公开(公告)号：GB2579531B

公开(公告)日：2020-11-11

申请号：GB202004685

申请日：2018-10-03

Applicant: IBM

Inventor： OKI GUNAWAN ,  NORMA EDITH SOSA

IPC: G01L5/00 ,  G01L1/12 ,  G01P15/08 ,  H01L21/02

Abstract: A tunable and resettable shock sensor using a parallel dipole line (PDL) trap system is provided. In one aspect, a shock sensor includes: a PDL trap having a pair of diametric magnets separated from one another by a gap gM, and a diamagnetic rod levitating in between the diametric magnets; and contact pads below the PDL trap, wherein the contact pads are separated from one another by a space that is less than a length l of the diamagnetic rod. A shock monitoring system is also provided that includes a network of the shock sensors, as is a method for shock monitoring using the shock sensors.

公开(公告)号：GB2579531A

公开(公告)日：2020-06-24

申请号：GB202004685

申请日：2018-10-03

Applicant: IBM

Inventor： OKI GUNAWAN ,  NORMA EDITH SOSA

IPC: G01L5/00 ,  G01L1/12 ,  G01P15/08 ,  H01L21/02

Abstract: A tunable and resettable shock sensor using a parallel dipole line (PDL) trap system is provided. In one aspect, a shock sensor includes: a PDL trap having a pair of diametric magnets separated from one another by a gap gM, and a diamagnetic rod levitating in between the diametric magnets;and contact pads below the PDL trap, wherein the contact pads are separated from one another by a space that is less than a length l of the diamagnetic rod. A shock monitoring system is also provided that includes a network of the shock sensors, as is a method for shock monitoring using the shock sensors.

公开(公告)号：GB2596448A

公开(公告)日：2021-12-29

申请号：GB202113217

申请日：2020-03-13

Applicant: IBM

Inventor： WANG ZHOU ,  SHIYU CHANG ,  NORMA EDITH SOSA ,  EMRAH AKIN SISBOT

IPC: G06N3/08

Abstract: Methods and systems perform incremental learning object detection in images and/or videos without catastrophic forgetting of previously-learned object classes. A two-stage neural network object detector is trained to locate and identify objects pertaining to an additional object class by iteratively updating the two-stage neural network object detector until an overall detection accuracy criterion is met. The updating is performed so as to balance minimizing a loss of an initial ability to locate and identify objects pertaining to the previously-learned object classes and maximizing an ability to additionally locate and identify the objects pertaining to the additional object class. Assessing whether the overall detection accuracy criterion is met compares outputs of an initial version of the two- stage neural network object detector with a current region proposal output by a current version of the two-stage neural network object detector to determining a region proposal distillation loss and a previously-learned-object identification distillation loss.