This is my first day taking the course and I feel like it is very centered around Deep Learning in opposed to Machine Learning. In all of the places I’ve worked what is used is ML so I was really looking for content on how to improve the ML systems.
I’m just lightly familiar with TFlow and DL, is this course for me?
Welcome to our forum.
The specialization is focused on the following topics:
- The design of a generic ML production system end-to-end
- How to build data pipelines by gathering, cleaning, and validating datasets.
- Establish data life cycle by using data lineage and provenance metadata tools.
- Establish a model baseline, address concept drift, and prototype how to develop, deploy, and continuously improve a generic ML application in a production environment.
All the topics are illustrated by many valuable jupiter notebooks often based on TFlow.
So the 4 courses of the current specialization are not related to the development of the Deep Learning models, but they explain how to deploy a generic ML model in a production environment.
If you are interested to improve your skills about Deep Learning or about TFLow, please consider to take other specializations released by DeepLearning.ai. For instance Deep Learning Specialization, or TensorFlow: Data and Deployment Specialization.
Hope this can help