Event Title

Training of CSRN

Student Presenter Information

Bryan Brevard, Old Dominion University

Presentation Type

Event

Disciplines

Electrical and Computer Engineering

Description/Abstract

In the past decade researchers put significant effort to solve complex problems using Artificial Neural Networks (ANNs). A unique type of ANN known as a Cellular Simultaneous Recurrent Network (CSRN) has shown excellent performance for solving complex topological mapping problems such as maze traversal. However, the complexity of CSRN architecture makes it very hard to train. Researchers in ODU’s Vision Lab have improved the training by introducing Unscented Kalman Filter (UKF) algorithm but it is not yet real time. In this research we plan to implement CSRN in a hardware platform to achieve real time performance for large scale problems.

Comments

Faculty Mentor: Dr. Khan M. Iftekharuddin

Location

Learning Commons @ Perry Library, Northwest Atrium

Start Date

13-2-2016 8:00 AM

End Date

13-2-2016 12:30 PM

Full Text of Presentation

wf_no

This document is currently not available here.

Share

COinS
 
Feb 13th, 8:00 AM Feb 13th, 12:30 PM

Training of CSRN

Learning Commons @ Perry Library, Northwest Atrium

In the past decade researchers put significant effort to solve complex problems using Artificial Neural Networks (ANNs). A unique type of ANN known as a Cellular Simultaneous Recurrent Network (CSRN) has shown excellent performance for solving complex topological mapping problems such as maze traversal. However, the complexity of CSRN architecture makes it very hard to train. Researchers in ODU’s Vision Lab have improved the training by introducing Unscented Kalman Filter (UKF) algorithm but it is not yet real time. In this research we plan to implement CSRN in a hardware platform to achieve real time performance for large scale problems.