Supervised learning methods require labeled training data, and in classification problems each data sample belongs to a known class, or category. The survey concludes with a discussion that highlights various gaps in deep learning from class imbalanced data for the purpose of guiding future research.
![keras data augmentation for unbalanced class keras data augmentation for unbalanced class](https://cdn.numerade.com/previews/30b1ba39-950e-437e-83ff-2a89364a0153_large.jpg)
data sampling and cost-sensitive learning, prove to be applicable in deep learning, while more advanced methods that exploit neural network feature learning abilities show promising results. Several traditional methods for class imbalance, e.g. We have found that research in this area is very limited, that most existing work focuses on computer vision tasks with convolutional neural networks, and that the effects of big data are rarely considered. Several areas of focus include: data complexity, architectures tested, performance interpretation, ease of use, big data application, and generalization to other domains. This survey discusses the implementation details and experimental results for each study, and offers additional insight into their strengths and weaknesses. Available studies regarding class imbalance and deep learning are surveyed in order to better understand the efficacy of deep learning when applied to class imbalanced data. Having achieved record-breaking performance results in several complex domains, investigating the use of deep neural networks for problems containing high levels of class imbalance is of great interest. Despite recent advances in deep learning, along with its increasing popularity, very little empirical work in the area of deep learning with class imbalance exists. Class imbalance has been studied thoroughly over the last two decades using traditional machine learning models, i.e. Moreover, highly imbalanced data poses added difficulty, as most learners will exhibit bias towards the majority class, and in extreme cases, may ignore the minority class altogether. Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g., fraud detection and cancer detection.
![keras data augmentation for unbalanced class keras data augmentation for unbalanced class](https://machinelearningmastery.com/wp-content/uploads/2019/10/Scatter-Plot-of-Imbalanced-Dataset-Transformed-by-SMOTE-and-Random-Undersampling.png)
![keras data augmentation for unbalanced class keras data augmentation for unbalanced class](https://www.mdpi.com/applsci/applsci-11-10528/article_deploy/html/images/applsci-11-10528-g006.png)
The purpose of this study is to examine existing deep learning techniques for addressing class imbalanced data.