Improving the Performance of the

David R. Lovell, David Simon1 & Ah Chung Tsoi2 Department of Electrical and Computer Engineering, University of Queensland, 4072 Australia Abstract The neocognitron is an arti cial 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 classi cation performance of the neocognitron.