公开(公告)号：US20200051309A1

公开(公告)日：2020-02-13

申请号：US16537140

申请日：2019-08-09

Applicant: Intel Corporation

Inventor： HUGUES LABBE ,  DARREL PALKE ,  SHERINE ABDELHAK ,  JILL BOYCE ,  VARGHESE GEORGE ,  SCOTT JANUS ,  ADAM LAKE ,  ZHIJUN LEI ,  ZHENGMIN LI ,  MIKE MACPHERSON ,  CARL MARSHALL ,  SELVAKUMAR PANNEER ,  PRASOONKUMAR SURTI ,  KARTHIK VEERAMANI ,  DEEPAK VEMBAR ,  VALLABHAJOSYULA SRINIVASA SOMAYAZULU

IPC: G06T15/00 ,  G06N3/08 ,  G06T1/20 ,  G06T1/60 ,  G06T15/40 ,  G06T17/20

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

公开(公告)号：US20220058853A1

公开(公告)日：2022-02-24

申请号：US17500631

申请日：2021-10-13

Applicant: Intel Corporation

Inventor： HUGUES LABBE ,  DARREL PALKE ,  SHERINE ABDELHAK ,  JILL BOYCE ,  VARGHESE GEORGE ,  SCOTT JANUS ,  ADAM LAKE ,  ZHIJUN LEI ,  ZHENGMIN LI ,  MIKE MACPHERSON ,  CARL MARSHALL ,  SELVAKUMAR PANNEER ,  PRASOONKUMAR SURTI ,  KARTHIK VEERAMANI ,  DEEPAK VEMBAR ,  VALLABHAJOSYULA SRINIVASA SOMAYAZULU

IPC: G06T15/00 ,  G06N3/08 ,  G06T17/20 ,  G06T1/60 ,  G06T15/40 ,  G06T1/20

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

公开(公告)号：US20180007433A1

公开(公告)日：2018-01-04

申请号：US15199424

申请日：2016-06-30

Applicant: Intel Corporation

Inventor： RAJNEESH CHOWDHURY ,  KARTHIK VEERAMANI

IPC: H04N21/454 ,  H04N21/41

CPC classification number: H04N21/454 ,  H04N21/4126 ,  H04N21/64322

Abstract: In embodiments, a streamed content filtering system (SCFS) may support filtering of content streamed from a content playing device (CPD) to a content display device (CDD). The CPD may include personal devices which may stream content to a CDD as well as play content on the CPD itself. The CPD may provide content-rating information (CRI) for content streamed to the CDD. The CPD and CDD may negotiate to determine that the CDD has content-filtering capabilities. The CRI may be retrieved by the CPD from the content itself or from a separate storage. Once the CRI is provided, the CDD may utilize a content filter (CF) to determine whether the content having the CRI is permitted. If not permitted, the CDD may prevent displaying of the content and/or may also display substitute content. Other embodiments may be described and/or claimed.

公开(公告)号：US20190041976A1

公开(公告)日：2019-02-07

申请号：US16144110

申请日：2018-09-27

Applicant: Intel Corporation

Inventor： KARTHIK VEERAMANI ,  OFER HAREUVENI ,  VIJAY SARATHI KESAVAN ,  RAJNEESH CHOWDHURY ,  GABRIEL ARROBO VIDAL

IPC: G06F3/01 ,  G06T19/00 ,  G02B27/01

Abstract: Wireless communication management methods and apparatuses for use with a virtual reality system are disclosed. A virtual reality subsystem, access point, and virtual reality devices are configured to interact with the access point to ensure that appropriate bandwidth is allocated and latency times are guaranteed between the virtual reality devices and a virtual reality application running on a host computer. The access point is configured with a virtual reality traffic handler to receive policies from the virtual reality subsystem, to ensure sufficient bandwidth and latency.

公开(公告)号：US20190006754A1

公开(公告)日：2019-01-03

申请号：US15639910

申请日：2017-06-30

Applicant: Intel Corporation

Inventor： Kim Pallister ,  KARTHIK VEERAMANI ,  VIJAY SARATHI KESAVAN

IPC: H01Q3/28 ,  H01Q3/24

Abstract: Methods, apparatus and systems for motion-predictive beamforming are disclosed. A method for motion predictive beamforming includes determining a time of a predicted transmission and determining a future position of a virtual reality (VR) receiving device at the time of the predicted transmission. Beamforming parameters are forwarded wireless system that correspond to the future position of the VR receiving device, the time of the predicted transmission, and an error correction margin to cause a transmission of a beam that is formed based on the future position of the VR receiving device, the time of the predicted transmission, and the error correction margin.

公开(公告)号：US20180277142A1

公开(公告)日：2018-09-27

申请号：US15467406

申请日：2017-03-23

Applicant: Intel Corporation

Inventor： KARTHIK VEERAMANI ,  RAJNEESH CHOWDHURY ,  MARK A. GRAY

IPC: G10L21/10 ,  G10L15/08 ,  G10L15/00 ,  G06F17/21 ,  G06F3/0481 ,  G10L21/028 ,  G06F17/28 ,  H04N21/488 ,  G10L15/26 ,  H04N21/439 ,  G10L17/00

CPC classification number: H04N21/4394 ,  G06F17/289 ,  G10L15/005 ,  G10L15/26 ,  G10L17/00 ,  G10L25/57 ,  G10L2015/088 ,  H04N21/42203 ,  H04N21/4884 ,  H04N21/84

Abstract: Apparatuses, methods and storage medium associated with real time closed captioning or highlighting are disclosed herein. In embodiments, an apparatus may include an audio interceptor to intercept an audio portion of an audio/video output stream of a multi-media application; a speech recognizer coupled to the audio interceptor to, in real time, process the audio portion of the audio/video stream, recognize speech within the audio portion, and automatically generate text corresponding to recognized speech, or keywords within the recognized speech; and a controller coupled to the audio interceptor and the speech recognizer, to control operations of the audio interceptor and the speech recognizer. The automatically generated text or keywords may be outputted as closed captions or highlights to complement video content of the audio/video stream. Other embodiments may be disclosed or claimed.

公开(公告)号：US20230360307A1

公开(公告)日：2023-11-09

申请号：US18310015

申请日：2023-05-01

Applicant: Intel Corporation

Inventor： HUGUES LABBE ,  DARREL PALKE ,  SHERINE ABDELHAK ,  JILL BOYCE ,  VARGHESE GEORGE ,  SCOTT JANUS ,  ADAM LAKE ,  ZHIJUN LEI ,  ZHENGMIN LI ,  MIKE MACPHERSON ,  CARL MARSHALL ,  SELVAKUMAR PANNEER ,  PRASOONKUMAR SURTI ,  KARTHIK VEERAMANI ,  DEEPAK VEMBAR ,  VALLABHAJOSYULA SRINIVASA SOMAYAZULU

IPC: G06T15/00 ,  G06N3/08 ,  G06T17/20 ,  G06T1/60 ,  G06T15/40 ,  G06T1/20

CPC classification number: G06T15/005 ,  G06N3/08 ,  G06T17/20 ,  G06T1/60 ,  G06T15/40 ,  G06T1/20

Abstract: One embodiment provides a graphics processor comprising a block of execution resources, a cache memory, a cache memory prefetcher, and circuitry including a programmable neural network unit, the programmable neural network unit comprising a network hardware block including circuitry to perform neural network operations and activation operations for a layer of a neural network, the programmable neural network unit addressable by cores within the block of graphics cores and the neural network hardware block configured to perform operations associated with a neural network configured to determine a prefetch pattern for the cache memory prefetcher.

公开(公告)号：US20180288458A1

公开(公告)日：2018-10-04

申请号：US15476283

申请日：2017-03-31

Applicant: Intel Corporation

Inventor： ABHIJEET KOLEKAR ,  INCHING CHEN ,  KARTHIK VEERAMANI

IPC: H04N21/2662 ,  H04W4/08 ,  H04W48/16 ,  H04W8/00 ,  H04N19/115 ,  H04N19/184 ,  H04N21/41 ,  H04N21/6373 ,  H04N21/442

CPC classification number: H04N21/2662 ,  H04N19/115 ,  H04N19/164 ,  H04N19/177 ,  H04N19/184 ,  H04N21/4122 ,  H04N21/43637 ,  H04N21/4402 ,  H04N21/44227 ,  H04N21/6373 ,  H04W4/08 ,  H04W8/005

Abstract: A method for adaptive video transmission based on channel capacity. As part of the method, a first wireless display capacity in a proximity of a wireless display source device is determined. The first wireless display capacity is based on information that is received from a wireless channel scan associated with a formation of a (P2P) peer-to-peer group that includes the wireless display source device and a wireless display. Further, the video bit rate of one or more devices with wireless display connections in the proximity is determined, the video bit rate of the one or more devices with wireless display connections in the proximity is compared to the wireless capacity, and, based on the comparing, a video bit rate of the wireless display source device is set. A second wireless display capacity in the proximity of the wireless display source device is determined based on a wireless channel scan of a wireless channel to determine wireless display connections in the proximity.

公开(公告)号：US20180183847A1

公开(公告)日：2018-06-28

申请号：US15392872

申请日：2016-12-28

Applicant: Intel Corporation

Inventor： RAJESH POORNACHANDRAN ,  RAJNEESH CHOWDHURY ,  KARTHIK VEERAMANI

IPC: H04L29/06 ,  H04L29/08

CPC classification number: H04L65/601 ,  H04L67/16 ,  H04L67/18 ,  H04L67/327 ,  H04L67/36

Abstract: Methods and apparatus for collaborative content rendering are disclosed. From a first device, the rendering capabilities of one or more devices that are within a proximity to the first device are determined, at least one of the one or more devices is identified that supports a delivery of first content that is not natively supported by the first device, and the delivery of the first content is initiated from the at least one of the one or more devices to the first device. The initiation of the delivery of the first content includes a negotiation of characteristics of content presentation and quality level of rendering capabilities. The first content that is received from the at least one of the one or more devices is rendered at the same time as second content that is natively supported by the first device.

公开(公告)号：US20170374276A1

公开(公告)日：2017-12-28

申请号：US15191058

申请日：2016-06-23

Applicant: Intel Corporation

Inventor： KARTHIK VEERAMANI ,  RAJNEESH CHOWDHURY

IPC: H04N5/232 ,  G02B27/01 ,  G06F3/01 ,  H04N7/18

CPC classification number: G02B27/017 ,  B64C39/024 ,  B64C2201/146 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0178 ,  G02B2027/0187 ,  G06F3/012 ,  G06F3/013 ,  G06F3/017 ,  G06F2203/0383 ,  H04N5/23203 ,  H04N5/232935 ,  H04N5/23296 ,  H04N7/185

Abstract: Apparatuses, methods, and storage media associated with generating control instructions to control a camera or a robot having the camera in continuously capturing and providing of a multimedia stream are disclosed herein. An apparatus comprises sensors to collect data on a user's physical response to the multimedia stream. Intermediate or derived data that describe the user's physical response, and one or more control instructions to control the camera or the robot are generated based on the collected data on the user's physical response, by a wearable device, a proximally disposed mobile device, or the robot itself. Another apparatus comprises a camera to capture and provide the multimedia stream, and a control module to process or generate instructions to control the camera or the robot. The apparatuses further comprise transmitters and receivers to transmit and/or receive the multimedia stream, the collected data, the intermediate or derived data, or the control instructions.