This project demonstrates the implementation of a JavaFx front end and a convolutional network back end. The front end interface allows the user to create various network scenarios without modifying the code. The back end code includes network layers, activation functions, a matrix library, and json utilities.
See JavaFX-Convolutional-Network.pdf for more information.
Keywords: JavaFx Application, Convolutional Network, Image Classification, Softmax Output Layer, Back Propagation, Gradient Descent, Partial Derivatives, Matrix Flattening, Matrix Unfolding, Concurrent Task, Performance Histogram, Confusion Matrix