The purpose of this project is to investigate self-adaptive forecasting and anomaly prediction algorithms based on deep neural networks (DNNs). DNNs present a compelling technology due to their wide-spread availability through open-source projects (e.g. TensorFlow, MXNet). However, usability of DNNs in scenarios outside of image, speech or text pattern recognition is mostly unproven. This project aims to reduce the knowledge gap that exists in the usage of DNNs in the context of pattern recognition with DNNs in network management and network equipment manufacturing. The output of the project will be a set of hyper-parameter optimization and concept drift adaptation algorithms, which can be used to optimize DNNs for pattern recognition in network management data and network equipment manufacturing data.