Certain aspects of the present disclosure provide techniques for performing machine learning computations in a compute in memory (CIM) array comprising a plurality of bit cells, including: determining that a sparsity of input data to a machine learning model exceeds an input data sparsity threshold; disabling one or more bit cells in the CIM array based on the sparsity of the input data prior to processing the input data; processing the input data with bit cells not disabled in the CIM array to generate an output value; applying a compensation to the output value based on the sparsity to generate a compensated output value; and outputting the compensated output value.

A speech recognition apparatus (2000) includes a first model (10) and a second model (20). The first model (10) is learned by training data with an audio frame as input data, and with, as correct answer data, compressed character string data acquired by encoding character string data represented by the audio frame. The second model (20) is a learned decoder (44) acquired by learning an autoencoder (40) being constituted of an encoder (42) converting input character string data into compressed character string data, and the decoder (44) converting, into character string data, the compressed character string data output from the encoder. The speech recognition apparatus (2000) inputs an audio frame to the first model (10), inputs, to the second model (20), compressed character string data output from the first model (10), and thereby generates character string data corresponding to the audio frame.

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.

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 method for selectively dropping out feature elements from a tensor in a neural network is disclosed. The method includes receiving a first tensor from a first layer of a neural network. The first tensor includes multiple feature elements arranged in a first order. A compressed mask for the first tensor is obtained. The compressed mask includes single-bit mask elements respectively corresponding to the multiple feature elements of the first tensor and has a second order that is different than the first order of their corresponding feature elements in the first tensor. Feature elements from the first tensor are selectively dropped out based on the compressed mask to form a second tensor which is propagated to a second layer of the neural network.

A method for adapting a trained neural network is provided. Input data is input to the trained neural network and a plurality of filters are applied to generate a plurality of channels of activation data. Differences between corresponding activation values in the plurality of channels of activation data are calculated and an order of the plurality of channels is determined based on the calculated differences. The neural network is adapted so that it will output channels of activation data in the determined order. The ordering of the channels of activation data is subsequently used to compress activation data values by taking advantage of a correlation between activation data values in adjacent channels.

A method, computer program, and computer system is provided for point cloud coding. Data corresponding to a point cloud is received. Hash elements corresponding to attribute values associated with the received data is reconstructed. A size of a hash table may be decreased based on deleting one or more of the hash elements corresponding to non-border regions associated with the attribute values. The data corresponding to the point cloud is decoded based on the reconstructed hash elements.

Disclosed are a data compression method, a computer-readable storage medium, and an electronic device. The method includes: converting each data in a to-be-compressed data set into binary data in a preset format; determining a to-be-compressed bit and a significant bit for the each data in the to-be-compressed data set based on a sequence of all bits of the binary data; determining a compression bit width corresponding to the to-be-compressed data set based on bit widths of the significant bits; compressing the each data in the to-be-compressed data set based on the compression bit width, to obtain a compressed data set; and generating attribute information of the compressed data set. According to the present disclosure, the significant bit can be determined based on the sequence of all bits without adjusting orders of the bits of the binary data, thereby simplifying a data compression process and improving efficiency of data compression.

An apparatus includes data acquisition circuitry and a processor. The data acquisition circuitry is configured to acquire multiple signals using multiple respective electrodes of an array of electrodes coupled to one of an organ of a patient and tissue or a cell culture. The processor is configured to hold a definition of a mixed-norm that is defined as a function of relative positions of the electrodes in the array, and jointly compress the multiple signals in a compressed-sensing (CS) process that minimizes the mixed-norm.

A storage system that performs irreversible compression on time-series data using a compressor/decompressor based on machine learning calculates a statistical amount value of each of one or more kinds of statistical amounts based on one or more parameters in relation to original data (time-series data input to a compressor/decompressor) and calculates a statistical amount value of each of the one or more kinds of statistical amounts based on the one or more kinds of parameters in relation to decompressed data (time-series data output from the compressor/decompressor) corresponding to the original data. The machine learning of the compressor/decompressor is performed based on the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data.