27 de Set de 2021

I would like to thank coursera to giving me opportunity to follow Structuring Machine Learning Projects course. In the last few weeks I learned a lot of new theories and basics of improving deep neural networks.

por Bibek B

31 de Ago de 2020

In this section I learnt about the theoritical part of ML strategy, how to set goal, compare with human-level performance, Error analysis etc which I think will help me to develop as Machine Learning Specialist.

por Seungjin B

23 de Ago de 2018

This is a great course but I think it'd be even better to place it after Convolutional NN course. And also wish that there were coding assignments, too, as in other courses in this specialization (Deep leaning).

por Kate S

1 de Jul de 2018

This class will give you some practical tips on moving deep learning projects along. How to focus your attention on the most important things to improve. Some techniques for using other work to move yours along.

por Nektarios K

28 de Abr de 2018

Great course to understand how best to structure and evaluate the performance of your deep learning project. Invaluable information! I actually used info in this course on my real-world project to great success.

por Jose-Fernando E

8 de Out de 2017

Very good course, focusing less on coding / tech aspects and more on the know-how and "art" of the seasoned practicioner. Very useful for acquiring both loose hints and structured approaches. Highly recommended.

por KAPIL M

26 de Ago de 2017

Very useful and practical knowledge. Indeed, this will not be available in any books or theoretical literature. This is very valuable set of suggestions coming from years of experience and research by Andrew Ng.

por Timothy Q

17 de Jun de 2020

As Andrew said, you will not find a lot of content in this course in a very structured way throughout the internet or other courses out there. This is a must take if you are a Data Scientist or an aspiring one.

por Terence T

1 de Nov de 2020

Excellent course. I really enjoyed being confronted with real life deep learning problems and hoe to go about structuring the project. The "flight simulators" were really beneficial for my learning experience.

por Sean D

9 de Set de 2020

Great course with insight into how to prepare your ML and DL projects and the order of operations and caveats and considerations to take into account with your data in real-world scenarios. Highly enjoyed it!