-
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
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：GB2588523A
公开(公告)日：2021-04-28
申请号：GB202017338
申请日：2019-03-28
Applicant: IBM
Inventor： BENJAMIN SCOTT MASHFORD , FILIZ ISABELL KIRAL-KORNEK , ROY SUBHRAJIT , JIANBIN TANG , STEFAN HARRER
Abstract: One or both of epilepsy seizure detection and prediction at least by performing the following: running multiple input signals from sensors for epilepsy seizure detection through multiple classification models, and applying weights to outputs of each of the classification models to create a final classification output. The weights are adjusted to tune relative output contribution from each classifier model in order that accuracy of the final classification output is improved, while power consumption of all the classification models is reduced. One or both of epilepsy seizure detection and prediction are performed with the adjusted weights. Another method uses streams from sensors for epilepsy seizure detection to train and create the classification models, with fixed weights once trained. Information defining the classification models with fixed weights is communicated to wearable computer platforms for epilepsy seizure detection and prediction. The streams maybe from multiple people and applied to an individual person.
-
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
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：GB2548194A
公开(公告)日：2017-09-13
申请号：GB201700228
申请日：2017-01-06
Applicant: IBM
Inventor： AMON AMIR , ANTONIO JOSE JIMENO YEPES , JIANBIN TANG
Abstract: Weighted population code for efficient data representation in neuromorphic systems. Input value is represented by spikes on axons, each of which has an associated weight. Weighted spikes are integrated/added, which may be over over multiple ticks, to give the input value. Requires less hardware for greater dynamic range compared to prior art. Can be converted to stochastic code by dividing value by size of dynamic range. Also disclosed is stochastic code corelet 206 on neuromorphic chip 205. Pre-processor 202 encodes input data to weighted population code for transfer onto neuromorphic chip, and corelet translates input to stochastic code for use by classifiers also on chip. This reduces the input bandwidth of the chip. Also disclosed is delaying sending of spikes to a neuron during a preload period. The spikes then affect the neuron during a subsequent setup period, before the neuron produces output. This means that input can be sent while the neuron is still producing the previous output, which reduces setup time and shortens processing cycle.
-
Patent Agency Ranking
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
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
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
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.
-
公开(公告)号：GB2588523B
公开(公告)日：2022-03-09
申请号：GB202017338
申请日：2019-03-28
Applicant: IBM
Inventor： BENJAMIN SCOTT MASHFORD , FILIZ ISABELL KIRAL-KORNEK , ROY SUBHRAJIT , JIANBIN TANG , STEFAN HARRER
Abstract: One or both of epilepsy seizure detection and prediction at least by performing the following: running multiple input signals from sensors for epilepsy seizure detection through multiple classification models, and applying weights to outputs of each of the classification models to create a final classification output. The weights are adjusted to tune relative output contribution from each classifier model in order that accuracy of the final classification output is improved, while power consumption of all the classification models is reduced. One or both of epilepsy seizure detection and prediction are performed with the adjusted weights. Another method uses streams from sensors for epilepsy seizure detection to train and create the classification models, with fixed weights once trained. Information defining the classification models with fixed weights is communicated to wearable computer platforms for epilepsy seizure detection and prediction. The streams may be from multiple people and applied to an individual person.
-
公开(公告)号：GB2548194B
公开(公告)日：2020-02-26
申请号：GB201700228
申请日：2017-01-06
Applicant: IBM
Inventor： ARNON AMIR , ANTONIO JOSE JIMENO YEPES , JIANBIN TANG
Abstract: Weighted population code in neuromorphic systems is provided. According to an embodiment, a plurality of input values is received. For each of the plurality of values, a plurality of spikes is generated. Each of the plurality of spikes has an associated weight. A consumption time is determined for each of the plurality of spikes. Each of the plurality of spikes is sent for consumption at its consumption time.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.016 seconds)
