Loading patent…
OwnerVladimir Petrovich Korviakov, Anuar Guldenbekovich TASKYNOV +3inventors
InventorsVladimir Petrovich Korviakov, Anuar Guldenbekovich TASKYNOV, Jiang Li, Ivan Leonidovich Mazurenko, Yepan Xiong
Estimating the term…
A device for implementing a tensor-train decomposition operation for a respective convolutional layer of a convolutional neural network (CNN) is provided. The device is configured to receive input data comprising a first number of channels, and perform a 1×1 convolution on the input data to obtain a plurality of data groups. The plurality of data groups comprises a second number of channels. The device is further configured to perform a group convolution on the plurality of data groups to obtain intermediate data comprising a third number of channels, and perform a 1×1 convolution on the intermediate data to obtain output data comprising a fourth number of channels.
A device for implementing a tensor-train decomposition operation for a respective convolutional layer of a convolutional neural network (CNN), the device being configured to:
A method for implementing a tensor-train decomposition operation for a convolutional layer of a convolutional neural network (CNN), the method comprising:
Dependencies are inferred from the claim text.