After spending longer than expected getting TensorFlow to work on my new M1 MacBook Air (I will add some pointers if someone is really interested in saving 8h of his/her life…) I have started the first post on the first steps using TensorFlow (remember that first post… sigh!).

In this post the main objectives for Machine Learning and some of the key concepts will be introduced. You will learn:

• How is the Machine Learning paradigm different from other programming approaches.
• Difference of classification vs prediction problems.
• How to define a machine learning problem and how to split the data available between training and testing.
• How to compare different models.
• Underfitting and overfitting and the balance between bias and variance.

I have been tinkering with the idea of preparing the TF Developer Certificate and I have finally decided to create some time for it. The main aim for this blog is to summarise the main concepts and the whole experience, alongside with providing pointers for preparing the exam.

This is the first post (of what I hope will be many to come!).