Member-only story
Build Your First Machine Learning Model With TensorFlow
A practical step-by-step example to understand how Machine Learning works
In this post, I will explain step by step how to create a straightforward Machine Learning model using TensorFlow.
TensorFlow is a library developed by Google that was released as open source in 2015. TensorFlow makes it very simple to build and train a Machine Learning model.
The model we are going to build next will allow us to convert kilometers to miles automatically. Performing this calculation with a mathematical formula has no mystery but what we are going to do in this example is to create a model that learns how to perform this conversion.
We will provide the model with an input CSV file with 29 conversions already performed between kilometers and miles, and, based on them, our model will learn to perform this conversion automatically.
We will use a supervised learning algorithm because we know the input and output results of our data.
As a programming language, we are going to use Python. Python offers a series of handy libraries and utilities to work with Machine Learning.
All the steps in this example were performed using Google Colab. Google Colab allows us to write and execute Python in our browser with zero configuration.
Importing the Necessary Libraries
We start by importing the libraries we are going to use in our example.
- We will import TensorFlow to create our Machine Learning model.
- We will also import the Pandas library to read the CSV file with conversions from kilometers to miles.
- And finally, we will import the Seaborn and Matlotlib libraries to paint the different results.
