Abstract: A system and method for processing machine learning techniques (such as neural networks) and other non-graphics applications using a graphics processing unit (GPU) to accelerate and optimize the processing. The system and method transfers an architecture that can be used for a wide variety of machine learning techniques from the CPU to the GPU. The transfer of processing to the GPU is accomplished using several novel techniques that overcome the limitations and work well within the framework of the GPU architecture. With these limitations overcome, machine learning techniques are particularly well suited for processing on the GPU because the GPU is typically much more powerful than the typical CPU. Moreover, similar to graphics processing, processing of machine learning techniques involves problems with solving non-trivial solutions and large amounts of data.

Abstract: Systems and methods are described that facilitate performing feature extraction across multiple received input features to reduce computational overhead associated with feature processing related to, for instance, optical character recognition. Input feature information can be unfolded and concatenated to generate an aggregated input matrix, which can be convolved with a kernel matrix to produce output feature information for multiple output features concurrently.

Abstract: Systems and methods are disclosed that facilitate normalizing and beautifying digitally generated handwriting, such as can be generated on a tablet PC or via scanning a handwritten document. A classifier can identify extrema in the digital handwriting and label such extrema according to predefined categories (e.g., bottom, baseline, midline, top, other, . . . ). Multi-linear regression, polynomial regression, etc., can be performed to align labeled extrema to respective and corresponding desired points as indicated by the labels. Additionally, displacement techniques can be applied to the regressed handwriting to optimize legibility for reading by a human viewer and/or for character recognition by a handwriting recognition application. The displacement techniques can comprise a “rubber sheet” displacement algorithm in conjunction with a “rubber rod” displacement algorithm, which can collectively preserve spatial features of the handwriting during warping thereof.

Abstract: A system and method facilitating pattern recognition is provided. The invention includes a pattern recognition system having a convolutional neural network employing feature extraction layer(s) and classifier layer(s). The feature extraction layer(s) comprises convolutional layers and the classifier layer(s) comprises fully connected layers. The pattern recognition system can be trained utilizing a calculated cross entropy error. The calculated cross entropy error is utilized to update trainable parameters of the pattern recognition system.

Abstract: Systems and methods for performing adaptive filtering are disclosed. The present invention generates probabilities that can be used in an encoder, such as an arithmetic encoder and generates those probabilities in a computationally efficient manner. Probabilities of previously encoded coefficients are employed, effectively, in generating probabilities of the coefficients without regard to directional information. Thus, a large amount of information is adaptively and efficiently used in generating the probabilities. For the coefficients, the probability is computed based at least partly on at least one probability of a previously computed probability of a neighboring coefficient. Then, the coefficients are encoded using those computed probabilities.

Abstract: A system and method for optimizing the performance of a graphics processing unit (GPU) for processing and execution of general matrix operations such that the operations are accelerated and optimized. The system and method describes the layouts of operands and results in graphics memory, as well as partitioning the processes into a sequence of passes through a macro step. Specifically, operands are placed in memory in a pattern, results are written into memory in a pattern appropriate for use as operands in a later pass, data sets are partitioned to insure that each pass fits into fixed sized memory, and the execution model incorporates generally reusable macro steps for use in multiple passes. These features enable greater efficiency and speed in processing and executing general matrix operations.

Abstract: A system and method for processing machine learning techniques (such as neural networks) and other non-graphics applications using a graphics processing unit (GPU) to accelerate and optimize the processing. The system and method transfers an architecture that can be used for a wide variety of machine learning techniques from the CPU to the GPU. The transfer of processing to the GPU is accomplished using several novel techniques that overcome the limitations and work well within the framework of the GPU architecture. With these limitations overcome, machine learning techniques are particularly well suited for processing on the GPU because the GPU is typically much more powerful than the typical CPU. Moreover, similar to graphics processing, processing of machine learning techniques involves problems with solving non-trivial solutions and large amounts of data.

Abstract: A system that facilitates generation of data that can be employed in connection with training a classifier. The system comprises a component that receives a data set that is employed in connection with training the classifier, and an expansion component that applies elastic distortion algorithm(s) to a subset of the data set to generate additional labeled training data.