Date of Graduation

5-2016

Document Type

Thesis

Degree Name

Bachelor of Science in Computer Engineering

Degree Level

Undergraduate

Department

Computer Science and Computer Engineering

Advisor

Gashler, Michael

Reader

Wu, Xintao

Second Reader

Parkerson, James

Abstract

Training a system of artificial neural networks on digital images is a big challenge. Often times digital images contain a large amount of information and values for artificial neural networks to understand. In this work, the inference model is proposed in order to absolve this problem. The inference model is composed of a parameterized autoencoder that endures the loss of information caused by the rescaling of images and transition model that predicts the effect of an action on the observation. To test the inference model, the images of a moving robotic arm were given as the data set. The inference model successfully reconstructed the observation using small, rescaled images and even anticipated the observation based on its intuition using its transition model. Capabilities of the inference model implies that the model extracted the essential features of the digital images.

Share

COinS