Abstract: The disclosed method for solving a Boolean satisfiability (SAT) problem includes receiving a SAT problem, generating, based on the SAT problem, a SAT problem matrix, performing, based on the SAT problem matrix, one or more operations to train an untrained machine learning model to generate a trained machine learning model and gradient data, wherein the trained machine learning model comprises a trained partial assignment matrix, and generating, based on the trained partial assignment matrix and the gradient data and using one or more SAT solvers, a SAT solver output.

Abstract: Neural networks, and in particular deep neural networks, are traditionally resource intensive as they require execution of a significant number of computations in order to generate an output. In an effort to accelerate neural networks, quantization has been employed in which the input/output of certain operations are scaled. However, the degree to which a neural network can be quantized is limited because current scaling methods, which do not ensure consistent scaling for operands, cannot be applied to the commonly used element-wise operations (e.g. addition and subtraction). The present disclosure provides scaling of element-wise operations in a neural network by using scale factors that are shared between operands, thus allowing for greater quantization of neural networks.

Abstract: The disclosed method for eye tracking includes processing an image using a trained machine learning model that detects a face within the image and predicts an identity of the face, determining at least one of an eye gaze or a point of regard based on the face and the identity of the face, and performing, via a computing device, at least one action based on the at least one of the eye gaze or the point of regard.

Abstract: One embodiment of a computer-implemented method for processing a neural network comprises receiving a first quantized matrix that corresponds to a portion of a multi-dimensional input tensor and has been quantized based on a first scale factor; and performing one or more computational operations using the first quantized matrix and the first scale factor to generate one or more data values that correspond to a first portion of a multi-dimensional output tensor.

Abstract: Quantization and sparsity serve as the two pivotal techniques driving dramatic improvements in deep neural network (DNN) performance. However, for diffusion models quantization and sparsity fail to work out-of-the-box due to the unique characteristics of these models. The present disclosure provides for optimization of the execution of a diffusion model based on a time-dependent activation sparsity pattern of the diffusion model, which can provide acceleration of the diffusion model while achieving state-of-the-art generation quality at significantly reduced hardware costs.

Abstract: One embodiment of a computer-implemented method for processing a neural network comprises receiving a first quantized matrix that corresponds to a portion of a multi-dimensional input tensor and has been quantized based on a first scale factor; and performing one or more computational operations using the first quantized matrix and the first scale factor to generate one or more data values that correspond to a first portion of a multi-dimensional output tensor.

Abstract: A method of forming a matrix of electrowetting pixels includes forming a patterned layer of electrodes (512) on a substrate (510) and forming a patterned insulating layer (514) on the electrodes (512) and the substrate (510) to define a plurality of wells (516), each of the wells (516) aligned over one of the electrodes (512). A hydrophobic material (518) is formed on the bottom surfaces of the wells (516) and a hydrophilic material (526) is formed on sidewalls (519) of the wells (516), for example by one of selective reaction, selective deposition and selective etching, by the application of a beam (524) at an angle to impact the sidewalls (519) while substantially avoiding impacting the bottom surface (515). First and second liquids (532, 534) are disposed within the wells (516), the first liquid being not soluble in the second liquid.

Abstract: A method of forming a matrix of electrowetting pixels includes forming a patterned layer of electrodes (512) on a substrate (510) and forming a patterned insulating layer (514) on the electrodes (512) and the substrate (510) to define a plurality of wells (516), each of the wells (516) aligned over one of the electrodes (512). A hydrophobic material (518) is formed on the bottom surfaces of the wells (516) and a hydrophilic material (526) is formed on sidewalls (519) of the wells (516), for example by one of selective reaction, selective deposition and selective etching, by the application of a beam (524) at an angle to impact the sidewalls (519) while substantially avoiding impacting the bottom surface (515). First and second liquids (532, 534) are disposed within the wells (516), the first liquid being not soluble in the second liquid.