Improving the Performance of the Neocognitron

D. Lovell, David Simon, and A. Tsoi
Fourth Australian Conference on Neural Networks, 1993, pp. 22-25.

  • Adobe portable document format (pdf) (426KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

The neocognitron is an artificial neural network which applies certain aspects of the mammalian visual process to the task of 2-D pattern recognition. The resulting network model is complex in both structure and parameterization. We describe experiments which show that the performance of the neocognitron is sensitive to certain parameters whose values are seldom detailed in the relevant literature. We also present results which suggest that the selectivity parameters in the neocognitron can be adjusted in a straightforward manner so as to improve the classification performance of the neocognitron.

Associated Center(s) / Consortia: Vision and Autonomous Systems Center

Text Reference
D. Lovell, David Simon, and A. Tsoi, "Improving the Performance of the Neocognitron," Fourth Australian Conference on Neural Networks, 1993, pp. 22-25.

BibTeX Reference
   author = "D. Lovell and David Simon and A. Tsoi",
   editor = "P. Leong and M. Jabri",
   title = "Improving the Performance of the Neocognitron",
   booktitle = "Fourth Australian Conference on Neural Networks",
   pages = "22-25",
   year = "1993",