Abstract: Compact and portable, real-time or near real-time, in-line, on-line, at-line, or off-line reagentless detection, identification, and/or quantification spectroscopic methods and sensor systems provide detection and quantification of chemical and biological (CB) materials or analytes (whether harmful or beneficial) at trace quantities and concentrations (e.g., at less than 10 ppb, 10 ppt, or 10 ppq). Some embodiments detect trace volumes of materials of interest that were originally in water or another liquid wherein detection is enhanced by one or more of (1) liquid reduction or elimination, (2) overlaid multi-droplet deposition, (3) analyte spatial separation, and/or (4) creation and storage of analyte sample archives in a readily accessible manner for future re-examination.

Abstract: Methods, apparatus and systems for wireless monitoring and tracking are described. In one example, a described method of a wireless monitoring system comprises: transmitting a wireless signal that is impacted by a wireless multipath channel in a venue and a modulation of an object undergoing a motion in the venue, to obtain a set of channel information (CI) of the wireless multipath channel; performing a monitoring task by monitoring the object and the motion; determining a plurality of admissible system states of the wireless monitoring system, wherein each admissible system state is associated with a respective setting of at least one of: the wireless signal, a series of sounding signals in the wireless signal, or the monitoring task; choosing one of the admissible system states to be a system state of the wireless monitoring system based on the monitoring task; and applying a setting associated with the chosen admissible system state to the wireless monitoring system.

Abstract: An air handler unit for use with residential heating, ventilation, and air conditioning (HVAC) systems. The air handler unit has high resistance mediums (HRMs) coupled closely to a wide-angle vane-diffuser mixed-flow fan system. The HRMs are placed immediately upstream and downstream of the wide-angle vane-diffuser mixed-flow fan to form a closely coupled, compact air handler that provides significant efficiency and noise benefits.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.

Abstract: The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more attentive layers that each include a gated attention unit.

Abstract: A method for monitoring a file system within a distributed network is provided. From a local hosting environment having a native scanning tool, creation of a new data store within the network is detected. Responsive to detecting creation of the new data store, it is determined whether the new data store is physically located within a foreign hosting environment that is communicatively coupled to the local hosting environment through a non-private network. If the new data store is physically located within the foreign hosting environment, an agent of the native scanning tool is created within the foreign hosting environment and the agent is applied to the new data store within the foreign hosting environment to obtain sensitivity information for the new data store. The sensitivity information for the new data store is received and recorded in the local hosting environment.

Abstract: The rate limiter circuits in the packet processing chip of a NIC are a limited hardware resource that may limit the number of workloads that can be run on a server. Some such chips include an egress packet processing pipeline circuit and a second packet processing pipeline circuit that prepares work for the egress pipeline circuit. Some of the stages of the second pipeline circuit can be configured as a first limiter and a second limiter that implement aspects of different rate limiters such as IOPS limiters, bandwidth limiters, etc. Another pipeline stage can use the outputs of the different rate limiters to make a limiting decision that is written into one of the rate limiter circuits. The second pipeline circuit is thereby implementing virtualized rate limiters where one of the rate limiter circuits performs the rate limiting for the virtualized rate limiters.

Abstract: A computer-implemented method according to one embodiment includes performing object detection on a frame to identify a set of objects within the frame, and determining a location of each object of the set of objects within the frame. The method further includes constructing a code tree structure for the frame. The code tree structure defines the determined locations. A rule defining modifications to make to at least some of the objects is received and the code tree structure is crawled. The rule is applied to the objects during the crawling. The method further includes layering the modifications defined in the rule on the set of objects within the frame. A computer program product according to another embodiment includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a computer to cause the computer to perform the foregoing method.

Abstract: The disclosed embodiments include computerized methods, systems, and devices, including computer programs encoded on a computer storage medium, for generating terms of a search query based on a user's spoken utterances, identifying multiple cross-platform messages based on the generated terms, and to generating, via a presentation device, a single interface that enables the user to interact with identified messages. Based on a spoken utterance, the disclosed embodiments may determine user-specified search terms and/or criteria, and based on the user-specified search terms and/or criteria, may obtain cross-platform message data that corresponds to the search query. The communications device may generate one or more interface elements that describe corresponding ones of the cross-platform messages, which may be presented within a unified graphical user interface or voice-user interface by a communications device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more expert neural network blocks that each include router that performs expert-choice routing between multiple expert neural networks.

Abstract: A method includes: receiving a prompt from an operator to initialize a current instance of a first instructional block, in a digital procedure, at a workspace assigned to the operator within a facility; in response to detecting a risk event proximal the workspace, accessing a procedure authoring model associated with a first equipment unit proximal the workspace; correlating the risk event with an action language signal corresponding to an action prompt related to the first equipment unit; correlating the risk event with a risk language signal corresponding to a first process risk associated with execution of the first action prompt with the first equipment unit; based on the action language signal, the risk language signal, and the procedure authoring model, generating a sequence of steps predicted to resolve the risk event; and initializing a second instructional block containing the sequence of steps predicted to resolve the risk event.

Abstract: Systems and methods are provided for efficiently calibrating a data mixture for training machine-learned models (e.g., machine-learned sequence processing models, such as transformer-based models). For example, machine-learned models can be trained over a broad dataset that can include multiple different categories of data. The mixture of data categories within the dataset can influence model performance. To improve the performance of machine-learned models, example implementations of the present disclosure can learn a distribution of data categories using a lightweight proxy model before initiating training of a large primary model. In this manner, for instance, example implementations can obtain an improved training data distribution with less computational expense and can leverage the learned training data distribution to better train a large primary model.

Abstract: A method performed by a processing system including at least one processor includes collecting a set of data from a plurality of sensors that is monitoring a system, wherein the plurality of sensors includes sensors of a plurality of different modalities, detecting an instance of out-of-distribution data in the set of data by providing the set of data as an input to a machine learning model that generates as an output an indicator that the instance of out-of-distribution data is out-of-distribution with respect to the set of data, identifying a root cause for the instance of out-of-distribution data, and initiating an action to remediate the root cause of the instance of out-of-distribution data.

Abstract: Systems and methods are provided that train a machine-learned language encoding model through the use of a contrastive learning task. In particular, the present disclosure describes a contrastive learning task where the encoder learns to distinguish input tokens from plausible alternatives. In some implementations, on each training example the proposed method masks out some subset (e.g., 15%) of the original input tokens, replaces the masked tokens with samples from a “generator” (e.g., which may be a small masked language model), and then trains the encoder to predict whether each token comes from the original data or is a replacement produced by the generator.

Abstract: The disclosure relates to compounds of formula (I), which are formyl peptide 2 (FPR2) receptor agonists and/or formyl peptide 1 (FPR1) receptor agonists. The disclosure also provides compositions and methods of using the compounds, for example, for the treatment of atherosclerosis, heart failure, and related diseases.

Abstract: Assets in a virtual environment are assigned to locations based on attributes of the locations, such as light level, temperature, etc. Attributes are determined based on simulating the virtual environment. The virtual environment can be simulated over a period of time, during which multiple attribute values can be recorded, resulting in an aggregated attribute value to better enable more immersive asset placement.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip placement. One of the methods includes training, through reinforcement learning, a node placement neural network that is configured to, at each of a plurality of time steps, receive an input representation comprising data representing a current state of a placement of a netlist of nodes on a surface of an integrated circuit chip as of the time step and process the input representation to generate a score distribution over a plurality of positions on the surface of the integrated circuit chip.

Abstract: Techniques are described herein for using a smart device such as a standalone assistant-centric interactive speaker and/or a standalone assistant-centric interactive display with speaker(s) to send a message using a messaging application on a client device such as a smartphone. A method includes: receiving, by a first device, a request from a first user to send a message to a second user; determining that a messaging application corresponding to the request is unavailable on the first device; and in response to determining that the messaging application corresponding to the request is unavailable on the first device: selecting a second device on which the messaging application corresponding to the request is available; and sending, to the second device, a command that causes the second device to send the message from the first user to the second user using the messaging application on the second device.

Abstract: Mechanisms are provided for rendering virtual objects in a computer generated virtual environment. Physical environment condition data is received and transformed into UV map data structure(s), where each UV map data structure comprises entries that store one or more environment condition values mapped from the physical environment condition data to the UV map data structure. A customized shader processes the UV map data structure(s) to apply environment condition effects to a rendering of a virtual object corresponding to the customized shader. The customized shader executes on the environment condition data of the UV map data structure(s) and specifies a modification to a representation of the virtual object due to the environment condition values represented in the UV map data structure(s). Generation of the virtual object in the virtual environment is controlled based on results of processing the one or more UV map data structures by the customized shader.