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.
ML Strategy (1)
Streamline and optimize your ML production workflow by implementing strategic guidelines for goal-setting and applying human-level performance to help define key priorities.
ML Strategy (2)
Develop time-saving error analysis procedures to evaluate the most worthwhile options to pursue and gain intuition for how to split your data and when to use multi-task, transfer, and end-to-end deep learning.
Rainer Dreyer completed this course, spending 4 hours a week on it and found the course difficulty to be medium.
The course covered a range of practical issues, such as creating a single performance metric to quickly compare algorithms, how to compare the algorithm with human error to estimate Bayes (ideal) error rates and how to manually inspect and analyze errors...
The course covered a range of practical issues, such as creating a single performance metric to quickly compare algorithms, how to compare the algorithm with human error to estimate Bayes (ideal) error rates and how to manually inspect and analyze errors to decide on further improvements to the algorithm.
This course was the first one in the series to have no programming assignments, opting instead for a quiz at the end of each week presented as a 45-minute case study or "flight simulator". The idea behind these "flight simulators" was to present the student with more complex, long term issues a practitioner would encounter over the course of a real-world machine learning project.
The previous course introduced a first small example using Tensorflow, so not getting to implement some of the new concepts in this course (like transfer learning and multi-task learning) was surprising, but these might be covered again in more detail in a future course.
Silveira Homero completed this course, spending 9 hours a week on it and found the course difficulty to be medium.
This course follows Neural Networks and Deep Learning and Improving Deep Neural Networks. the practical tips are sure valuable to the practitioner.
Raivis Joksts completed this course, spending 4 hours a week on it and found the course difficulty to be very easy.
Interesting course, if you could call it that (more like a series of experience sharing videos) with some applicable ideas. Could benefit from coding exercises that actually model the situations discussed.