This document presents a Deep Hyper-Network Embedding (DHNE) model to learn low-dimensional representations of hypernetworks. The DHNE model uses an autoencoder and fully connected layer to preserve both local and global proximity in the embedding space. The DHNE model is tested on four datasets and outperforms other network embedding methods on tasks like network reconstruction, link prediction, and classification. The DHNE model can learn embeddings of hypernetworks while preserving the decomposability property of hyperedges using a nonlinear tuple similarity function.