An alternative approach for the evaluation of the neocognitron

The neocognitron network is analysed from the point of view of the contribution of the di erent layers to the nal classi cation. A variation to the neocognitron which gives improved performance is suggested. This variant combines the low level feature extraction capabilities of the initial layers with alternative classi ers such as LVQ and Class Based Means Clustering. This is shown to give performance which is superior to the either of those classi ers acting on their own, and to the neocognitron in its standard form on two di erent instances of the letter recognition problem.