Fig. 7.

Performance of VisNet and HMAX C2 units measured by the percentage of images classified correctly on the classification task with 8 objects using the Amsterdam Library of Images dataset and measurement of performance using a pattern association network with one output neuron for each class. The training set consisted of 4 views of each object spaced ${90}^{\circ }$ apart; or 9 views spaced ${40}^{\circ }$ apart; or 18 views spaced ${20}^{\circ }$ apart. The test set of images was in all cases a cross-validation set of 18 views of each object spaced ${20}^{\circ }$ apart and offset by ${10}^{\circ }$ from the training set with 18 views and not including any training view. The 10 best cells from each class were used to measure the performance. Chance performance was 12.5 % correct