Disclosed are a computer system, a software path prediction computer, non-transitory computer-readable medium, and method for determining a predicted software path that utilize segmentation machine learning in combination with ensemble machine learning to keep a most accurate model running on a server program that receives requests from and sends predicted software path(s) to a software client.

Systems, apparatus, and methods for thread-based scheduling within a multicore processor. Neural networking uses a network of connected nodes (aka neurons) to loosely model the neuro-biological functionality found in the human brain. Various embodiments of the present disclosure use thread dependency graphs analysis to decouple scheduling across many distributed cores. Rather than using thread dependency graphs to generate a sequential ordering for a centralized scheduler, the individual thread dependencies define a count value for each thread at compile-time. Threads and their thread dependency count are distributed to each core at run-time. Thereafter, each core can dynamically determine which threads to execute based on fulfilled thread dependencies without requiring a centralized scheduler.

Systems, apparatus, and methods for thread-based scheduling within a multicore processor. Neural networking uses a network of connected nodes (aka neurons) to loosely model the neuro-biological functionality found in the human brain. Various embodiments of the present disclosure use thread dependency graphs analysis to decouple scheduling across many distributed cores. Rather than using thread dependency graphs to generate a sequential ordering for a centralized scheduler, the individual thread dependencies define a count value for each thread at compile-time. Threads and their thread dependency count are distributed to each core at run-time. Thereafter, each core can dynamically determine which threads to execute based on fulfilled thread dependencies without requiring a centralized scheduler.

Apparatus and methods for training a neural network accelerator using quantized precision data formats are disclosed, and in particular for storing activation values from a neural network in a compressed format having lossy or non-uniform mantissas for use during forward and backward propagation training of the neural network. In certain examples of the disclosed technology, a computing system includes processors, memory, and a compressor in communication with the memory. The computing system is configured to perform forward propagation for a layer of a neural network to produced first activation values in a first block floating-point format. In some examples, activation values generated by forward propagation are converted by the compressor to a second block floating-point format having a non-uniform and/or lossy mantissa. The compressed activation values are stored in the memory, where they can be retrieved for use during back propagation.

Embodiments of the present disclosure disclose a method and apparatus for compressing a deep learning model. An embodiment of the method includes: acquiring a to-be-compressed deep learning model; pruning each layer of weights of the to-be-compressed deep learning model in units of channels to obtain a compressed deep learning model; and sending the compressed deep learning model to a terminal device, so that the terminal device stores the compressed deep learning model. By pruning each layer of weights of the deep learning model in units of channels, the parameter redundancy of the deep learning model is effectively reduced, thereby improving the computational speed of the deep learning model and maintaining the model accuracy.

A computer-implemented method of data compression leveraging quantum computing and classical computing includes extracting metadata from a binary data to be compressed. The binary data is compressed by iteratively performing a compression operation including selecting a hashing function and hashing the binary data. The quantum computer device performs an inverting of the hashing function and generates a finite number of one or more resultant files associated with the hashed data. A compressed file including the hashes and the metadata used for the decompression is stored upon determining that the one or more resultant files is a single file.

Embodiments describe a method for decoding speech including receiving speech input at an audio input device, generating speech data that is a digital representation of the speech input; extracting acoustic features of the speech data, assigning acoustic scores to the acoustic features, receiving data representing the acoustic features and the acoustic scores, decoding the data representing the acoustic features into a word, having a word score, by referencing a WFST language model, modifying the word score into a new word score based on a personalized grammar model stored in the external memory device, the processor is separate from and external to the WFST accelerator, and determining an intent represented by a plurality of words outputted by the WFST accelerator, where the plurality of words include the word and the new word score.

Multi-byte compressed string representation embodiments define a String class control field identifying compression as enabled/disabled, and another control field, identifying a decompressed string created when compression enabled. On pattern matching by a compiler, noping tests based on null setting of stringCompressionFlag and registering a class loading assumption on a nop location. When arguments to a String class constructor are not compressible, a decompressed String is created and stringCompressionFlag initialized. Endian-aware helper methods for reading/writing byte and character values and helper methods for widening, narrowing, truncation, conversion and masking are defined. Enhanced String class constructors, when characters are not compressible, create a decompressed String, and initialize stringCompressionFlag triggering class load assumptions, overwriting all nopable patch points. A String object sign bit is set to one for decompressed strings when compression enabled, and masking/testing this flag bit is noped using stringCompressionFlag and associated class load assumption. Alternative package protected string constructors and operations are provided. Checking a predetermined location to determine whether supplied arguments to a String class constructor are compressible is performed.

A method for controlling an electronic apparatus is provided. The method for controlling an electronic apparatus includes the steps of selecting a generic-purpose artificial intelligence model, generating a compressed artificial intelligence model based on the selected generic-purpose artificial intelligence model, and generating a dedicated artificial intelligence model based on the generated compressed artificial intelligence model, and the step of generating a compressed artificial intelligence model includes the steps of acquiring a rank of a singular value decomposition (SVD) algorithm based on a compression rate, compressing and training the selected generic-purpose artificial intelligence model based on the acquired rank and converting the model into the compressed artificial intelligence model, determining the performance of the converted compressed artificial intelligence model based on a predetermined first threshold value, and based on the performance of the converted compressed artificial intelligence model being lower than the predetermined first threshold value, generating the dedicated artificial intelligence model.

An information handling system improves removal of steganography data embedded in a graphics file by processing graphics files stored in a file system or transmitted through a network by processing the graphics files in a steganalyzer. The steganalyzer converts the body segment of the graphics file into binary code, and then compresses the binary code into a graphics file. This process results in the removal of any potential malicious code. The body segment location can be determined by parsing the portable network graphics file to determine a location of a pre-fix graphics file signature and a post-fix graphics file signature, with the graphics files signatures being specific to a particular type of graphics file.