Abstract

Inefficient analysis is a large issue in companies with large data pools. Company employees are having to sift through numerous data sets when their time could be used more efficiently elsewhere. Therefore our team intends on designing software to be able to detect patterns and similarities when given a data set. If the program we design is successful, companies can utilize employee time, minimize the number of necessary tasks, and evaluate new patterns of data sets. Through the use of TensorFlow_python and Matlab_deep learning we hope to achieve our goals and create a program to effectively sort through large data files and identify all the necessary patterns quickly and accurately.