Christian Roberson, Douglas D. Dankel II
We investigate the use of a morphological neural network to improve the performance of information retrieval systems. A morphological neural network is a neural network based on lattice algebra that is capable of solving decision boundary problems. The morphological neural network structure is one that theoretically can be easily applied to information retrieval. In this paper we propose a new information retrieval system based on morphological neural networks and present experimental results comparing it against other proven models.
Subjects: 1.10 Information Retrieval; 14. Neural Networks
Submitted: Feb 9, 2007