Abstract
Regional empirical typologies have received criticisms for characterizing artifact types as immutable, mutually exclusive groups, rather than analytical groups developed for an analytical purposes. The research presented here uses an empirical regional typology to supply data for the creation of analytical units. Developed in the field of computer science as a means to discover complex patterns in data sets, archaeologists can use artificial neural networks to identify analytical patterns in typological data. In this paper we explain what neural networks are and how they work. We show how a specific architecture and training process can be applied to artificial neural networks to create analytical units from empirical units. Finally, we provide four examples to show that the networks will not find a pattern where none exists, and to demonstrate how artificial neural networks can be applied to solve more complex problems.
Acknowledgements
We would like to thank Dr Michael Collins for his guidance throughout this project. We would also like to thank Sean R. Nash, and Jill Patton for their help with this project, as well as everyone working at the Pre-History Research Project at Texas State University, and the three anonymous reviewers. This project would not have been possible without their support, and guidance.
Notes on Contributors
Brendan S. Nash is an archaeologist at Texas State University, and the Gault School of Archaeological Research, where he researches applications of the computer sciences to archaeological data and materials.
Elton R. Prewitt is an archaeologist retired from Prewitt and Associates, Inc. He is a lecturer at Texas State University and a research fellow at Texas Archeological Research Laboratory at The University of Texas at Austin, and serves as a director of the Shumla Archeological Research and Education Center and of the Gault School of Archaeological Research. His current research includes painted pebbles in Southwest Texas, military actions in the Lower Pecos River, and projectile point classification systems.