What you get:
10 ideas for machine learning projects.
Free datasets to use for your projects.
Examples of libraries and algorithms for each case.
There are two key concepts that are important when working as a Data Scientist.
First, you have to experiment. When I approach a machine learning problem, most of the time, I don't know the best way to solve it. There is some intuition, but I always try multiple machine learning models, features, and parameters.
Second, you need to be able to share your solution. It is not enough that the code works on your local machine, otherwise, it is just a personal project. You need to be able to work with others in your team and to productionize your code.
In the video, I show the setup I use in my machine learning projects, what is the folder structure I normally use, and how to combine Jupyter notebooks and Python libraries to effectively solve problems with AI.
If you think this is valuable, consider joining https://bit.ly/emaillistmiguel