Deep quaternion neural networks for spoken language understanding

Abstract

Deep Neural Networks (DNN) received a great interest from researchers due to their capability to construct robust abstract representations of heterogeneous documents in a latent subspace. Nonetheless, mere real-valued deep neural networks require an appropriate adaptation, such as the convolution process, to capture latent relations between input features… (More)
DOI: 10.1109/ASRU.2017.8268978

Topics

Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.

Slides referencing similar topics