Skip to main content

Table 5 Classification accuracy of discovered models by evolutionary approaches on different datasets

From: Application of evolutionary and swarm optimization in computer vision: a literature survey

Dataset Approach Accuracy OPT. time #GPUs
CIFAR-10 LEIC [1] 94.60 10 days 250
  CoDeepNEAT [3] 92.70
  CGP-CNN [4] 94.34 10.4 days 2
  Genetic CNN [5] 92.90 2 days 10
  HREAS [6] 96.40 1.5 days 200
  DENSER [7, 8] 93.29
  PSOAO [10] 83.5 3.4 days 1
CIFAR-100 LEIC [1] 77.00
  Genetic CNN [5] 70.97
  DENSER [7, 8] 77.51
MNIST EvoCNN [2] 98.82 2-3 days 2
  DENSER [7, 8] 99.70
  PSOAO [10] 99.51 5 days 1
  IPPSO [11] 98.87
BZI000065_conv-xml0x.pngFashion MNIST\c:IMG EvoCNN [2] 94.53 4 days 2
  DENSER [7, 8] 95.11
ImageNet Genetic CNN [5] 72.13
  HREAS [6] 79.70