Liam Comerford Apps

This app solves dual-classclassificationproblems in a 2-dimensional space with an ExtremeLearning Machine(ELM) Artificial Neural Network (ANN). Thealgorithm used is basedon the paper “Extreme Learning Machine:Theory and Applications” byG.-B. Huang, Q.-Y. Zhu and C.-K. Siew,Neurocomputing, vol. 70, pp.489-501, 2006.It is designed for educational use and may be useful whenteachingcourses in Machine Learning, whilst also demonstratingtheefficiency of the ELM as a classification tool.Instructions for use:First, define a dual class problem using the red and bluepaintsby selecting "Define Problem" in the upper left corner ofthescreen and drawing on the canvas.Press "Training Data" and drag the slider to define howmanyclassified points are used to train the network.Press "Setup Network" to specify the number of hiddenlayerneurons to use.Press "Train" to train the network - this may take between5-30seconds depending on your hardware and problem setup.On the top right of the screen, once the network is trained,youcan switch between viewing the original specified problem, andthecanvas space as defined by your trained neural network.For more information on ELMs, references and codes for morecomplexproblems visit www3.ntu.edu.sg/home/egbhuang/