公开(公告)号：WO2018184222A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079771

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

Inventor： GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

IPC: G06N3/02 ,  G06N3/04 ,  G06N3/08

Abstract: 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. For each L layer in the plurality of layers, the nodes of each L layer are randomly connected to nodes in a L+1 layer. For each L+1 layer in the plurality of layers, 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, and L is an integer starting with 1. In another example, a deep neural network includes an input layer, output layer, and a plurality of hidden layers. Inputs for the input layer and labels for the output layer are determined related to a first sample. Similarity between different pairs of inputs and labels between a second sample with the first sample is estimated using Gaussian regression process.

公开(公告)号：WO2018184204A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079719

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  GUO, Yiwen ,  HOU, Yuqing ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

Inventor： GUO, Yiwen ,  HOU, Yuqing ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

IPC: G06K9/66 ,  G06N3/08

Abstract: 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.

公开(公告)号：WO2018176186A1

公开(公告)日：2018-10-04

申请号：PCT/CN2017/078256

申请日：2017-03-27

Applicant: INTEL CORPORATION ,  WANG, Libin ,  YAO, Anbang ,  LI, Jianguo ,  CHEN, Yurong

Inventor： WANG, Libin ,  YAO, Anbang ,  LI, Jianguo ,  CHEN, Yurong

IPC: H04N19/169

CPC classification number: G06K9/4628 ,  G06K9/00684 ,  G06K9/6274

Abstract: An example apparatus for semantic image segmentation includes a receiver to receive an image to be segmented. The apparatus also includes a gated dense pyramid network comprising a plurality of gated dense pyramid (GDP) blocks to be trained to generate semantic labels for each pixel in the received image. The apparatus further includes a generator to generate a segmented image based on the generated semantic labels.

公开(公告)号：WO2018035805A1

公开(公告)日：2018-03-01

申请号：PCT/CN2016/096707

申请日：2016-08-25

Applicant: INTEL CORPORATION ,  WANG, Libin ,  YAO, Anbang ,  CHEN, Yurong

Inventor： WANG, Libin ,  YAO, Anbang ,  CHEN, Yurong

IPC: G06K9/62

CPC classification number: G06T7/10 ,  G06F16/55 ,  G06K9/00973 ,  G06K9/34 ,  G06K9/4628 ,  G06N3/0454 ,  G06N3/08 ,  G06N5/046 ,  G06T7/11 ,  G06T7/143 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20016 ,  G06T2207/20081

Abstract: Techniques related to implementing fully convolutional networks for semantic image segmentation are discussed. Such techniques may include combining feature maps from multiple stages of a multi-stage fully convolutional network to generate a hyper-feature corresponding to an input image, up-sampling the hyper-feature and summing it with a feature map of a previous stage to provide a final set of features, and classifying the final set of features to provide semantic image segmentation of the input image.

Abstract translation: 讨论了与实现用于语义图像分割的完全卷积网络有关的技术。 这样的技术可以包括组合来自多级完全卷积网络的多个阶段的特征映射以生成对应于输入图像的超特征，对超特征进行上采样并且将其与前级的特征映射进行求和以提供 最后一组特征，并对最后一组特征进行分类，以提供输入图像的语义图像分割。

公开(公告)号：WO2018184224A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079774

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  WANG, Libin ,  GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

Inventor： WANG, Libin ,  GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

IPC: G06F9/30

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/063 ,  G06T1/20

Abstract: 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.

公开(公告)号：WO2018184194A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079682

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  WANG, Shandong ,  GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  CHENG, Wenhua ,  CHEN, Yurong

Inventor： WANG, Shandong ,  GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  CHENG, Wenhua ,  CHEN, Yurong

IPC: G06K9/00

Abstract: Methods and systems are disclosed using improved Convolutional Neural Networks (CNN) for image processing. In one example, an input image is down-sampled into smaller images with a smaller resolution than the input image. The down-sampled smaller images are processed by a CNN having a last layer with a reduced number of nodes than a last layer of a full CNN used to process the input image at a full resolution. A result is outputted based on the processed down-sampled smaller images by the CNN having a last layer with a reduced number of nodes. In another example, shallow CNN networks are built randomly. The randomly built shallow CNN networks are combined to imitate a trained deep neural network (DNN).

公开(公告)号：WO2018184187A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079663

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  WANG, Shandong ,  CHENG, Wenhua ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  GUO, Yiwen ,  YANG, Liu ,  HOU, Yuqing ,  SU, Zhou ,  CHEN, Yurong

Inventor： YAO, Anbang ,  WANG, Shandong ,  CHENG, Wenhua ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  GUO, Yiwen ,  YANG, Liu ,  HOU, Yuqing ,  SU, Zhou ,  CHEN, Yurong

IPC: G06K9/66

Abstract: Methods and systems for advanced and augmented training of deep neural networks (DNNs) using synthetic data and innovative generative networks. A method includes training a DNN using synthetic data, training a plurality of DNNs using context data, associating features of the DNNs trained using context data with features of the DNN trained with synthetic data, and generating an augmented DNN using the associated features.

公开(公告)号：WO2019090506A1

公开(公告)日：2019-05-16

申请号：PCT/CN2017/109885

申请日：2017-11-08

Applicant: INTEL CORPORATION ,  CHENG, Wenhua ,  YAO, Anbang ,  WANG, Libin ,  CAI, Dongqi ,  LI, Jianguo ,  CHEN, Yurong

Inventor： CHENG, Wenhua ,  YAO, Anbang ,  WANG, Libin ,  CAI, Dongqi ,  LI, Jianguo ,  CHEN, Yurong

IPC: G06K9/20 ,  G06K9/72

CPC classification number: G06K9/325 ,  G06K9/6267 ,  G06K9/72

Abstract: A semiconductor package apparatus (20), comprising: one or more substrates (21); and logic (22) coupled to the one or more substrates (21), the logic (22) coupled to the one or more substrates (21) to: apply a trained scene text detection network to an image to identify a core text region, a supportive text region (31), and a background region of the image, and detect text in the image based on the identified core text region and supportive text region (32).

公开(公告)号：WO2018184214A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079749

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  GUO, Yiwen ,  YANG, Liu ,  CHEN, Yurong ,  HOU, Yuqing ,  SU, Zhou

Inventor： YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  GUO, Yiwen ,  YANG, Liu ,  CHEN, Yurong ,  HOU, Yuqing ,  SU, Zhou

IPC: G06N3/00 ,  G06T7/00

Abstract: Described herein are systems and methods for providing deeply stacked automated program synthesis. In one embodiment, an apparatus to perform automated program synthesis includes a memory to store instructions for automated program synthesis and a compute cluster coupled to the memory. The compute cluster supports the instructions for performing the automated program synthesis including partitioning sketched data into partitions, training diverse sets of individual program synthesis units each having different capabilities with partitioned sketched data and for each partition applying respective transformations, and generating sketched baseline data for each individual program synthesis unit.

公开(公告)号：WO2018184192A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079677

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  XU, Lin ,  YANG, Liu ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  GUO, Yiwen ,  CHEN, Yurong

Inventor： XU, Lin ,  YANG, Liu ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  GUO, Yiwen ,  CHEN, Yurong

IPC: H04N7/18

Abstract: Methods and systems are disclosed using camera devices for deep channel and Convolutional Neural Network (CNN) images and formats. In one example, image values are captured by a color sensor array in an image capturing device or camera. The image values provide color channel data. The captured image values by the color sensor array are input to a CNN having at least one CNN layer. The CNN provides CNN channel data for each layer. The color channel data and CNN channel data is to form a deep channel image that stored in a memory. In another example, image values are captured by sensor array. The captured image values by the sensor array are input a CNN having a first CNN layer. An output is generated at the first CNN layer using the captured image values by the color sensor array. The output of the first CNN layer is stored as a feature map of the captured image.