公开(公告)号：IL295821A

公开(公告)日：2022-10-01

申请号：IL29582122

申请日：2022-08-22

Applicant: IBM ,  UMAR ASIF ,  SUBHRAJIT ROY ,  JIANBIN TANG ,  STEFAN HARRER

Inventor： UMAR ASIF ,  SUBHRAJIT ROY ,  JIANBIN TANG ,  STEFAN HARRER

IPC: G06F16/23 ,  G06N20/00 ,  G06N20/10 ,  G06N20/20

Abstract: Aspects described herein include a method of generating three-dimensional (3D) spikes. The method comprises receiving a signal comprising time-series data and generating a first two-dimensional (2D) grid. Generating the first 2D grid comprises mapping segments of the time-series data to respective positions of the first 2D grid, and generating, for each position, a spike train corresponding to the respective mapped segment. The method further comprises generating a second 2D grid including performing, for each position, a mathematical operation on the spike train of the corresponding position of the first 2D grid. The method further comprises generating a third 2D grid including performing spatial filtering on the positions of the second 2D grid. The method further comprises generating a 3D grid based on a combination of the first 2D grid, the second 2D grid, and the third 2D grid. The 3D grid comprises one or more 3D spikes.

公开(公告)号：GB2616998B

公开(公告)日：2025-04-02

申请号：GB202309315

申请日：2021-10-19

Applicant: IBM

Inventor： UMAR ASIF ,  LENIN MEHEDY ,  JIANBIN TANG

IPC: H04N13/00 ,  G06T3/00

Abstract: A computer-implemented method of decoding video data in multiple resolution formats includes receiving an encoded video stream including a salient data and a non-salient data, the salient data having a higher resolution format than the non-salient data. The video stream is decoded into the non-salient data in a lower-resolution format and the salient data in the higher-resolution format. The non-salient data is reconstructed to a higher resolution format. The salient data and the reconstructed non-salient data are combined to form a video stream in the higher-resolution format of the salient data.

公开(公告)号：IL295821B1

公开(公告)日：2025-05-01

申请号：IL29582122

申请日：2022-08-22

Applicant: IBM CORP ,  UMAR ASIF ,  SUBHRAJIT ROY ,  JIANBIN TANG ,  STEFAN HARRER

Inventor： UMAR ASIF ,  SUBHRAJIT ROY ,  JIANBIN TANG ,  STEFAN HARRER

IPC: G06F16/23 ,  G06N20/00 ,  G06N20/10 ,  G06N20/20

Abstract: Aspects described herein include a method of generating three-dimensional (3D) spikes. The method comprises receiving a signal comprising time-series data and generating a first two-dimensional (2D) grid. Generating the first 2D grid comprises mapping segments of the time-series data to respective positions of the first 2D grid, and generating, for each position, a spike train corresponding to the respective mapped segment. The method further comprises generating a second 2D grid including performing, for each position, a mathematical operation on the spike train of the corresponding position of the first 2D grid. The method further comprises generating a third 2D grid including performing spatial filtering on the positions of the second 2D grid. The method further comprises generating a 3D grid based on a combination of the first 2D grid, the second 2D grid, and the third 2D grid. The 3D grid comprises one or more 3D spikes.

公开(公告)号：GB2609832A

公开(公告)日：2023-02-15

申请号：GB202216258

申请日：2021-03-19

Applicant: IBM

Inventor： UMAR ASIF ,  SUBHRAJIT ROY ,  JIANBIN TANG ,  STEFAN HARRER

IPC: G06Q50/02 ,  G06N7/00 ,  G06N7/01 ,  G06N20/00

Abstract: A method of generating three-dimensional (3D) spikes. The method comprising receiving a signal comprising time-series data and generating a first two- dimensional (2D) grid. Generating the first 2D grid comprises mapping segments of the time-series data to respective positions of the first 2D grid, and generating, for each position, a spike train corresponding to the respective mapped segment. The method further comprises generating a second 2D grid including performing, for each position, a mathematical operation on the spike train of the corresponding position of the first 2D grid. The method further comprises generating a third 2D grid including performing spatial filtering on the positions of the second 2D grid. The method further comprises generating a 3D grid based on a combination of the first 2D grid, the second 2D grid, and the third 2D grid. The 3D grid comprises one or more 3D spikes.

公开(公告)号：GB2603831A

公开(公告)日：2022-08-17

申请号：GB202113292

申请日：2021-09-17

Applicant: IBM

Inventor： UMAR ASIF ,  STEFAN VON CAVALLAR ,  JIANBIN TANG ,  STEFAN HARRER

IPC: G06N3/04 ,  G06N3/08

Abstract: A machine learning model can be optimized for deployment on a device based on hardware specifications of the device. An existing model is acquired and pruned to reduce hardware resource consumption of the model. The pruned model is then trained based on training data. The pruned model is also trained based on a collection of “teacher” models. Performance of the trained model is then evaluated and compared to performance requirements, which can be based on the hardware specifications of a device.