Deep learning neural networks (DLNN) are a subset of machine learning techniques that model high-level abstractions in data through multiple layers of interconnected nodes. DLNN can be used to generate test cases by learning the behavior of a given system and generating inputs that are likely to uncover defects, as well as optimize test cases by identifying redundant or irrelevant cases and prioritizing those with higher fault detection capabilities. There have been several successful applications of DLNN in automated test case generation and optimization, and future trends in this area include combining DLNN with other AI techniques, such as reinforcement learning and genetic algorithms.