Example methods, apparatus, and articles of manufacture to compress telematics data are disclosed herein. An example computer-implemented method includes identifying, using one or more processors, a portion of recorded telematics data representing a physical transversal of a physical intersection of two or more road segments, wherein each road segment has an assigned unique ordinal value; identifying, using one or more processors, a first road segment on which the physical transversal entered the intersection; identifying, using one or more processors, a second road segment on which the physical transversal exited the intersection; identifying, using one or more processors, a pair of ordinal values including a first ordinal value assigned to the first road segment, and a second ordinal value assigned to the second road segment; and storing the pair of ordinal values instead of the portion of the recorded telematics data in a compressed representation of the recorded telematics data.

Techniques and apparatuses to decompress data that has been stack compressed is described. Stack compression refers to compression of data in one or more dimensions. For uncompressed data blocks that are very sparse, i.e., data blocks that contain many zeros, stack compression can be effective. In stack compression, uncompressed data block is compressed into compressed data block by removing one or more zero words from the uncompressed data block. A map metadata that maps the zero words of the uncompressed data block is generated during compression. With the use of the map metadata, the compressed data block can be decompressed to restore the uncompressed data block.

Systems, devices and methods for adaptive compression of stored information includes a memory management computing device programmed to monitor a size of a plurality of data structures stored in a data repository. The computing device compares the size of each of a plurality of data structures to a predetermined threshold. When a size of an uncompressed data structure meets the threshold, the memory management computing device calculates a value of a first compression parameter based on a value of a first parameter and a value of a second parameter of each data element of the uncompressed data structure, calculates a value of a second compression parameter based the value of the first parameter of each data element of the uncompressed data structure, generates a compressed data structure based on the value of the first compression parameter and the second compression parameter; and replaces, in the data repository, the uncompressed data structure with the compressed data structure.

A weight data compression method includes: generating a 4-bit data string of 4-bit data items each expressed as any one of nine 4-bit values, by dividing ternary weight data into data items each having 4 bits; and generating first compressed data including a first flag value string and a first non-zero value string by (i) generating the first flag value string by assigning one of 0 and 1 as a first flag value of a 1-bit flag to a 4-bit data item 0000 and assigning an other of 0 and 1 as a second flag value of the 1-bit flag to a 4-bit data item other than 0000 among the 4-bit data items in the 4-bit data string and (ii) generating the first non-zero value string by converting the 4-bit data item other than 0000 into a 3-bit data item having any one of eight 3-bit values.

A system and method to compress application control data, such as weights for a layer of a convolutional neural network, is disclosed. A multi-core system for executing at least one layer of the convolutional neural network includes a storage device storing a compressed weight matrix of a set of weights of the at least one layer of the convolutional network and a decompression matrix. The compressed weight matrix is formed by matrix factorization and quantization of a floating point value of each weight to a floating point format. A decompression module is operable to obtain an approximation of the weight values by decompressing the compressed weight matrix through the decompression matrix. A plurality of cores executes the at least one layer of the convolutional neural network with the approximation of weight values to produce an inference output.

Described herein are computer-implemented methods for compressing sparse multidimensional ordered series data. In particular, these methods and apparatuses for performing them (including software) may be particularly well suited to efficiently compressing spectrographic data.

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.

A computer-implemented method of selecting a power-optimal compression scheme for transmitting digital control signals from a classical interface of a quantum computer to a quantum processing unit (QPU) of the quantum computer is disclosed. The method involves receiving static and dynamic power consumption values associated with operations performable by the QPU; determining compression schemes implementable by the QPU; calculating total power consumption values associated with receiving and decompressing a representative control signal at the QPU using the compression schemes; and selecting the compression scheme having the lowest total power consumption value. A corresponding method for transmitting control signals from a classical interface of the quantum computer to the QPU is also disclosed in which a compressed control signal is transmitted from the classical interface to the QPU with one or more delays.

A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud.

An autoregressor that compresses input data for a specific purpose. Input data is compressed using a compression/decompression framework and by accounting for a purpose of a prediction model. The compression aspect of the framework is distributed and the decompression aspect of the framework may be centralized. The compression/decompression framework and a machine learning prediction model can be centrally trained. The compressor is distributed to nodes such that the input data can be compressed and transmitted to a central node. The model and the compression/decompression framework are continually trained on new data. This allows for lossy compression and higher compression rates while maintaining low prediction error rates.