US Patent Issued to Emory University on May 13 for "Systems and methods for training an autoencoder neural network using sparse data" (Georgia Inventors)

ALEXANDRIA, Va., June 12 -- United States Patent no. 12,299,582, issued on May 13, was assigned to Emory University (Atlanta).

"Systems and methods for training an autoencoder neural network using sparse data" was invented by Chethan Pandarinath (Decatur, Ga.) and Mohammadreza Keshtkaran (Atlanta).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems are provided to prevent pathological overfitting in training autoencoder networks, by forcing the network to only model structure that is shared between different data variables and to enable an automatic search of hyperparameters in training autoencoder networks, resulting in automated discovery of optimally-trained models. The method may include tr...