An evaluation of the neocognitron

Lovell, D. R., Downs, T., & Tsoi, A. C. (1997) An evaluation of the neocognitron. IEEE Transactions on Neural Networks, 8(5), pp. 1090-1105.

View at publisher


We describe a sequence of experiments investigating the strengths and limitations of Fukushima's neocognitron as a handwritten digit classifier. Using the results of these experiments as a foundation, we propose and evaluate improvements to Fukushima's original network in an effort to obtain higher recognition performance. The neocognitron's performance is shown to be strongly dependent on the choice of selectivity parameters and we present two methods to adjust these variables. Performance of the network under the more effective of the two new selectivity adjustment techniques suggests that the network fails to exploit the features that distinguish different classes of input data. To avoid this shortcoming, the network's final layer cells were replaced by a nonlinear classifier (a multilayer perceptron) to create a hybrid architecture. Tests of Fukushima's original system and the novel systems proposed in this paper suggest that it may be difficult for the neocognitron to achieve the performance of existing digit classifiers due to its reliance upon the supervisor's choice of selectivity parameters and training data. These findings pertain to Fukushima's implementation of the system and should not be seen as diminishing the practical significance of the concept of hierarchical feature extraction embodied in the neocognitron. © 1997 IEEE.

Impact and interest:

15 citations in Scopus
Search Google Scholar™
11 citations in Web of Science®

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

ID Code: 79865
Item Type: Journal Article
Refereed: Yes
Keywords: Handwritten character recognition, Neocognitron, Selectivity, Feature extraction, Hierarchical systems, Neural networks, Parallel processing systems, Character recognition
DOI: 10.1109/72.623211
ISSN: 10459227 (ISSN)
Divisions: Current > Schools > School of Electrical Engineering & Computer Science
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: IEEE
Deposited On: 07 Jan 2015 03:59
Last Modified: 07 Jan 2015 03:59

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page