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.

There is provided a computer implemented method of compressing a baseline dataset comprising a sequence of a plurality of instances of a plurality of unique data elements, the method comprising: providing a weight function that calculates an increasing value for a weight for each one of the plurality of instances of each one of the plurality of unique data elements in the baseline dataset, as a function of increasing number of previously processed sequential locations of each of the plurality of instances of each respective unique data element within the baseline dataset relative to a current sequential location of the baseline dataset, computing an encoding for the baseline dataset according to a distribution of the weight function computed for the plurality of unique data elements in the baseline dataset, and creating a compressed dataset according to the encoding.

A FRAMEWORK and the associated method, schema and design for processing digital data, whether random or not, through encoding and decoding losslessly and correctly for purposes including the purposes of encryption/decryption or compression/decompression or both. There is no assumption of the digital information to be processed before processing. A Universal Coder is invented and now Pigeonhole meets Blackhole.

A processing device for executing a machine learning neural network operation includes memory and a processor. The processor is configured to receive input data at a layer of the machine learning neural network operation, receive a plurality of sorted filters to be applied to the input data, apply the plurality of sorted filters to the input data to produce a plurality of different feature maps, compress the plurality of different feature maps according to a sparsity of the feature maps and store the plurality of different feature maps in the memory.

Systems and methods providing a hybrid intermediate stream format are provided. The method includes compressing a vertex into a first data block via a first compression method, compressing the vertex into a second data block via a second compression method, determining a smaller file of the first data block and the second data block, finalizing compression of the vertex via a compression method, selected from the first compression method and the second compression method, corresponding to the determined smaller file of the first data block and the second data block, and transferring the compressed vertex.

According to one embodiment, an interleaving unit divides a symbol string into first and second symbols. A first coding unit converts the first symbols to first codewords. A first packet generating unit generates first packets including the first codewords. A first request generating unit generates first packet requests including sizes of variable length packets. A second coding unit converts the second symbols to second codewords. A second packet generating unit generates second packets including the second codewords. A second request generating unit generates second packet requests including sizes of variable length packets. A multiplexer outputs a compressed stream including the first and second variable length packets cut out from the first and second packets.

A computer-implemented method for content-agnostic referencing of a binary data file, the method comprising: determining a length of the binary data file, the length comprising the number of bits of the binary data file; for the determined length, generating all permutations of data of the determined length; locating an index within the generated permutations, wherein the index is the starting position of the binary data file within the generated permutations; and using the length and the index to indicate the binary data file.

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 method for processing image data and a system thereof are provided. The method is operated in the system including an encoding system and a decoding system. In the decoding system, multiple image data packages are received from the encoding system. The image data packages include multiple encoded data that are formed by encoding the pixels of an image and the pixels are beforehand rearranged according to an arrangement order. The arrangement order is exemplarily made based on the quantity of encoding circuits of the encoding system. In the decoding system, the encoded data received from the encoding system are sequentially stored in a memory according to the arrangement order. The decoding circuits start to decode the encoded data from an initial code synchronously for enhancing decoding performance. The method can be applied to decoding of high resolution images. The image is reproduced after the decoding process.

A framework and the associated method, schema and design for processing digital data, whether random or not, through encoding and decoding losslessly and correctly for purposes including the purposes of encryption/decryption or compression/decompression or both. There is no assumption of the digital information to be processed before processing. An universal coder is invented and now pigeonhole meets blackhole.