yamizi/FeatureNet

Deep Neural Networks (DNNs) are intensively used to solve a wide variety of complex problems. Although powerful, such systems re- quire manual configuration and tuning. To this end, we view DNNs as configurable systems and propose an end-to-end framework that allows the configuration, evaluation and automated search for DNN architectures. Our FM and framework have been released in this repository to support replication and future research.

Python