公开(公告)号：US20200326852A1

公开(公告)日：2020-10-15

申请号：US16674919

申请日：2019-11-05

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Se-Bum Paik ,  Hyeonsu Lee ,  Youngjin Park

IPC: G06F3/06 ,  G06N3/04 ,  G06N3/08

Abstract: Provided are a storage device using a neural network and an operating method of the storage device for automatic redistribution of information and variable storage capacity based on accuracy-storage capacity tradeoff that may learn input information using the neural network and may store the learned information. The neural network may include a plurality of input neurons and a plurality of output neurons; at least one stable synapse configured to connect at least one of the input neurons and at least one of the output neurons, respectively; and at least one flexible synapse configured to connect at least one remaining of the input neurons and at least one remaining of the output neurons, respectively.

公开(公告)号：US11068774B2

公开(公告)日：2021-07-20

申请号：US15720772

申请日：2017-09-29

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Se-Bum Paik ,  Youngjin Park

IPC: G06N3/063 ,  G06N3/04 ,  G06N3/08 ,  G11C11/54 ,  G11C11/16

Abstract: Provided is a spiking neural network system for dynamical control of flexible, stable, and hybrid memory storage. An information storage method may include converting input information to a temporal pattern in a form of a spike; and storing the information that is converted to the temporal pattern in a spiking neural network. The storing may comprise storing information by applying, to the spiking neural network, a spike-timing-dependent plasticity (STDP) learning rate that is an unsupervised learning rule.

公开(公告)号：US11467728B2

公开(公告)日：2022-10-11

申请号：US16674919

申请日：2019-11-05

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Se-Bum Paik ,  Hyeonsu Lee ,  Youngjin Park

IPC: G06F3/06 ,  G06N3/08 ,  G06N3/04

Abstract: Provided are a storage device using a neural network and an operating method of the storage device for automatic redistribution of information and variable storage capacity based on accuracy-storage capacity tradeoff that may learn input information using the neural network and may store the learned information. The neural network may include a plurality of input neurons and a plurality of output neurons; at least one stable synapse configured to connect at least one of the input neurons and at least one of the output neurons, respectively; and at least one flexible synapse configured to connect at least one remaining of the input neurons and at least one remaining of the output neurons, respectively.

公开(公告)号：US11354918B2

公开(公告)日：2022-06-07

申请号：US17000887

申请日：2020-08-24

Applicant: Korea Advanced Institute Of Science And Technology

Inventor： Se-Bum Paik ,  Gwangsu Kim ,  Jaeson Jang ,  Seungdae Baek ,  Min Song

IPC: G06V30/194 ,  G06N20/10 ,  G06N3/04 ,  G06N3/08

Abstract: Various example embodiments relate to an electronic device for recognizing visual stimulus based on spontaneous selective neural response of deep artificial neural network and an operating method thereof, and may configured to measure a response of an untrained randomly-initialized neural network for an input image, and recognize at least one visual stimulus from the input image, based on the measured response.