Optimal Design of Convolutional Neural Network Architectures Using Teaching–Learning-Based Optimization for Image Classification

RandNet-298.75% (+)91.53% (+)86.53% (+)88.35% (+)56.31% (+)LDANet-298.95% (+)92.48% (+)93.19% (+)87.58% (+)61.46% (+)CAE-198.60% (+)

95.48% (+)

93.19% (+)87.58% (+)61.46% (+)CAE-297.52% (+)90.34% (+)89.10% (+)84.50% (+)54.77% (+)ScatNet-298.73% (+)92.52% (+)87.70% (+)81.60% (+)49.52% (+)SVM+RBF96.97% (+)88.89% (+)85.42% (+)77.49% (+)44.82% (+)SVM+Poly96.31% (+)84.58% (+)83.38% (+)75.99% (+)43.59% (+)PCANet-298.60% (+)91.48% (+)93.15% (+)88.45% (+)64.14% (+)NNet95.31% (+)81.89% (+)79.96% (+)72.59% (+)37.84% (+)SAA-396.54% (+)89.70% (+)88.72% (+)77.00% (+)48.07% (+)DBN-396.89% (+)89.70% (+)93.27% (+)83.69% (+)52.61% (+)EvoCNN 98.82% (+)94.78% (+)97.20% (+)95.47% (+)64.97% (+)psoCNN

99.51% (+)

94.56% (+)

97.61% (+)

96.87% (+)

81.05% (+)

TLBOCNN (Best)99.55%96.44%98.06%97.13%83.64%TLBOCNN (Mean)99.52%95.73%97.72%96.96%81.14%AlgorithmsRectanglesRectangles-IConvex

w/t/l

#BCA

RandNet-299.91% (+)83.00% (+)94.55% (+)8/0/00LDANet-299.86% (+)83.80% (+)92.78% (+)8/0/00CAE-199.86% (+)83.80% (+)NA7/0/00CAE-298.46% (+)78.00% (+)NA7/0/00ScatNet-299.99% (=)91.98% (+)93.50% (+)7/1/00SVM+RBF97.85% (+)75.96% (+)80.87% (+)8/0/00SVM+Poly97.85% (+)75.95% (+)80.18% (+)8/0/00PCANet-299.51% (+)86.61% (+)95.81% (+)8/0/00NNet92.84% (+)66.80% (+)67.75% (+)8/0/00SAA-397.59% (+)75.95% (+)81.59% (+)8/0/00DBN-397.39% (+)77.50% (+)81.37% (+)8/0/00EvoCNN99.99% (=)94.97% (+)95.18% (+)7/1/01psoCNN

99.93% (+)

96.03% (+)

97.74% (+)

8/0/00TLBOCNN (Best)99.99%97.25%97.84%NA8TLBOCNN (Mean)99.94%95.72%97.53%NANA