Open Source Neural Network Model

Rudy, Paula Lorraine

Student Work

Open Source Neural Network Model

Public

This Major Qualifying Project is an open source supervised machine learning neural network software development kit (SDK) utilizing a stochastic gradient descent with cross-entropy error backpropagation algorithm, implemented in Java. This SDK provides a human-readable implementation of a commonly used method of machine learning, thereby supplying a transparent learning tool for students. The SKD was demonstrated by providing functional examples of networks designed for classification. Examples were provided ranging in complexity from the simplest most transparent example of learning, to a real world example of classification based on color.

This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator