Image classification is a computer vision problem where Machine Learning has obtained impressive results. In the past to tackle this task practitioners had to use expert knowledge and perform feature engineering, carefully crafting and creating visual features for Machine Learning models to learn. After this step, classical and shallow models were usually employed such as Adaboost, RandomForests, Support Vector Machines, and Multi-layer Perceptrons. 

Despite making their first appearance in the late 80s early 90s, Convolution Neural Networks (CNNs) became popular since 2010 due to technological advances, namely in GPU computing, and have been heavily used for image classification problems with great success surpassing most classical approaches. The main feature that this type of Artificial Neural Network provides is that feature extraction and learning is an integral part of the neural network, performing automatic feature extraction using the whole image as input, where the features are then passed to dense layers, providing the classification power as typical fully connected Multi-Layer Perceptrons are able to. 

In this work, we are going to tackle an image classification dataset of traffic sign images using Artificial Neural Networks (ANNs).