Summary

Up to this point, we have explored Python with the NumPy, TensorFlow, scikit-learn, pandas, and Matplotlib libraries. More platforms and libraries will be used in this book. In the months and years to come, even more languages, libraries, frameworks, and platforms will appear on the market.

However, AI is not only about development techniques. Building a k-means clustering program from scratch requires careful planning. The program relies on data that is rarely available as we expect it. That's where our imagination comes in handy to find the right features for our datasets.

Once the dataset has been defined, poor conditioning can compromise the project. Some small changes in the data will lead to incorrect results.

Preparing the training dataset from scratch takes much more time than we would initially expect. AI was designed to make life easier, but that's after a project has been successfully implemented. The problem is that building...