公开(公告)号：US11521057B2

公开(公告)日：2022-12-06

申请号：US15795691

申请日：2017-10-27

申请人： DENSO IT LABORATORY, INC. ,  Tokyo Institute of Technology

发明人： Ikuro Sato ,  Ryo Fujisaki ,  Akihiro Nomura ,  Yosuke Oyama ,  Satoshi Matsuoka

IPC分类号： G06N3/08 ,  G06F17/10 ,  G06N3/04

摘要： According to one embodiment of the present disclosure, provided is a learning system that updates a parameter for a neural network, the learning system including: a plurality of differential value calculators; and a parameter update module.

公开(公告)号：US20180336430A1

公开(公告)日：2018-11-22

申请号：US15947009

申请日：2018-04-06

申请人： Denso IT Laboratory, Inc.

发明人： Ikuro Sato ,  Mitsuru Ambai ,  Hiroshi Doi

IPC分类号： G06K9/46 ,  G06T7/10 ,  G06N3/04 ,  G06K9/20

CPC分类号： G06K9/46 ,  G06K9/209 ,  G06K9/6257 ,  G06N3/0454 ,  G06N3/0481 ,  G06N3/063 ,  G06N3/084 ,  G06T7/10 ,  G06T2207/20084

摘要： A recognition system includes: a sensor processing unit (SPU) that performs sensing to output a sensor value; a task-specific unit (TSU) including an object detection part that performs an object detection task based on the sensor value and a semantic segmentation part that performs a semantic segmentation task based on the sensor value; and a generic-feature extraction part (GEU) including a generic neural network disposed between the sensor processing unit and the task-specific unit, the generic neural network being configured to receive the sensor value as an input to extract a generic feature to be input in common into the object detection part and the semantic segmentation part.

公开(公告)号：US10769479B2

公开(公告)日：2020-09-08

申请号：US15947009

申请日：2018-04-06

申请人： Denso IT Laboratory, Inc.

发明人： Ikuro Sato ,  Mitsuru Ambai ,  Hiroshi Doi

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06T7/10 ,  G06K9/20

摘要： A recognition system includes: a sensor processing unit (SPU) that performs sensing to output a sensor value; a task-specific unit (TSU) including an object detection part that performs an object detection task based on the sensor value and a semantic segmentation part that performs a semantic segmentation task based on the sensor value; and a generic-feature extraction part (GEU) including a generic neural network disposed between the sensor processing unit and the task-specific unit, the generic neural network being configured to receive the sensor value as an input to extract a generic feature to be input in common into the object detection part and the semantic segmentation part.

公开(公告)号：US09824586B2

公开(公告)日：2017-11-21

申请号：US13689196

申请日：2012-11-29

申请人： DENSO IT LABORATORY, INC. ,  DENSO CORPORATION

发明人： Ikuro Sato ,  Yukimasa Tamatsu ,  Kunihiro Goto

IPC分类号： G08G1/16 ,  G06K9/00

CPC分类号： G08G1/166 ,  G06K9/00805

摘要： The moving object recognition system includes: a camera that is installed in a vehicle and captures continuous single-view images; a moving object detecting unit that detects a moving object from the images captured by the camera; a relative approach angle estimating unit that estimates the relative approach angle of the moving object detected by the moving object detecting unit with respect to the camera; a collision risk calculating unit that calculates the risk of the moving object colliding with the vehicle, based on the relationship between the relative approach angle and the moving object direction from the camera toward the moving object; and a reporting unit that reports a danger to the driver of the vehicle in accordance with the risk calculated by the collision risk calculating unit.

公开(公告)号：US20180032865A1

公开(公告)日：2018-02-01

申请号：US15439304

申请日：2017-02-22

申请人： DENSO CORPORATION ,  TOKYO INSTITUTE OF TECHNOLOGY

发明人： Hiroki Nishimura ,  Satoshi Matsuoka ,  Akihiro Nomura ,  Yosuke Oyama ,  Ikuro Sato

IPC分类号： G06N3/08 ,  G06N3/04

CPC分类号： G06N3/08 ,  G06F9/46 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/084

摘要： In a prediction apparatus for a learning system, an obtaining unit obtains, as input variables, at least one parameter indicative of a structure of a convolutional neural network, the number of nodes of a learning system, and a sub-batch number indicative of the number of pieces of training data collectively processed by at least one graphic processing unit. A predictor predicts at least one of learning time and an average mini-batch size as a function of the input variables obtained by the obtainer. The learning time is time required for one update of all the weights by a central processing unit. The average mini-batch size is an average number of pieces of training data used for the one update of all the weights.