Other

Alireza Goudarzi

Steven Wayde Graves

Darko Stefanovic

Daniel Kalb

The invention is directed to a hybrid architecture that comprises a stacked autoencoder and a deep echo state layer for temporal pattern discovery in high-dimensional sequence data. The stacked autoencoder plays a preprocessing role that exploits spatial structure in data and creates a compact representation. The compact representation is then fed to the echo state layer in order to generate a short-term memory of the inputs. The output of the network may be trained to generate any target output.

Growing community of inventors

Albuquerque, NM, United States of America

Alireza Goudarzi