IS THE NEOCOGNITRON CAPABLE OF STATE-OF-THE-ART DIGIT RECOGNITION?
David Lovell, Tom Downs and Ah Chung Tsoi
July 1995
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 recognition performance on a par with state-of-the-art digit recognition systems.
The neocognitron's performance is shown to be highly 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 selectivity adjustment techniques suggests that e 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 the neocognitron is unable to achieve the rformance of existing digit classifiers due to its reliance upon the supervisor's choice of selectivity parameters and training data. ese 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.
If you have difficulty viewing files that end '.gz',
which are gzip compressed, then you may be able to find
tools to uncompress them at the gzip
web site.
If you have difficulty viewing files that are in PostScript, (ending
'.ps' or '.ps.gz'), then you may be able to
find tools to view them at
the gsview
web site.
We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.