Invention Grant
- Patent Title: Subset conditioning using variational autoencoder with a learnable tensor train induced prior
-
Application No.: US16134624Application Date: 2018-09-18
-
Publication No.: US11593660B2Publication Date: 2023-02-28
- Inventor: Aleksandr Aliper , Aleksandrs Zavoronkovs , Alexander Zhebrak , Daniil Polykovskiy , Maksim Kuznetsov , Yan Ivanenkov , Mark Veselov , Vladimir Aladinskiy , Evgeny Putin , Yuriy Volkov , Arip Asadulaev
- Applicant: Insilico Medicine, Inc.
- Applicant Address: US MD Rockville
- Assignee: Insilico Medicine, Inc.
- Current Assignee: Insilico Medicine, Inc.
- Current Assignee Address: US MD Rockville
- Agency: Maschoff Brennan
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/088 ; G06K9/62 ; G06V20/69
Abstract:
The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.
Public/Granted literature
- US20200090049A1 SUBSET CONDITIONING USING VARIATIONAL AUTOENCODER WITH A LEARNABLE TENSOR TRAIN INDUCED PRIOR Public/Granted day:2020-03-19
Information query
