A python script for analysis of some using Keras for machine learning for classification using TensorFlow library and with different optimizers. This script has been developed for a final project in Computer Engineer Grade in Malaga University. This script has been setup for a individual classification research for a specific dataset. The dataset could be downloaded from UCI Cover Type
Today we can´t deny that we live surrounded by the generation of a large amount of data, indeed today that we are in the digital age and most of this information is possible to store and process. Numerous companies seek to focus on the use of such information to make a profit in favor of the objectives of their business and we help ourselves with the appropriate tools to carry out this task. The branch of Artificial Intelligence called "Machine Learning" is one that allows machines to learn through data by detecting patterns and helping to make decisions. With this branch of artificial intelligence what we intend is to use the knowledge of historical data to be able to carry out concrete decisions in the future. Within the automatic learning there are different types of problems, depending on their nature and the target, so in this case we will focus on supervised learning for classification. There are different algorithms and mathematical techniques to carry out a classification problem, one of the most used and known is neural networks. In this project we will make use of two libraries for machine learning to implement a neural network, both designed for use in Python language: one of them is the Scikit-learn library for Machine Learning, and on the other hand the use of the open source library TensorFlow. A comparison and analysis of the behavior of each algorithm will be made with different metrics in the prediction of 7 forest cover types with the use of cartographic variables different values taken in 4 different areas of the Roosevelt National Park, in the north of the state of Colorado.