Set Reminder Save for later

Structuring Machine Learning Projects

This course is a part of Deep Learning, a 5-course Specialization series from Coursera.

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.

Get Details and Enroll Now

OpenCourser is an affiliate partner of Coursera.

Get a Reminder

Not ready to enroll yet? We'll send you an email reminder for this course

Send to:



Rating 4.6 based on 1,794 ratings
Length 3 weeks
Effort 2 weeks of study, 3-4 hours/week
Starts Feb 11 (10 weeks ago)
Cost $49
From via Coursera
Instructors Andrew Ng, Teaching Assistant - Kian Katanforoosh, Teaching Assistant - Younes Bensouda Mourri, Head Teaching Assistant - Kian Katanforoosh
Download Videos On all desktop and mobile devices
Language English
Subjects Data Science Programming
Tags Data Science Data Analysis Machine Learning

Get a Reminder

Get an email reminder about this course

Send to:

What people are saying

We analyzed reviews for this course to surface learners' thoughts about it

neural network in 33 reviews

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.

I took this course soon after completing the Machine Learning course, before starting the Neural Network and Deep Learning.

Thanks Andrew 希望本课能增加一些编程作业 Lots of good advises and guidance for analyzing the performance of neural network effective and efficiently.

Very good insights on how to go ahead in stuck up projects Having talked to someone who is actively working on Neural Network models, some of the insights I learned from the course looked to be helpful to them as well when we talked.

求中文字幕 Amazing high level overview of neural network alternate implementation options.

A clear explanation of a difficult subject with an emphasis on being able to create and to understand your own neural networks.- Plus in this module how to allocate your resources so you can achieve a successful project.

Not much to learn in this course, basic recommendations can be condensed in one or two lectures Nice presentation on how to start and drive your deep neural network construction.

This course is very helpful that I got to know the things beyond the technical details of the neural network.

case studies in 18 reviews

Excellent I really liked the case studies as it helped understand the real world scenarios Practical approach examples are really good for thought formulation.

I felt the case studies were amazing.

Would have liked references to more case studies.

The idea of the case studies was great!

The case studies in the quiz are extremely helpful as some concepts can be a bit confusing and they help clarify the doubts you might have in the subtleties between the different situations you may find.

I've also missed having a practical home work, the case studies were fine, but I find that practical applications help me remember things better.

The two case studies are challenging but equally interesting and helpful.

Case studies are incredibly useful and give a global understanding of the different aspects in a ML project.

error analysis in 17 reviews

Excellent course, these materials are never taught anywhere, brilliant stuff Very nice error analysis !

Very nice insights on how to assess your ML algorithm using error analysis.

This course is good and give you skill of error analysis, as well as how to handle data from different distribution.

Good course to learn about structuring the projects and carrying out error analysis.

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.

The concepts are difficult to understand Important insights on error analysis.

Thanks for explaining for Error analysis and how to split train/dev/test data set.

About selecting test and dev set distribution, transfer learning, error analysis , end to end deep learning etc.

neural networks in 16 reviews

This course follows Neural Networks and Deep Learning and Improving Deep Neural Networks.

A lot of useful tips to create neural networks systematically.

This course gave a chance to understand organize the neural networks and machine learning.

Gives a sense about improving the performance of Deep Neural Networks, with error/bias/variance/data mismatch analysis.

It's very easy now-a-days to create Neural Networks and get a grasp of how they work due to high-level frameworks (keras, scikit, tflearn, etc) and abundance of literature and videos, respectively.

I have in the past build some complex Neural Networks, but would hit road blocks that would ruin productivity for I didn't know how to approach problems correctly, and didn't know what knobs to turn to improve performance of my program.

This course contained a lot of great practical tips for implementing Artificial Neural Networks and structuring your own machine learning and learning projects!

It has been an really awesome experience learning about neural networks from you.

case study in 15 reviews

:) Loved the pragmatic, real-world focused material and the case study assignment (much more effective than a quiz with random questions) Shorter than other courses in this specialization, but realy important.

Really awesome, practical workflow with case study!

I really liked the "case study" quizzes for learning.

For better confidence, I would like if you add one more case study.In general the course is good Very interesting!

I wish there were some assignment to work on in addition to the case study quizzes.

Case study flight simulators are good, but poorly introduced.

Absolutely LOVED this course: with the two "case study" you can really get a sense of what does it mean to set up a real ML/DL project and how to address the problems you may (and you're very likely to) face by building up or leading a ML/DL project.If you're thinking about learning Deep Learning, this course is absolutely NECESSARY!

The course showed the experiences while dealing with machine learning projects but could have been better if the experience would have been shared through practical exercises rather than objective case study.It would be better if there were programming exercise as well.

best practices in 12 reviews

very good course This course may seem less technical than the others but it provides a lot of best practices that will impact your work probably more than what you have learnt from the more technical courses.

Highly recommend this to anyone who works on personal projects or is a manager guiding a data science team on a machine learning project Great course to assimilate in best way how structure projects and what best practices apply This course is very important and practical.

This topics needs more quizzes thanks While it was useful to see some of the best practices in ML, and the course contains practical information, the information could be delivered more concisely.

Actually coding in Octave for that class cemented a lot of concepts as well, which this course does not.The title of the course suggests this is pitched towards more advanced students who already know about Machine Learning but maybe not so much about best practices.

Consider this a course on best practices.

It teaches you the best practices in ML projects.

I don't expect advanced math and derivations, but better intuition into why certain best practices exist would be nice.

This course is full of advices and best practices which helps you while working through the projects.


An overview of related careers and their average salaries in the US. Bars indicate income percentile.

Research Scientist-Machine Learning $55k

Cloud Architect - Azure / Machine Learning $75k

Watson Machine Learning Engineer $81k

Machine Learning Software Developer $103k

Software Engineer (Machine Learning) $116k

Applied Scientist, Machine Learning $130k

Autonomy and Machine Learning Solutions Architect $131k

Applied Scientist - Machine Learning -... $136k


Machine Learning Engineer 2 $161k

Machine Learning Scientist Manager $170k

Machine Learning Scientist, Personalization $213k

Write a review

Your opinion matters. Tell us what you think.



Rating 4.6 based on 1,794 ratings
Length 3 weeks
Effort 2 weeks of study, 3-4 hours/week
Starts Feb 11 (10 weeks ago)
Cost $49
From via Coursera
Instructors Andrew Ng, Teaching Assistant - Kian Katanforoosh, Teaching Assistant - Younes Bensouda Mourri, Head Teaching Assistant - Kian Katanforoosh
Download Videos On all desktop and mobile devices
Language English
Subjects Data Science Programming
Tags Data Science Data Analysis Machine Learning

Similar Courses

Sorted by relevance

Like this course?

Here's what to do next:

  • Save this course for later
  • Get more details from the course provider
  • Enroll in this course
Enroll Now