Abstract: Apparatuses, systems, and techniques to perform inferencing using one or more neural networks with improved noise immunity are disclosed. In at least one embodiment, one or more neural networks may generate inferences, where these inferences may include measurably consistent information from the same input data irrespective of changes in environmental conditions.

Abstract: The invention is a battery protection device and a current regulation system for battery power supply. It features adjustable low- and high-voltage protection. It includes a housing, circuit board, first display screen, first and second buttons, indicator light, and sealing film. The first display screen, first button, second button, and indicator light are electrically connected to the circuit board. The first and second buttons set the minimum voltage output value. The first display screen displays the set minimum voltage output value and the real-time voltage of the battery. The indicator light indicates the device's on/off state. The circuit board is inside the housing. The housing’s upper surface has multiple openings. The first button, second button, indicator light, and first display screen protrude from the housing through corresponding openings. The sealing film covers the upper surface of the housing. The device offers high safety, long life, and good waterproofing.

Abstract: Processors, systems and techniques to dynamically configure multiple variants of neural networks, including enabling or disabling portions of the neural networks, are disclosed. In at least one embodiment, portions of the neural networks may be enabled or disabled based at least in part on user configurable indicators of performance characteristics of processors or systems hosting the neural networks.

Abstract: Apparatuses, systems, and techniques to generate an image. In at least one embodiment, one or more neural networks are to generate a second image based, at least in part, on a first image and information indicating zero or more differences between the first and second image.

Abstract: Processors, systems and techniques to perform different inferencing tasks using a unified multi-task inferencing mode are disclosed. In at least one embodiment, multiple task-specific models are created through fine tuning of a common pre-trained model, a single unified model is derived from the multiple task-specific models, and a task-specific model is then reconstructed from the unified model according to a type of inferencing task to be performed.

Abstract: Processors, systems and techniques to efficiently select numeric encoding formats of varying precision for processing within neural networks is disclosed. In at least one embodiment, tensor data of respective layers of a neural network may be quantized according to a plurality of low precision formats, either during or subsequent to training, and a preferred encoding format selected according at least to quantization error of the tensor data.

Abstract: Apparatuses, systems, and methods cause one or more neural networks to generate one or more representations of one or more integrated circuits. In at least one embodiment, a processor comprises one or more circuits to use one or more neural networks to generate one or more representations of one or more integrated circuits to perform one or more instructions, wherein the one or more representations are based, at least in part, on one or more different instruction operands and one or more representations resulting from the one or more different instruction operands.

Abstract: Apparatuses, systems, and methods to enable matrix multiplication acceleration by modifying an input to apply sparsity through sparse activation filtering. In at least one embodiment, a neural network modifies pixels within an image through sparse activation filtering to enable use of one or more matrix multiplication acceleration units to perform a sparse patch embedding operation.

Abstract: Apparatuses, systems, and techniques to simulate high-precision calculations with a series expansion of lower precision tensor cores. In at least one embodiment, one or more multiplication operands of a first precision are represented by a sum of two or more operands of a different precision.

Abstract: Apparatuses, systems, and techniques to generate an image. In at least one embodiment, one or more neural networks are to generate a second image based, at least in part, on a first image and information indicating zero or more differences between the first and second image.

Abstract: Apparatuses, systems, and techniques to generate neural networks optimized for different hardware. In at least one embodiment, a processor using circuits is to adjust a neural network architecture based on computing resources that use said neural network in inference.

Abstract: Apparatuses, techniques, and/or software to reduce a number of weight parameter values for one or more neural networks by causing said one or more neural networks to use one or more tensors in two or more portions of the one or more neural networks. For example, apparatuses, techniques, processors, and/or software to generate a linear combination of tensors to approximate two or more layers of a neural network, where said same tensors can be used or repeated to approximate different portions of a neural network. In one or more embodiments, said two or more portions are generated and provided to said one or more neural networks using knowledge distillation techniques.

Abstract: Apparatuses, systems, and techniques to transform data sets, such as matrices representing layers of neural networks, to increase sparsity and/or other characteristics of said data sets to improve performance in computations, such as neural network computations. In at least one embodiment, one or more subsets of data in one or more sets of data are rearranged as part of a process to increase sparsity in said one or more sets of data to satisfy one or more one or more structural sparsity constraints.

Abstract: Apparatuses, systems, and techniques to generate one or more neural networks. In at least one embodiment, a processor comprises one or more circuits to use one or more first neural networks to generate one or more second versions of one or more second neural networks based, at least in part, on one or more first versions of the one or more second neural networks and one or more hardware resources to be used to perform the one or more second versions of the one or more second neural networks.

Abstract: Apparatuses, systems, and techniques to perform a neural network to select a dataset. In at least one embodiment, for example, a neural network calculates an expected relevance of data of a dataset subset, where said subset is portioned based, at least in part, on an amount of available storage. In at least one embodiment, as another example, a processor is to cause one or more neural networks to identify one or more first portions of first information to be used by one or more neural networks to generate second information, wherein one or more neural networks are to identify one or more first portions based, at least in part, on an amount of available storage.

Abstract: Apparatuses, systems, and techniques are to modify a precision and/or sparsity of one or more neural network layers. In at least one embodiment, a precision and/or sparsity of one or more neural network layers are based, at least in part on, a comparison of activations of a sparse version and a dense version of a neural network.

Abstract: Apparatuses, systems, and techniques are to modify a neural network according to hardware type. In at least one embodiment, one or more masks are used with a neural network to be deployed on a specific GPU hardware platform.

Abstract: Apparatuses, systems, and techniques to construct a neural network architecture. In at least one embodiment, candidate neural components may be selected for the neural network by jointly updating performance metric masks attached to these candidate neural components and a union neural network comprising all candidate neural components.

Abstract: In various examples, a technique for processing sensor data includes generating, using a machine learning model and based on a first sensor data instance, a first set of confidences for a set of output types and a first adversarial confidence that represents a likelihood that the first sensor data instance is adversarial. The technique also includes determining that the first sensor data instance is adversarial based on the first adversarial confidence. The technique further includes transmitting a first indication that the first sensor data instance is adversarial to one or more downstream components such that the one or more downstream components perform one or more operations based at least on the indication.

Abstract: Apparatuses, systems, and techniques to generate labels for images. In at least one embodiment, one or more labels of one or more images are generated based, at least in part, on an amount by which the one or more images were modified.