Intel Corporation

Sony Corporation

Thales Dis Cpl Usa, Inc.

Hao Zhao

Anbang Yao

Yurong Chen

Ming Lu

Yiwen Guo

Tao Kong

Yun Ren

Jing Min Xu

Hu Tiger Chen

Kan Liu

Junjie Cai

YuBao Cheng

Aojun Zhou

Kuan Wang

An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

Joint training of neural networks using multi-scale hard example mining

Methods, apparatus, systems and articles of manufacture for loss-error-aware quantization of a low-bit neural network are disclosed. An example apparatus includes a network weight partitioner to partition unquantized network weights of a first network model into a first group to be quantized and a second group to be retrained. The example apparatus includes a loss calculator to process network weights to calculate a first loss. The example apparatus includes a weight quantizer to quantize the first group of network weights to generate low-bit second network weights. In the example apparatus, the loss calculator is to determine a difference between the first loss and a second loss. The example apparatus includes a weight updater to update the second group of network weights based on the difference. The example apparatus includes a network model deployer to deploy a low-bit network model including the low-bit second network weights.

Loss-error-aware quantization of a low-bit neural network

Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

Methods and apparatus for discriminative semantic transfer and physics-inspired optimization of features in deep learning

Methods and apparatus are disclosed for enhancing a binary weight neural network using a dependency tree. A method of enhancing a convolutional neural network (CNN) having binary weights includes constructing a tree for obtained binary tensors, the tree having a plurality of nodes beginning with a root node in each layer of the CNN. A convolution is calculated of an input feature map with an input binary tensor at the root node of the tree. A next node is searched from the root node of the tree and a convolution is calculated at the next node using a previous convolution result calculated at the root node of the tree. The searching of a next node from root node is repeated for all nodes from the root node of the tree, and a convolution is calculated at each next node using a previous convolution result.

Methods and apparatus for enhancing a binary weight neural network using a dependency tree

Methods and apparatus are disclosed for enhancing a neural network using binary tensor and scale factor pairs. For one example, a method of optimizing a trained convolutional neural network (CNN) includes initializing an approximation residue as a trained weight tensor for the trained CNN. A plurality of binary tensors and scale factor pairs are determined. The approximation residue is updated using the binary tensors and scale factor pairs.

Methods and apparatus for enhancing a neural network using binary tensor and scale factor pairs

The invention is a method for controlling execution of an application. The method comprising:

Method for controlling execution of an application

Joint training of neural networks using multi scale hard example mining

This application discloses a method for prolonging sleeping time of CPU. After CPU enters sleeping state, interrupt controller delays reporting deferrable external interrupts to the CPU, with the delay time set or as default. This application also provides a device corresponding to the method. This application can prolong the sleeping time of CPU in all kinds of intelligent electronic devices, and make the CPU enter a deep sleeping mode, thereby reducing power consumption substantially without affecting system performance.

Growing community of inventors

Beijing, China

Hao Zhao