The present disclosure relates to circuitry for performing a multiply-accumulate (MAC) operation. The circuitry comprises a first multiplexer having a plurality of inputs for receiving a plurality of unary-coded input signals representing operands of the MAC operation and an output for outputting a multiplexer output signal representing a result of the MAC operation and a first vector quantizer configured to receive a plurality of weighting signals, each representing a proportion of a computation time period for which a respective one of the unary-coded input signals should be selected by the multiplexer and to output a first selector signal to the multiplexer to cause the multiplexer to select each of the input signals in accordance with the plurality of weighting signals.

The present disclosure relates to circuitry for performing a multiply-accumulate (MAC) operation. The circuitry comprises a first multiplexer having a plurality of inputs for receiving a plurality of unary-coded input signals representing operands of the MAC operation and an output for outputting a multiplexer output signal representing a result of the MAC operation and a first vector quantizer configured to receive a plurality of weighting signals, each representing a proportion of a computation time period for which a respective one of the unary-coded input signals should be selected by the multiplexer and to output a first selector signal to the multiplexer to cause the multiplexer to select each of the input signals in accordance with the plurality of weighting signals.

Method and system relating generally to convolution is disclosed. In such a method, an image patch is selected from input data for a first channel of a plurality of input channels of an input layer. The selected image patch is transformed to obtain a transformed image patch. The transformed image patch is stored. Stored is a plurality of predetermined transformed filter kernels. A stored transformed filter kernel of the plurality of stored predetermined transformed filter kernels is element-wise multiplied by multipliers with the stored transformed image patch for a second channel of the plurality of input channels different from the first channel to obtain a product. The product is inverse transformed to obtain a filtered patch for the image patch.

Method and system relating generally to convolution is disclosed. In such a method, an image patch is selected from input data for a first channel of a plurality of input channels of an input layer. The selected image patch is transformed to obtain a transformed image patch. The transformed image patch is stored. Stored is a plurality of predetermined transformed filter kernels. A stored transformed filter kernel of the plurality of stored predetermined transformed filter kernels is element-wise multiplied by multipliers with the stored transformed image patch for a second channel of the plurality of input channels different from the first channel to obtain a product. The product is inverse transformed to obtain a filtered patch for the image patch.

Data analytics systems and methods are disclosed herein. A parser can parse reference data from various data sources to store in a data structure. An uploader can receive study data designated by a researcher and store the study data in the data structure. A matcher can compare analyte nameset data in the study data with analyte nameset data from the reference data to generate one or more links each correlating an instance of an analyte in the study data with an instance of that analyte in the reference data. Library overlays each include one or more modules to access reference data to generate organized associations of reference data. A calculation engine can receive a selection of one or more library overlay(s) and manipulate the reference data and study data according to the organized associations of the selected library overlay(s) to generate configured data stored in a collection of data caches for presentation to a researcher via a user interface.

Data analytics systems and methods are disclosed herein. A parser can parse reference data from various data sources to store in a data structure. An uploader can receive study data designated by a researcher and store the study data in the data structure. A matcher can compare analyte nameset data in the study data with analyte nameset data from the reference data to generate one or more links each correlating an instance of an analyte in the study data with an instance of that analyte in the reference data. Library overlays each include one or more modules to access reference data to generate organized associations of reference data. A calculation engine can receive a selection of one or more library overlay(s) and manipulate the reference data and study data according to the organized associations of the selected library overlay(s) to generate configured data stored in a collection of data caches for presentation to a researcher via a user interface.

The embodiments of this application provide a method and device for optimizing neural network. The method includes: binarizing and bit-packing input data of a convolution layer along a channel direction, and obtaining compressed input data; binarizing and bit-packing respectively each convolution kernel of the convolution layer along the channel direction, and obtaining each corresponding compressed convolution kernel; dividing the compressed input data sequentially in a convolutional computation order into blocks of the compressed input data with the same size of each compressed convolution kernel, wherein the data input to one time convolutional computation form a data block; and, taking a convolutional computation on each block of the compressed input data and each compressed convolution kernel sequentially, obtaining each convolutional result data, and obtaining multiple output data of the convolution layer according to each convolutional result data.

A processor system comprises a plurality of processing elements. Each processing element includes a corresponding convolution processor unit configured to perform a portion of a groupwise convolution. The corresponding convolution processor unit determines multiplication results by multiplying each data element of a portion of data elements in a convolution data matrix with a corresponding data element in a corresponding groupwise convolution weight matrix. The portion of data elements in the convolution data matrix that are multiplied belong to different channels and different groups. For each specific channel of the different channels, the corresponding convolution processor unit sums together at least some of the multiplication results belonging to the same specific channel to determine a corresponding channel convolution result data element. The processing elements sum together a portion of the channel convolution result data elements from a group of different convolution processor units to determine a groupwise convolution result data element.

An electronic device, method, and computer readable medium for 3D association of detected objects are provided. The electronic device includes a memory and at least one processor coupled to the memory. The at least one processor configured to convolve an input to a neural network with a basis kernel to generate a convolution result, scale the convolution result by a scalar to create a scaled convolution result, and combine the scaled convolution result with one or more of a plurality of scaled convolution results to generate an output feature map.

An electronic device, method, and computer readable medium for 3D association of detected objects are provided. The electronic device includes a memory and at least one processor coupled to the memory. The at least one processor configured to convolve an input to a neural network with a basis kernel to generate a convolution result, scale the convolution result by a scalar to create a scaled convolution result, and combine the scaled convolution result with one or more of a plurality of scaled convolution results to generate an output feature map.