deep neural networks

In this paper, we focus on the numerical solution of high-dimensional stochastic optimal control problems, whose system states are modeled as jump-diffusion processes.  Through the maximum principle and deep neural networks, we restate the original control problem as a variational problem, and we introduce specialized algorithms to solve this new formulation.  The algorithms and the various architectures employed have been introduced.  The mean-variance portfolio selection problem in a financial market consisting of two kinds of assets in a jump-diffusion process settin

With rapid development of machine learning and subsequently deep learning, deep neural networks achieved remarkable results in solving various tasks. However, with increasing the accuracy of trained models, new architectures of neural networks present new challenges as they require significant amount of computing power for training and inference. This paper aims to review existing approaches to reducing computational power and training time of the neural network, evaluate and improve one of existing pruning methods for a face detection model.