公开(公告)号：US20200026999A1

公开(公告)日：2020-01-23

申请号：US16475076

申请日：2017-04-07

Applicant: INTEL CORPORATION

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

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

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：US11790223B2

公开(公告)日：2023-10-17

申请号：US16475076

申请日：2017-04-07

Applicant: INTEL CORPORATION

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

IPC: G06N3/08 ,  G06N3/063 ,  G06T1/20 ,  G06F18/21 ,  G06F18/214 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06F18/217 ,  G06F18/2148 ,  G06N3/045 ,  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：US11551335B2

公开(公告)日：2023-01-10

申请号：US16474848

申请日：2017-04-07

Applicant: Intel Corporation

Inventor： Lin Xu ,  Liu Yang ,  Anbang Yao ,  Dongqi Cai ,  Libin Wang ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yiwen Guo ,  Yurong Chen

IPC: G06T5/00 ,  G06N20/10 ,  G06F9/50 ,  G06N3/08 ,  G06N5/04 ,  H04N9/07 ,  H04N9/64

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.

公开(公告)号：US11341368B2

公开(公告)日：2022-05-24

申请号：US16475079

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Anbang Yao ,  Shandong Wang ,  Wenhua Cheng ,  Dongqi Cai ,  Libin Wang ,  Lin Xu ,  Ping Hu ,  Yiwen Guo ,  Liu Yang ,  Yuqing Hou ,  Zhou Su ,  Yurong Chen

IPC: G06K9/62 ,  G06N3/08 ,  G06T1/20 ,  G06V10/94

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：US11107189B2

公开(公告)日：2021-08-31

申请号：US16474927

申请日：2017-04-07

Applicant: INTEL CORPORATION

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

IPC: G06K9/00 ,  G06T3/40 ,  G06N20/20 ,  G06N20/10 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06N5/04 ,  G06T1/20

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：US20200026988A1

公开(公告)日：2020-01-23

申请号：US16475075

申请日：2017-04-07

Applicant: INTEL CORPORATION

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

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

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：US20200026965A1

公开(公告)日：2020-01-23

申请号：US16475078

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Yiwen GUO ,  Yuqing Hou ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shangong Wang ,  Wenhua Cheng ,  Yurong Chen ,  Libin Wag

IPC: G06K9/62 ,  G06K9/00 ,  G06N3/04 ,  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：US20200026499A1

公开(公告)日：2020-01-23

申请号：US16475080

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Yiwen Guo ,  Anbang Yao ,  Dongqi Cai ,  Libin Wang ,  Lin Xu ,  Ping Hu ,  Shangong Wang ,  Wenhua Cheng

IPC: G06F7/58 ,  G06N3/08 ,  G06N3/04

Abstract: Described herein are hardware acceleration of random number generation for machine learning and deep learning applications. An apparatus (700) includes a uniform random number generator (URNG) circuit (710) to generate uniform random numbers and an adder circuit (750) that is coupled to the URNG circuit (710). The adder circuit hardware (750) accelerates generation of Gaussian random numbers for machine learning.