A Hybrid Method for Training Convolutional Neural Networks

TL;DR

This paper introduces a hybrid training approach combining backpropagation and evolutionary strategies for CNNs, improving image classification accuracy on CIFAR-10 by avoiding local minima and fine-tuning weights.

Contribution

The paper presents a novel hybrid training method that integrates evolutionary strategies with backpropagation to enhance CNN performance.

Findings

Achieved a 0.61% increase in accuracy on CIFAR-10 with VGG16.

Demonstrated the hybrid method's ability to avoid local minima.

Improved training results over standard backpropagation.

Abstract

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