Intel Corporation

Midea Group Co., Ltd.

China Agricultural University

Seetatech (beijing) Technology Co., Ltd.

Zhuang Liu

Jianguo Li

Shoumeng Yan

Ning Yang

Junyang Zhou

Xiujuan Chai

Congjiao Sun

Shiguang Shan

Guiqin Wu

Xilin Chen

Zixuan Yang

Dahai Yu

Yiyuan Yan

Provided are an egg-type chicken whole-genome SNP chip and the use thereof. The SNP loci of the chip are respectively derived from 14,624 SNP loci shared by each line of the major egg-type chickens in China; 3,677 SNP loci associated with disease-resistant traits in egg-type chickens; 16,000 SNP loci associated with economic traits in egg-type chickens; and 9,358 SNP loci making up genomic regions not covered by the foregoing probes. The 43,681 SNPs on the egg-type chicken whole-genome SNP chip have DNA sequences as represented by SEQ ID NO. 1-43,681. The chip can specifically identify the genetic relationship between commercial egg-type chickens and egg-type chickens of local breeds, and can also perform applications such as whole-genome association analysis, genome selective breeding, and QTL location analysis of target traits and population genetic analysis.

Egg-type chicken whole-genome SNP chip and use thereof

A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method of embodiments, as described herein, includes learning a first neural network associated with machine learning processes to be performed by a processor of a computing device, where learning includes analyzing a plurality of channels associated with one or more layers of the first neural network. The method may further include computing a plurality of scaling factors to be associated with the plurality of channels such that each channel is assigned a scaling factor, wherein each scaling factor to indicate relevance of a corresponding channel within the first neural network. The method may further include pruning the first neural network into a second neural network by removing one or more channels of the plurality of channels having low relevance as indicated by one or more scaling factors of the plurality of scaling factors assigned to the one or more channels.

Slimming of neural networks in machine learning environments

Embodiments provide a process to identify one or more areas containing a hand or hands of one or more subjects in an image. The detection process can start with coarsely locating one or more segments in the image that contain portions of the hand(s) of the subject(s) in the image using a coarse CNN. The detection process can then combine these segments to obtain the one or more areas capturing the hand(s) of the subject(s) in the image. The combined area(s) can then be fed to a grid-based deep neural network finely detect area(s) in the image that contain only the hand(s) of the subject(s) captured.

Coarse-to-fine hand detection method using deep neural network

Growing community of inventors

Beijing, China

Zhuang Liu