Presenter Information

Gabriel Ferrer, Hendrix College

Location

Science Center Auditorium, University of Dayton

Start Date

22-4-2016 4:00 PM

Description

In our research program, we are developing machine learning algorithms to enable a mobile robot to build a compact representation of its environment. This requires the processing of each new input to terminate in constant time. Existing machine learning algorithms are either incapable of meeting this constraint or deliver problematic results. In this paper, we describe a new algorithm for real-time unsupervised clustering, Bounded Self-Organizing Clustering. It executes in constant time for each input, and it produces clusterings that are significantly better than those created by the Self-Organizing Map, its closest competitor, on sensor data acquired from a physically embodied mobile robot.

Comments

Copyright © 2016 by the author. This paper was presented at the 2016 Modern Artificial Intelligence and Cognitive Science Conference, held at the University of Dayton April 22-23, 2016. Permission documentation is on file.

 
Apr 22nd, 4:00 PM

Real-time Unsupervised Clustering

Science Center Auditorium, University of Dayton

In our research program, we are developing machine learning algorithms to enable a mobile robot to build a compact representation of its environment. This requires the processing of each new input to terminate in constant time. Existing machine learning algorithms are either incapable of meeting this constraint or deliver problematic results. In this paper, we describe a new algorithm for real-time unsupervised clustering, Bounded Self-Organizing Clustering. It executes in constant time for each input, and it produces clusterings that are significantly better than those created by the Self-Organizing Map, its closest competitor, on sensor data acquired from a physically embodied mobile robot.