-
公开(公告)号：US20180004735A1
公开(公告)日：2018-01-04
申请号：US15199248
申请日：2016-06-30
Applicant: Intel Corporation
Inventor： Sudhir K. Singh , Abhishek Narain , Jose M. Rodriguez , Prasad Modali
IPC: G06F17/30
CPC classification number: G06F16/435 , G06F16/285
Abstract: A method of emotive autography includes calculating a plurality of classifiers associated with an individual user. Each of the classifiers indicates a preference of the user for an associated type of multimedia content. Multimedia data is received including video data, audio data and/or image data. The multimedia data is divided into semantically similar segments. A respective preference score is assigned to each of the semantically similar segments by use of the classifiers. The semantically similar segments are arranged in a sequential order dependent upon the preference scores. An emotive autograph is presented based on the semantically similar segments arranged in the sequential order.
-
公开(公告)号：US11263526B2
公开(公告)日：2022-03-01
申请号：US16613349
申请日：2018-05-31
Applicant: Intel Corporation
Abstract: A deep neural network (DNN) includes hidden layers arranged along a forward propagation path between an input layer and an output layer. The input layer accepts training data comprising quaternion values, outputs a quaternion-valued signal along the forward path to at least one of the hidden layers. At least some of the hidden layers include quaternion layers to execute consistent quaternion (QT) forward operations based on one or more variable parameters. A loss function engine produces a loss function representing an error between the DNN result and an expected result. QT backpropagation-based training operations include computing layer-wise QT partial derivatives, consistent with an orthogonal basis of quaternion space, of the loss function with respect to a QT conjugate of the one or more variable parameters and of respective inputs to the quaternion layers.
-
公开(公告)号：US11593643B2
公开(公告)日：2023-02-28
申请号：US16613365
申请日：2018-05-31
Applicant: Intel Corporation
Abstract: A quaternion deep neural network (QTDNN) includes a plurality of modular hidden layers, each comprising a set of QT computation sublayers, including a quaternion (QT) general matrix multiplication sublayer, a QT non-linear activations sublayer, and a QT sampling sublayer arranged along a forward signal propagation path. Each QT computation sublayer of the set has a plurality of QT computation engines. In each modular hidden layer, a steering sublayer precedes each of the QT computation sublayers along the forward signal propagation path. The steering sublayer directs a forward-propagating quaternion-valued signal to a selected at least one QT computation engine of a next QT computation subsequent sublayer.
-
公开(公告)号：US11521060B2
公开(公告)日：2022-12-06
申请号：US16613380
申请日：2018-05-31
Applicant: Intel Corporation
Abstract: A machine-learning system includes a quaternion (QT) computation engine. Input data to the QT computation engine includes quaternion values, each comprising a real component and three imaginary components, represented as a set of real-valued tensors. A single quaternion value is represented as a 1-dimensional real-valued tensor having four real-valued components, wherein a first real-valued component represents the real component of the single quaternion value, and wherein a second, a third, and a fourth real-valued component each respectively represents one of the imaginary components. A quaternion-valued vector having a size N is represented as a 2-dimensional real-valued tensor comprising N 1-dimensional real-valued tensors. A quaternion-valued matrix having N×M dimensions is represented as a 3-dimensional real-valued tensor comprising M 2-dimensional real-valued tensors comprising N 1-dimensional real-valued tensors.
-
-
-
Search Results
4
records
(took 0.011 seconds)
