NEURAL NETWORK BASED RECOGNITION APPARATUS AND METHOD OF TRAINING NEURAL NETWORK

Patent №

US 10,452,976

Granted

2019-10-22

Filed 2017

Owner

SAMSUNG ELECTRONICS CO., LTD.

Lab

AI components

5

ml · nlp · vision · speech · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15463553

A neural network recognition method includes obtaining a first neural network that includes layers and a second neural network that includes a layer connected to the first neural network, actuating a processor to compute a first feature map from input data based on a layer of the first neural network, compute a second feature map from the input data based on the layer connected to the first neural network in the second neural network, and generate a recognition result based on the first neural network from an intermediate feature map computed by applying an element-wise operation to the first feature map and the second feature map.

Machine learningNatural languageVisionSpeechAI hardwareG06N 3/084G06F 18/24133G06N 3/045G06N 3/0495G06N 3/0499G06N 3/09G06V 10/454G06V 10/764+2 more

AI classification

Machine learning1.00
Vision1.00
Natural language0.99
AI hardware0.99
Speech0.71
Knowledge representation0.08
Planning0.03
Evolutionary computation0.01

Ownership

SAMSUNG ELECTRONICS CO., LTD.

assignment · 416460422

Assignors

YOO, BYUNGIN, KIM, YOUNGSUNG, KWAK, YOUNGJUN, CHOI, CHANG KYU

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

© 2026 NYSGPT2525 LLC