-
公开(公告)号：US20210350215A1
公开(公告)日：2021-11-11
申请号：US17323694
申请日：2021-05-18
申请人： Intel Corporation
发明人： Brian T. Lewis , Rajkishore Barik , Murali Sundaresan , Leonard Truong , Feng Chen , Xiaoming Chen , Mike B. MacPherson
摘要： A mechanism is described for facilitating efficient training of neural networks at computing devices. A method of embodiments, as described herein, includes detecting one or more inputs for training of a neural network, and introducing randomness in floating point (FP) numbers to prevent overtraining of the neural network, where introducing randomness includes replacing less-significant low-order bits of operand and result values with new low-order bits during the training of the neural network.
-
公开(公告)号：US20200019844A1
公开(公告)日：2020-01-16
申请号：US16518828
申请日：2019-07-22
申请人： Intel Corporation
发明人： Brian T. Lewis , Feng Chen , Jeffrey R. Jackson , Justin E. Gottschlich , Rajkishore Barik , Xiaoming Chen , Prasoonkumar Surti , Mike B. Macpherson , Murali Sundaresan
IPC分类号： G06N3/063 , B60W30/095 , G06N3/00 , G06N3/04
摘要： A mechanism is described for facilitating smart collection of data and smart management of autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and combining a first computation directed to be performed locally at a local computing device with a second computation directed to be performed remotely at a remote computing device in communication with the local computing device over the one or more networks, where the first computation consumes low power, wherein the second computation consumes high power.
-
公开(公告)号：US12001944B2
公开(公告)日：2024-06-04
申请号：US17874876
申请日：2022-07-27
申请人： Intel Corporation
发明人： Rajkishore Barik , Brian T. Lewis , Murali Sundaresan , Jeffrey Jackson , Feng Chen , Xiaoming Chen , Mike Macpherson
摘要： A mechanism is described for facilitating smart distribution of resources for deep learning autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and introducing a library to a neural network application to determine an optimal point at which to apply frequency scaling without degrading performance of the neural network application at a computing device.
-
公开(公告)号：US20180314936A1
公开(公告)日：2018-11-01
申请号：US15581152
申请日：2017-04-28
申请人： Intel Corporation
发明人： Rajkishore Barik , Brian T. Lewis , Murali Sundaresan , Jeffrey Jackson , Feng Chen , Xiaoming Chen , Mike Macpherson
摘要： A mechanism is described for facilitating smart distribution of resources for deep learning autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and introducing a library to a neural network application to determine optimal point at which to apply frequency scaling without degrading performance of the neural network application at a computing device.
-
公开(公告)号：US20230017304A1
公开(公告)日：2023-01-19
申请号：US17874876
申请日：2022-07-27
申请人： Intel Corporation
发明人： Rajkishore Barik , Brian T. Lewis , Murali Sundaresan , Jeffrey Jackson , Feng Chen , Xiaoming Chen , Mike Macpherson
摘要： A mechanism is described for facilitating smart distribution of resources for deep learning autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and introducing a library to a neural network application to determine optimal point at which to apply frequency scaling without degrading performance of the neural network application at a computing device.
-
公开(公告)号：US11488005B2
公开(公告)日：2022-11-01
申请号：US16518828
申请日：2019-07-22
申请人： Intel Corporation
发明人： Brian T. Lewis , Feng Chen , Jeffrey R. Jackson , Justin E. Gottschlich , Rajkishore Barik , Xiaoming Chen , Prasoonkumar Surti , Mike B. Macpherson , Murali Sundaresan
摘要： A mechanism is described for facilitating smart collection of data and smart management of autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and combining a first computation directed to be performed locally at a local computing device with a second computation directed to be performed remotely at a remote computing device in communication with the local computing device over the one or more networks, where the first computation consumes low power, wherein the second computation consumes high power.
-
公开(公告)号：US11017291B2
公开(公告)日：2021-05-25
申请号：US15581031
申请日：2017-04-28
申请人： Intel Corporation
发明人： Brian T. Lewis , Rajkishore Barik , Murali Sundaresan , Leonard Truong , Feng Chen , Xiaoming Chen , Mike B. Macpherson
摘要： A mechanism is described for facilitating efficient training of neural networks at computing devices. A method of embodiments, as described herein, includes detecting one or more inputs for training of a neural network, and introducing randomness in floating point (FP) numbers to prevent overtraining of the neural network, where introducing randomness includes replacing less-significant low-order bits of operand and result values with new low-order bits during the training of the neural network.
-
公开(公告)号：US10410115B2
公开(公告)日：2019-09-10
申请号：US15581133
申请日：2017-04-28
申请人： Intel Corporation
发明人： Brian T. Lewis , Feng Chen , Jeffrey R. Jackson , Justin E. Gottschlich , Rajkishore Barik , Xiaoming Chen , Prasoonkumar Surti , Mike B. Macpherson , Murali Sundaresan
摘要： A mechanism is described for facilitating smart collection of data and smart management of autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and combining a first computation directed to be performed locally at a local computing device with a second computation directed to be performed remotely at a remote computing device in communication with the local computing device over the one or more networks, where the first computation consumes low power, wherein the second computation consumes high power.
-
公开(公告)号：US20180314935A1
公开(公告)日：2018-11-01
申请号：US15581031
申请日：2017-04-28
申请人： Intel Corporation
摘要： A mechanism is described for facilitating efficient training of neural networks at computing devices. A method of embodiments, as described herein, includes detecting one or more inputs for training of a neural network, and introducing randomness in floating point (FP) numbers to prevent overtraining of the neural network, where introducing randomness includes replacing less-significant low-order bits of operand and result values with new low-order bits during the training of the neural network.
-
公开(公告)号：US20180300845A1
公开(公告)日：2018-10-18
申请号：US15488547
申请日：2017-04-17
申请人： Intel Corporation
发明人： Adam T. Lake , Guei-Yuan Lueh , Balaji Vembu , Murali Ramadoss , Prasoonkumar Surti , Abhishek R. Appu , Altug Koker , Subramaniam M. Maiyuran , Eric C. Samson , David J. Cowperthwaite , Zhi Wang , Kun Tian , David Puffer , Brian T. Lewis
摘要： An apparatus to facilitate data prefetching is disclosed. The apparatus includes a memory, one or more execution units (EUs) to execute a plurality of processing threads and prefetch logic to prefetch pages of data from the memory to assist in the execution of the plurality of processing threads.
-
-
-
-
-
-
-
-
-
搜索结果
26 条记录 (耗时 0.026 秒)
