Feature-Augmented Neural Networks and Applications of Same

Patent №

US 9,519,858

Granted

2016-12-13

Filed 2013

Owner

MICROSOFT CORPORATION

AI components

5

ml · nlp · vision · speech · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13763701

A system is described herein which uses a neural network having an input layer that accepts an input vector and a feature vector. The input vector represents at least part of input information, such as, but not limited to, a word or phrase in a sequence of input words. The feature vector provides supplemental information pertaining to the input information. The neural network produces an output vector based on the input vector and the feature vector. In one implementation, the neural network is a recurrent neural network. Also described herein are various applications of the system, including a machine translation application.

Machine learningNatural languageVisionSpeechAI hardwareG06N 3/08G06F 40/44G06N 3/04G06N 3/0442G06N 3/0499G06N 3/09

AI classification

Machine learning1.00
Natural language1.00
Speech1.00
AI hardware1.00
Vision0.99
Knowledge representation0.03
Planning0.02
Evolutionary computation0.02

Ownership

MICROSOFT CORPORATION

assignment · 297920840

Assignors

ZWEIG, GEOFFREY G., MIKOLOV, TOMAS, ACERO, ALEJANDRO

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

© 2026 NYSGPT2525 LLC