Techniques are provided herein for more efficiently storing images that have a common subject, such as product images that share the same product in the image. Each image undergoes an adaptive tiling procedure to split the image into a plurality of tiles, with each tile identifying a region of the image having pixels with the same content. The tiles across multiple images can then be clustered together and those tiles having identical content are removed. Once all duplicate tiles have been removed from the set of all tiles across the images, the tiles are once again clustered based on their encoding scheme and certain encoding parameters. Tiles within each cluster are compressed using the best compression technique for the tiles in each corresponding cluster. By removing duplicative tile content between numerous images of the same subject, the total amount of data that needs to be stored is reduced.

A system includes a non-transitory computer readable medium configured to store instructions thereon; and a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for generating a mask based on received data from a sensor, wherein the mask includes a plurality of importance values, and each region of the received data is designated a corresponding importance value of the plurality of importance values. The processor is configured to execute the instructions for encoding the received data based on the mask; and transmitting the encoded data to a decoder for defining reconstructed data. The processor is configured to execute the instructions for computing a loss based on the reconstructed data, the received data and the mask. The processor is configured to execute the instructions for providing training to an encoder for encoding the received data based on the computed loss.

A disclosed information handling system includes an edge device communicatively coupled to a cloud computing resource. The edge device is configured to respond to receiving, from an internet of things (IoT) unit, a numeric value for a parameter of interest by determining a compressed encoding for the numeric value in accordance with a non-lossless compression algorithm. The edge device transmits the compressed encoding of the numeric value to the cloud computing resource. The cloud computing resource includes a decoder communicatively coupled to the encoder and configured to respond to receiving the compressed encoding by generating a surrogate for the numeric value. The surrogate may be generated in accordance with a probability distribution applicable to the parameter of interest. The compression algorithm may be a clustering algorithm such as a k-means clustering algorithm.

An electronic apparatus is provided. The electronic apparatus includes a storage storing a matrix included in an artificial intelligence model, and a processor. The processor divides data included in at least a portion of the matrix by one of rows and columns of the matrix to form groups, clusters the groups into clusters based on data included in each of the groups, and quantizes data divided by the other one of rows and columns of the matrix among data included in each of the clusters.

The present invention suppresses the data size of a data frame to be transmitted to a control device at every control period even if oversampling is performed. A counter unit (10) compresses the data size of sampling data (Sd) indicating a second or subsequent count value (Ct) to the number of bits by which the maximum (Vmax) of a count value countable in one sampling processing can be represented.

A system and method for generating and using fixed-point operations for neural networks includes converting floating-point weighting factors into fixed-point weighting factors using a scaling factor. The scaling factor is defined to minimize a cost function and the scaling factor is derived from a set of multiples of a predetermined base. The set of possible scaling function is defined to reduce the computational effort for evaluating the cost function for each of a number of possible scaling factors. The system and method may be implemented in one or more controllers that are programmed to execute the logic.

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.

A system is provided for electronic data compression by automated time-dependent compression algorithm. In particular, the system may track instances in which a particular dataset is used, copied, or accessed over time. For certain datasets (e.g., datasets that have not been accessed for a threshold amount of time), the system may use a time-based compression algorithm that progressively removes the least significant bits of such datasets as time passes. The compression of the datasets may continue until the system detects that further compression would cause the dataset to be unreadable or unrecoverable. In this way, the system may minimize the computing resources allocated to storing datasets that are not frequently accessed.

In an embodiment, a processor supports one or more compression assist instructions which may be employed in compression software to improve the performance of the processor when performing compression/decompression. That is, the compression/decompression task may be performed more rapidly and consume less power when the compression assist instructions are employed then when they are not. In some cases, the cost of a more effective, more complex compression algorithm may be reduced to the cost of a less effective, less complex compression algorithm.

A communication system SYS includes a transmission apparatus 1 and a reception apparatus 2. The transmission apparatus includes: a conversion unit 111 for converting a bit stream Z having a bit length b into a bit stream Y that has w−1 (w is an integer equal to or larger than 2) bit 1 and that has a bit length n (n>b); a conversion unit 112 for converting the bit stream Y into a bit stream X having a bit length t (t<n); and a Neural Network 113 that has a t input node and that outputs a value relating to a feature of a transmission signal Tx when the bit stream X is inputted thereto. The reception apparatus includes: a Neural Network 212 that has a t output node and that outputs a numerical data stream U including t numerical data when a feature of the reception signal is inputted thereto; a conversion unit 213 for converting the numerical data stream U into a numerical data stream Y′ including n numerical data; and a generation unit 214 for generating a bit stream Z′ having the bit length b by performing, on the numerical data stream U, an inverse conversion of a conversion processing performed by the conversion unit 111.