Invention Grant
- Patent Title: Transforming source distribution to target distribution using Sobolev Descent
-
Application No.: US16174622Application Date: 2018-10-30
-
Publication No.: US10860900B2Publication Date: 2020-12-08
- Inventor: Youssef Mroueh , Tom Sercu
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee Address: US NY Armonk
- Agency: Amin, Turocy & Watson, LLP
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06N3/04

Abstract:
Systems, computer-implemented methods, and computer program products for transforming a source distribution to a target distribution. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a sampling component that receives a source distribution having a source sample and a target distribution having a target sample. The computer executable components can further comprise an optimizer component that employs a neural network to find a critic that dynamically discriminates between the source sample and the target sample, while constraining a gradient of the neural network. The computer executable components can further comprise a morphing component that generates a first product distribution by morphing the source distribution along the gradient of the neural network to the target distribution.
Public/Granted literature
- US20200134399A1 TRANSFORMING SOURCE DISTRIBUTION TO TARGET DISTRIBUTION USING SOBOLEV DESCENT Public/Granted day:2020-04-30
Information query