Neural Networks for Discovering Latent Factors from Data

Patent №

US 11,468,265

Granted

2022-10-11

Filed 2019

Owner

HITACHI, LTD.

Lab

AI components

4

ml · nlp · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16389532

Aspects of the disclosure relate to a method for discovering latent factors from data in a neural network environment. Aspects include adding, by a data noise unit of the neural network environment, noise to a set of input data; computing, by the encoder model and a set of stochastic non-linear units, a set of latent code based on the set of input data; obtaining, by decoding the latent code with a decoder model, a set of reconstructed data.

Machine learningNatural languageKnowledge representationAI hardwareG06N 3/045G06N 3/0455G06F 18/2113G06F 18/2148G06F 18/2155G06N 3/0464G06N 3/0475G06N 3/0495+6 more

AI classification

Machine learning1.00
AI hardware0.98
Natural language0.96
Knowledge representation0.69
Speech0.04
Planning0.00
Evolutionary computation0.00
Vision0.00

Ownership

HITACHI, LTD.

assignment · 489490317

Assignors

CHHABRA, MOHIT, KLINKIGT, MARTIN, MURAKAMI, TOMOKAZU

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC