Example methods, apparatus, and articles of manufacture to capture and compress telematics data are disclosed herein. An example computer-implemented method, executed by a processor, to represent telematics data includes identifying, with the processor, a physical intersection of roads, identifying, with the processor, virtual lines crossing the roads, assigning, with the processor, ordinals to the virtual lines, representing, with the processor, a physical traversal through the physical intersection captured in first telematics data by a pair of the ordinals, and storing the pair of the ordinals in second compressed telematics data.

A system and a method provide compression and decompression of weights of a layer of a neural network. For compression, the values of the weights are pruned and the weights of a layer are configured as a tensor having a tensor size of H×W×C in which H represents a height of the tensor, W represents a width of the tensor, and C represents a number of channels of the tensor. The tensor is formatted into at least one block of values. Each block is encoded independently from other blocks of the tensor using at least one lossless compression mode. For decoding, each block is decoded independently from other blocks using at least one decompression mode corresponding to the at least one compression mode used to compress the block; and deformatted into a tensor having the size of H×W×C.

The present invention aims to encode and decode a sequence of integer values by substantially assigning the number of bits of a decimal fraction value per sample. An integer converter 11 selects M selected integer values from L input integer values for a set of the L input integer values and obtains J-value selection information that specifies which of the L input integer values the M selected integer values are. Furthermore, the integer converter 11 obtains one converted integer value by reversibly converting the M selected integer value and an integer value corresponding to the J-value selection information. An integer encoder 12 encodes the converted integer value to obtain a code.

In deep learning, and in particular, for data compression for allreduce in deep learning, a gradient may be compressed for synchronization in a data parallel deep neural network training for allreduce by sharing a consensus vector between each node in a plurality of nodes to ensure identical indexing in each of the plurality of nodes prior to performing sparse encoding.

Methods, systems, and computer programs for compressing nucleic acid sequence data. A method can include obtaining nucleic acid sequence data representing: (i) a read sequence, and (ii) a plurality of quality scores, determining whether the read sequence includes at least one “N” base, based on a determination that the read sequence includes at least one “N” base, generating, by one or more computers, a first encoding data set by using a first encoding process to encode each set of four quality scores of the read sequence into a single byte of memory, and using a second encoding process to encode the first encoded data set, thereby compressing the data to be compressed.

A decoding device comprising a decoding unit configured to decode a tactile signal encoded for each of frequency bands. A decoding method comprising decoding a tactile signal encoded for each of frequency bands. A non-transitory storage medium encoded with instructions that, when executed by a computer, execute processing comprising decoding a tactile signal encoded for each of frequency bands.

A method for compressing data in a local cache of a web server is described. A local cache compression engine accesses values in the local cache and determines a cardinality of the values of the local cache. The local cache compression engine determines a compression rate of a compression algorithm based on the cardinality of the values of the local cache. The compression algorithm is applied to the cache based on the compression rate to generate a compressed local cache.

Certain aspects of the present disclosure provide techniques for committing log data in an application to a log data repository. An example method generally includes receiving, from an application, data to be committed to a remote storage location. A type of the received data is determined. The type of the received data is generally associated with a prioritization level and a compression mechanism to be used in committing the data to the remote storage location. An application execution context associated with the received data is determined. At a dispatch time associated with the prioritization level of the received data and the application execution context associated with the received data, a compressed data payload is generated and transmitted to the remote storage location. Generally, to compress the data payload, at least the received data is generally compressed based on the determined compression mechanism.

A method of compressing weights of a neural network includes compressing a weight set including the weights of a the neural network, determining modified weight sets by changing at least one of the weights, calculating compression efficiency values for the determined modified weight sets based on a result of compressing the weight set and results of compressing the determined modified weight sets, determining a target weight of the weights satisfying a compression efficiency condition among the weights based on the calculated compression efficiency values, and determining a final compression result by compressing the weights based on a result of replacing the determined target weight.

An apparatus of neural network model decompression includes processing circuitry. The processing circuitry can be configured to receive, from a bitstream of a compressed neural network representation, one or more first syntax elements associated with a 3-dimensional coding unit (CU3D) partitioned from a 3-dimensional coding tree unit (CTU3D). The first CTU3D can be partitioned from a tensor in a neural network. The one or more first syntax elements can indicate that the CU3D is partitioned based on a 3D pyramid structure that includes multiple depths. Each depth corresponds to one or more nodes. Each node has a node value. Second syntax elements corresponding to the node values of the nodes in the 3D pyramid structure can be received from the bitstream in a breadth-first scan order for scanning the nodes in the 3D pyramid structure. Model parameters of the tensor can be reconstructed based on the received second syntax elements.