Generative Adversarial Network (GAN) is a deep learning architecture that has gained popularity in solving complex computer vision problems. Most of the classification problems which popularly employ a deep learning approach can be seen as a Stackelberg game. The design of deep learning models often involves a game-theoretic approach. Existing research contributions demonstrate that game theory is a potential approach to improve results in deep learning models. Game theory helps to model or solve various deep learning-based problems. The application of game theory to deep learning includes another dimension in research. Alternatively, game theory has been showing its multi-dimensional applications in the last few decades.
Today, deep learning is a fast-evolving area for research in the domain of artificial intelligence. This paper provides a comprehensive overview of the applications of game theory in deep learning.
