Affiliations: [a] Faculty of Science and Education, University of Mostar, Mostar, Bosnia and Herzegovina | [b] Faculty of Electrical Engineering, Computer Science and Information Technology, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
Correspondence:
[*]
Corresponding author: Hrvoje Ljubić, Faculty of Science and Education, University of Mostar, Matice hrvatske b.b., Bosnia and Herzegovina. E-mail: hrvoje.ljubic@fpmoz.sum.ba.
Abstract: Performance of neural networks greatly depends on quality, size and balance of training dataset. In a real environment datasets are rarely balanced and training deep models over such data is one of the main challenges of deep learning. In order to reduce this problem, methods and techniques are borrowed from the traditional machine learning. Conversely, generative adversarial networks (GAN) were created and developed, a relatively new type of generative models that are based on game theory and consist of two neural networks, a generator and a discriminator. The generator’s task is to create a sample from the input noise that is based on training data distribution and the discriminator should detect those samples as fake. This process goes through a finite number of iterations until the generator successfully fools the discriminator. When this occurs, sample becomes a part of new (augmented) dataset. Even though the original GAN creates unlabeled samples, variants that soon appeared removed that limitation. Generating artificial data through these networks appears to be a meaningful solution to the imbalance problem since it turned out that artificial samples created by GAN are difficult to differentiate from the real ones. In this manner, new samples of minority class could be created and dataset imbalance ratio lowered.
Keywords: Generative adversarial networks, data augmentation, oversampling, deep learning, imbalanced data, imbalanced classification
