Machine Learning

Many people tend to say that machine learning models are black boxes because they can make good predictions but cannot understand the logic behind those predictions.

Using machine learning in data analysis is a rather procedural approach. As we can notice from the approach, we will start by Preparing data » Defining a model » Model diagnostic checking » Model prediction to complete our workflow. This workflow is often and commonly practiced when we are doing data analysis work.

Creation and evaluation of a deep learning model is a procedural work with steps. *Data preparation » Model optimization» Model fitting » Model evaluation » Model prediction Note Model optimization (adam optimizer) Model fitting (batch, epoch)