A Hybrid Method for Training Convolutional Neural Networks

Artificial Intelligence algorithms have been steadily increasing in popularity and usage. Deep Learning, allows neural networks to be trained using huge datasets also removes the need for human extracted features, as it automates feature learning process. In hearth of training deep networks, such Convolutional Neural Networks, we find backpropagation, that by computing gradient loss function with respect weights network a given input, adjusted better perform task. this paper, propose hybrid method uses both backpropagation evolutionary strategies train where are used help avoid local minimas fine-tune weights, so achieves higher accuracy results. We show proposed is capable improving upon regular task image classification CIFAR-10, VGG16 model was final test results increased 0.61%, average, when compared only backpropagation.