利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

20 条记录 (耗时 0.03 秒)

    Methods and systems using improved training and learning for deep neural networks
    2.
    发明授权
    Methods and systems using improved training and learning for deep neural networks 有权

    公开(公告)号：US11537851B2

    公开(公告)日：2022-12-27

    申请号：US16475075

    申请日：2017-04-07

    申请人： INTEL CORPORATION

    发明人： Yiwen Guo ,  Anbang Yao ,  Dongqi Cai ,  Libin Wang ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen

    IPC分类号： G06N3/04 ,  G06K9/62 ,  G06F17/18 ,  G06T1/20

    摘要： Methods and systems are disclosed using improved training and learning for deep neural networks. In one example, a deep neural network includes a plurality of layers, and each layer has a plurality of nodes. The nodes of each L layer in the plurality of layers are randomly connected to nodes of an L+1 layer. The nodes of each L+1 layer are connected to nodes in a subsequent L layer in a one-to-one manner. Parameters related to the nodes of each L layer are fixed. Parameters related to the nodes of each L+1 layers are updated. In another example, inputs for the input layer and labels for the output layer of a deep neural network are determined related to a first sample. A similarity between different pairs of inputs and labels is estimated using a Gaussian regression process.

    METHODS AND SYSTEMS FOR BUDGETED AND SIMPLIFIED TRAINING OF DEEP NEURAL NETWORKS
    3.
    发明申请
    METHODS AND SYSTEMS FOR BUDGETED AND SIMPLIFIED TRAINING OF DEEP NEURAL NETWORKS 有权

    公开(公告)号：US20220222492A1

    公开(公告)日：2022-07-14

    申请号：US17584216

    申请日：2022-01-25

    申请人： Intel Corporation

    发明人： Yiwen GUO ,  Yuqing Hou ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen ,  Libin Wang

    IPC分类号： G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V10/94

    摘要： Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM.

    Methods and systems for budgeted and simplified training of deep neural networks
    4.
    发明授权
    Methods and systems for budgeted and simplified training of deep neural networks 有权

    公开(公告)号：US11263490B2

    公开(公告)日：2022-03-01

    申请号：US16475078

    申请日：2017-04-07

    申请人： INTEL CORPORATION

    发明人： Yiwen Guo ,  Yuqing Hou ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen ,  Libin Wang

    IPC分类号： G06K9/62 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08

    摘要： Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM.

    Skin map-aided skin smoothing of images using a bilateral filter
    5.
    发明授权
    Skin map-aided skin smoothing of images using a bilateral filter 有权

    公开(公告)号：US11176641B2

    公开(公告)日：2021-11-16

    申请号：US16079308

    申请日：2016-03-24

    申请人： INTEL CORPORATION

    发明人： Liu Yang ,  Weike Chen ,  Lin Xu

    IPC分类号： G06T5/00 ,  G06T5/20

    摘要： Skin smoothing is applied to images using a bilateral filter and aided by a skin map. In one example a method includes receiving an image having pixels at an original resolution. The image is buffered. The image is downscaled from the original resolution to a lower resolution. A bilateral filter is applied to pixels of the downscaled image. The filtered pixels of the downscaled image are blended with pixels of the image having the original resolution, and the blended image is produced.

    METHODS AND SYSTEMS FOR BOOSTING DEEP NEURAL NETWORKS FOR DEEP LEARNING
    8.
    发明申请
    METHODS AND SYSTEMS FOR BOOSTING DEEP NEURAL NETWORKS FOR DEEP LEARNING 审中-公开

    公开(公告)号：US20200026999A1

    公开(公告)日：2020-01-23

    申请号：US16475076

    申请日：2017-04-07

    申请人： INTEL CORPORATION

    发明人： Libin Wang ,  Yiwen Guo ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shangong Wang ,  Wenhua Cheng ,  Yurong Chen

    IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N3/063 ,  G06T1/20 ,  G06K9/62

    摘要： Methods and systems are disclosed for boosting deep neural networks for deep learning. In one example, in a deep neural network including a first shallow network and a second shallow network, a first training sample is processed by the first shallow network using equal weights. A loss for the first shallow network is determined based on the processed training sample using equal weights. Weights for the second shallow network are adjusted based on the determined loss for the first shallow network. A second training sample is processed by the second shallow network using the adjusted weights. In another example, in a deep neural network including a first weak network and a second weak network, a first subset of training samples is processed by the first weak network using initialized weights. A classification error for the first weak network on the first subset of training samples is determined. The second weak network is boosted using the determined classification error of the first weak network with adjusted weights. A second subset of training samples is processed by the second weak network using the adjusted weights.

    METHOD, APPARATUS AND SYSTEM OF VIDEO AND AUDIO SHARING AMONG COMMUNICATION DEVICES
    9.
    发明申请
    METHOD, APPARATUS AND SYSTEM OF VIDEO AND AUDIO SHARING AMONG COMMUNICATION DEVICES 审中-公开
    通信设备中视频和音频共享的方法，装置和系统

    公开(公告)号：US20150281309A1

    公开(公告)日：2015-10-01

    申请号：US14128996

    申请日：2012-12-10

    申请人： INTEL CORPORATION

    发明人： Qiang Li ,  Yangzhou Du ,  Wenlong Li ,  Xiaofeng Tong ,  Wei Hu ,  Lin Xu ,  Yimin Zhang

    IPC分类号： H04L29/06 ,  G10L19/04

    CPC分类号： H04L65/607 ,  G10L19/04 ,  H04N21/235 ,  H04N21/2368 ,  H04N21/242 ,  H04N21/4307 ,  H04N21/4341 ,  H04N21/435

    摘要： A device, method and system of video and audio sharing among communication devices, may comprise a communication device for generating and sending a packet containing information related to the video and audio, and another communication device for receiving the packet and rendering the information related to the audio and video. In some embodiments, the communication device may comprise: an audio encoding module to encode a piece of audio into an audio bit stream; an avatar data extraction module to extract avatar data from a piece of video and generate an avatar data bit stream; and a synchronization module to generate synchronization information for synchronizing the audio bit stream with the avatar parameter stream. In some embodiments, the another communication device may comprise: an audio decoding module to decode an audio bit stream into decoded audio data; an Avatar animation module to animate an Avatar model based on an Avatar data bit stream to generate an animated Avatar model; and a synchronizing and rendering module to synchronize and render the decoded audio data and the animated Avatar model by utilizing the synchronization information.

    摘要翻译： 在通信设备之间的视频和音频共享的设备，方法和系统可以包括用于生成和发送包含与视频和音频相关的信息的分组的通信设备，以及用于接收分组并呈现与 音频和视频。 在一些实施例中，通信设备可以包括：音频编码模块，用于将音频片段编码成音频比特流; 一个头像数据提取模块，用于从一条视频中提取头像数据，并生成化身数据比特流; 以及同步模块，用于生成用于使音频比特流与化身参数流同步的同步信息。 在一些实施例中，另一通信设备可以包括：音频解码模块，用于将音频比特流解码为解码的音频数据; Avatar动画模块，用于基于Avatar数据位流为Avatar模型生成动画Avatar模型; 以及同步和渲染模块，通过利用同步信息来同步和渲染解码的音频数据和动画化身模型。