Abstract: The freshness of one or more terms in a documentation, indicative of a currency of the one or more terms is computed. Each term includes one or more constituent words, and the terms are visually marked as current or out-of-date based on the computed freshness. Upon marking a term as out-of-date, a latest term for the out-of-date term is retrieved or a most possible latest term for the out-of-date term is predicted.

Abstract: A system, apparatus and method are provided for securing a neural network (or other artificial intelligence model) against malicious activity, such as piracy, theft of intellectual property, sabotage, etc. One or more security elements or features (e.g., digital watermarks, encryption, obfuscation) are applied to the neural network model during training and/or optimization. Therefore, the model is enhanced with robust security before it is linked or merged with application software for performing inference processing using the model.

Abstract: The disclosed embodiments relate to a system that optimizes execution of a DNN based on operational performance parameters. During operation, the system collects the operational performance parameters from the DNN during operation of the DNN, wherein the operational performance parameters include parameters associated with operating conditions for the DNN, parameters associated with resource utilization during operation of the DNN, and parameters associated with accuracy of results produced by the DNN. Next, the system uses the operational performance parameters to update the DNN model to improve performance and efficiency during execution of the DNN.

Abstract: Systems, tools and methods are provided for optimizing neural networks (NNs) to run efficiently on target hardware such as central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), etc. The provided software tools are implemented as part of a machine-learning operations (MLOps) workflow for building a neural network, and include optimization algorithms (e.g., for quantization and/or pruning) and compiler processes that reduce memory requirements and processing latency.

Abstract: Artificial neural network systems involve the receipt by a computing device of input data that defines a pattern to be recognized (such as faces, handwriting, and voices). The computing device may then decompose the input data into a first subband and a second subband, wherein the first and second subbands include different characterizing features of the pattern in the input data. The first and second subbands may then be fed into first and second neural networks being trained to recognize the pattern. Reductions in power expenditure, memory usage, and time taken, for example, allow resource-limited computing devices to perform functions they otherwise could not.

Abstract: A method of generating a prototype of a graphical user interface (GUI). The method includes acquiring a draft wireframe representing a GUI design, the draft wireframe including one or more wireframe components, and decomposing the draft wireframe into one or more component slices, each component slice including a respective wireframe component of the one or more wireframe components. The method also includes generating a component slice sequence including the one or more component slices and at least one additional component slice selected based on the draft wireframe, constructing a wireframe based on the component slice sequence, and generating a prototype of the GUI design based on the constructed wireframe.

Abstract: A low-cost, low-power, stand-alone sensor platform having a visible-range camera sensor, a thermopile array, a microphone, a motion sensor, and a microprocessor that is configured to perform occupancy detection and counting while preserving the privacy of occupants. The platform is programmed to extract shape/texture from images in spatial domain; motion from video in time domain; and audio features in frequency domain. Embedded binarized neural networks are used for efficient object of interest detection. The platform is also programmed with advanced fusion algorithms for multiple sensor modalities addressing dependent sensor observations. The platform may be deployed for (i) residential use in detecting occupants for autonomously controlling building systems, such as HVAC and lighting systems, to provide energy savings, (ii) security and surveillance, such as to detect loitering and surveil places of interest, (iii) analyzing customer behavior and flows, (iv) identifying high performing stores by retailers.

Abstract: In general, the disclosure describes techniques for creating runtime-throttleable neural networks (TNNs) that can adaptively balance performance and resource use in response to a control signal. For example, runtime-TNNs may be trained to be throttled via a gating scheme in which a set of disjoint components of the neural network can be individually “turned off” at runtime without significantly affecting the accuracy of NN inferences. A separate gating neural network may be trained to determine which trained components of the NN to turn off to obtain operable performance for a given level of resource use of computational, power, or other resources by the neural network. This level can then be specified by the control signal at runtime to adapt the NN to operate at the specified level and in this way balance performance and resource use for different operating conditions.

Abstract: Techniques are disclosed for training machine learning systems. An input device receives training data comprising pairs of training inputs and training labels. A generative memory assigns training inputs to each archetype task of a plurality of archetype tasks, each archetype task representative of a cluster of related tasks within a task space and assigns a skill to each archetype task. The generative memory generates, from each archetype task, auxiliary data comprising pairs of auxiliary inputs and auxiliary labels. A machine learning system trains a machine learning model to apply a skill assigned to an archetype task to training and auxiliary inputs assigned to the archetype task to obtain output labels corresponding to the training and auxiliary labels associated with the training and auxiliary inputs assigned to the archetype task to enable scalable learning to obtain labels for new tasks for which the machine learning model has not previously been trained.

Abstract: Techniques are disclosed for training a deep neural network (DNN) for reduced computational resource requirements. A computing system includes a memory for storing a set of weights of the DNN. The DNN includes a plurality of layers. For each layer of the plurality of layers, the set of weights includes weights of the layer and a set of bit precision values includes a bit precision value of the layer. The weights of the layer are represented in the memory using values having bit precisions equal to the bit precision value of the layer. The weights of the layer are associated with inputs to neurons of the layer. Additionally, the computing system includes processing circuitry for executing a machine learning system configured to train the DNN. Training the DNN comprises optimizing the set of weights and the set of bit precision values.

Abstract: The disclosed embodiments relate to a system that generates and executes a deep neural network (DNN) based on target runtime parameters. During operation, the system receives a trained original model and a set of target runtime parameters for the DNN, wherein the target runtime parameters are associated with one or more of the following for the DNN: desired operating conditions, desired resource utilization, and desired accuracy of results. Next, the system generates a context-specific model based on the original model and the set of target runtime parameters. The system also generates an operational plan for executing both the original model and the context-specific model to meet requirements of the target runtime parameters. Finally, the system controls execution of the original model and the context-specific model based on the operational plan.

Abstract: The disclosed embodiments relate to a system that facilitates dynamic runtime execution of a deep neural network (DNN). During operation, the system receives a model, a set of weights and runtime metadata for the DNN. The system also obtains code to perform inference-processing operations for the DNN. Next, the system compiles code to implement a runtime engine that facilitates throttling operations during execution of the inference-processing operations, wherein the runtime engine conserves computing resources by selecting portions of the inference-processing operations to execute based on the runtime metadata.

Abstract: The disclosed embodiments relate to a system that optimizes execution of a DNN based on operational performance parameters. During operation, the system collects the operational performance parameters from the DNN during operation of the DNN, wherein the operational performance parameters include parameters associated with operating conditions for the DNN, parameters associated with resource utilization during operation of the DNN, and parameters associated with accuracy of results produced by the DNN. Next, the system uses the operational performance parameters to update the DNN model to improve performance and efficiency during execution of the DNN.

Abstract: In general, techniques are described for processing a set of high-resolution images of an integrated circuit, the images captured at different locations with respect to the integrated circuit, to automatically align and “stitch” the set of high-resolution images into a larger composite image. For example, an imaging system as described herein may use sampled feature points distributed across different grid tiles within overlap regions for pairs of images to match feature points to inform the alignments of a pair with respect to each image in the pair. The system may in some cases further apply a bundle adjustment to iteratively align and refine the alignment results for each image in a set of images being processed. In some examples, the bundle adjustment is a best-fit adjustment based on minimizing the net error associated with the alignment of the set of images.

Abstract: In general, techniques are described for processing a set of high-resolution images of an integrated circuit, the images captured at different locations with respect to the integrated circuit, to automatically align and “stitch” the set of high-resolution images into a larger composite image. For example, an imaging system as described herein may use sampled feature points distributed across different grid tiles within overlap regions for pairs of images to match feature points to inform the alignments of a pair with respect to each image in the pair. The system may in some cases further apply a bundle adjustment to iteratively align and refine the alignment results for each image in a set of images being processed. In some examples, the bundle adjustment is a best-fit adjustment based on minimizing the net error associated with the alignment of the set of images.

Abstract: Techniques are disclosed for training machine learning systems. An input device receives training data comprising pairs of training inputs and training labels. A generative memory assigns training inputs to each archetype task of a plurality of archetype tasks, each archetype task representative of a cluster of related tasks within a task space and assigns a skill to each archetype task. The generative memory generates, from each archetype task, auxiliary data comprising pairs of auxiliary inputs and auxiliary labels. A machine learning system trains a machine learning model to apply a skill assigned to an archetype task to training and auxiliary inputs assigned to the archetype task to obtain output labels corresponding to the training and auxiliary labels associated with the training and auxiliary inputs assigned to the archetype task to enable scalable learning to obtain labels for new tasks for which the machine learning model has not previously been trained.

Abstract: Systems and methods for computerized time tracking are disclosed. In one aspect, a computer-implemented device is disclosed. The device comprises a memory storing instructions, a network device, a display device, and at least one processor configured to execute the instructions. The instructions direct the processor to determine a location of the device based on one or more network signals; based on the determined location, display a first user interface element that, when selected, records a start time associated with a user identifier; receive a selection of the first user interface element; after receiving a selection of the first user interface element, display a second user interface element that, when selected, records an end time associated with the user identifier; receive a selection of the second user interface element; and send at least one of the start time or the end time to a remote server via the network device.

Abstract: In general, the disclosure describes techniques for creating runtime-throttleable neural networks (TNNs) that can adaptively balance performance and resource use in response to a control signal. For example, runtime-TNNs may be trained to be throttled via a gating scheme in which a set of disjoint components of the neural network can be individually “turned off” at runtime without significantly affecting the accuracy of NN inferences. A separate gating neural network may be trained to determine which trained components of the NN to turn off to obtain operable performance for a given level of resource use of computational, power, or other resources by the neural network. This level can then be specified by the control signal at runtime to adapt the NN to operate at the specified level and in this way balance performance and resource use for different operating conditions.

Abstract: Techniques are disclosed for training a deep neural network (DNN) for reduced computational resource requirements. A computing system includes a memory for storing a set of weights of the DNN. The DNN includes a plurality of layers. For each layer of the plurality of layers, the set of weights includes weights of the layer and a set of bit precision values includes a bit precision value of the layer. The weights of the layer are represented in the memory using values having bit precisions equal to the bit precision value of the layer. The weights of the layer are associated with inputs to neurons of the layer. Additionally, the computing system includes processing circuitry for executing a machine learning system configured to train the DNN. Training the DNN comprises optimizing the set of weights and the set of bit precision values.

Abstract: A low-cost, low-power, stand-alone sensor platform having a visible-range camera sensor, a thermopile array, a microphone, a motion sensor, and a microprocessor that is configured to perform occupancy detection and counting while preserving the privacy of occupants. The platform is programmed to extract shape/texture from images in spatial domain; motion from video in time domain; and audio features in frequency domain. Embedded binarized neural networks are used for efficient object of interest detection. The platform is also programmed with advanced fusion algorithms for multiple sensor modalities addressing dependent sensor observations. The platform may be deployed for (i) residential use in detecting occupants for autonomously controlling building systems, such as HVAC and lighting systems, to provide energy savings, (ii) security and surveillance, such as to detect loitering and surveil places of interest, (iii) analyzing customer behavior and flows, (iv) identifying high performing stores by retailers.