International Business Machines Corporation

Tom D J Sercu

Payel Das

Cicero Nogueira Dos Santos

Inkit Padhi

Pierre L Dognin

Youssef Mroueh

Sebastian Gehrmann

Kahini Wadhawan

Igor Melnyk

Jarret Ross

A computing device receives a data X and Y, each having N samples. A function f(x,y) is defined to be a trainable neural network based on the data X and the data Y. A permuted version of the data Y is created. A loss mean is computed based on the trainable neural network f(x,y), the permuted version of the sample data Y, and a trainable scalar variable &#x3b7;. A loss with respect to the scalar variable &#x3b7; and the trainable neural network is minimized. Upon determining that the loss is at or below the predetermined threshold, estimating a mutual information (MI) between a test data Xand Y. If the estimated MI is above a predetermined threshold, the test data Xand Yis deemed to be dependent. Otherwise, it is deemed to be independent.

Mutual information neural estimation with Eta-trick

A computer-implemented method according to one aspect includes training a latent variable model (LVM), utilizing labeled data and unlabeled data within a data set; training a classifier, utilizing the labeled data and associated labels within the data set; and generating new data having a predetermined set of labels, utilizing the trained LVM and the trained classifier.

Generating attribute-based samples

Growing community of inventors

New York, NY, United States of America

Tom D J Sercu