This work proposes the use of a micro genetic algorithm to optimize the architecture of fully connected layers in convolutional neural networks. with the aim of reducing model complexity without sacrificing performance. Our approach applies the paradigm of transfer learning. enabling training without the need for extensive datasets. https://www.lightemupsequences.com/deal-find-14K-Gold-plated-Lobster-Closure-Freshwater-Pearl-Bracelet-super-grab/