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.
PD
Generally, the course is great. This is a short course and could be combined with other courses in this series. Also, some knowledge such as data splitting has been introduced in the courses before.
YP
Very important and valuable intuitions about DNN training/optimization. It's full of really practical information while implementing my own models.DNN을 실제 적용할때 반드시 이해하고 적용해야 할 실질적 내용들로 구성된 멋진 코스 입니다!
WG
Though it might not seem imminently useful, the course notes I've referred back to the most come from this class. This course is could be summarized as a machine learning master giving useful advice.
CC
Useful to know what are the steps that should be taken after obtaining results. Tho there isn't much information regarding making machine learning projects here (ie. there isn't any hands on project)
EM
I think this is the best way of understanding the models we build and train. Now I can understand where are the errors are coming from and how to focus and choose an error rate problem to solve.
DC
Going beyond the technical details, this part of the course goes into the high level view on how to direct your efforts in a ML project. Really enjoyable and useful. Thanks for making this available!
SB
This course gave some very useful tips on how to start with a Machine learning project when I was struggling to do so. It also gave useful information about error analysis and data set distribution.
ST
This is a must course in the entire specialization. It covers the step by step procedure to approach and solve a problem. The case studies provided are real world problems which are so much helpful.
YL
It's a great course! This course gave me a lot of new perspectives in constructing a machine learning project. Especially, the discussion of data distribution in the train/dev/test set is fantastic.
BB
The course was very insightful on how to tweak and evaluate and measure the performance of your model. I loved the course very very much. Hope to see more courses from deeplearning.ai and Andrew.
AS
Really a good course with mostly the theoretical knowledge on some aspects to reuse your model as well as some error analysis. Thoroughly taught with lots of real-life examples, thanks to Andrew Ng.
ED
Excellent start for digging into topics that are not taught nowhere else. The author books 'Machine Learning Yearning' is a great next read that goes deeper in some of the aspects, really recommended.