Intel Corporation

Inventec Appliances Corporation

Dian Gu

Yu Zhang

Anbang Yao

Yurong Chen

Xiao Zhou

David Ho

Guangli Zhang

Dawei Sun

Chih-Chung Hung

Jiahui Zhang

Techniques related to poly-scale kernel-wise convolutional neural network layers are discussed. A poly-scale kernel-wise convolutional neural network layer is applied to an input volume to generate an output volume and include filters each having a number of filter kernels with the same sample rate and differing dilation rates optionally in a repeating pattern of dilation rate groups within each of filters with the pattern of dilation rate groups offset between the filters the poly-scale kernel-wise convolutional neural network layer.

Poly-scale kernel-wise convolution for high-performance visual recognition applications

The present invention is to provide a combination antenna having multi-mode and multi-band arrangements, which comprises a conductive seat; a non-uniform helical antenna extending from one end of the conductive seat; and a pole antenna extending from one end of the conductive seat through the helical antenna, enabling to be tuned to three or more resonant frequencies through tuning the helical antenna to a plurality of resonant frequencies and tuning the pole antenna to a plurality of resonant frequencies different from that to which the helical antenna is tuned.

Multi-mode antenna and multi-band antenna combination

Growing community of inventors

Shanghai, China

Dian Gu