Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps, processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence, processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

Abstract: Generally, the present disclosure is directed to systems and methods that generate augmented training data for machine-learned models via application of one or more augmentation techniques to audiographic images that visually represent audio signals. In particular, the present disclosure provides a number of novel augmentation operations which can be performed directly upon the audiographic image (e.g., as opposed to the raw audio data) to generate augmented training data that results in improved model performance. As an example, the audiographic images can be or include one or more spectrograms or filter bank sequences.

Abstract: Aberrant cross talk between Notch ligand (e.g. Jag1) and Notch receptor (e.g. Notch1) has been implicated in tumorigenesis in the colon. Inhibition of Notch pathway is therefore an attractive approach for treating diseases with upregulated Jag1 e.g. colorectal cancer (CRC). Pan-notch inhibitors like gamma secretase inhibitors (GSIs) have been developed to inhibit Notch and its downstream events. However, severe gastrointestinal toxicity profiles impede the clinical development of GSIs. The present invention develops novel oligopeptides that specifically inhibit Jag1-Notch1 pathway without interfering DLL1-Notch1 or DLL4-Notch1, which demonstrates a clear advantage over pan-notch inhibitors.

Abstract: Aberrant cross talk between Notch ligand (e.g. Jag1) and Notch receptor (e.g. Notch1) has been implicated in tumorigenesis in the colon. Inhibition of Notch pathway is therefore an attractive approach for treating diseases with upregulated Jag1 e.g. colorectal cancer (CRC). Pan-notch inhibitors like gamma secretase inhibitors (GSIs) have been developed to inhibit Notch and its downstream events. However, severe gastrointestinal toxicity profiles impede the clinical development of GSIs. The present invention develops novel oligopeptides that specifically inhibit Jag1-Notch1 pathway without interfering DLL1-Notch1 or DLL4-Notch1, which demonstrates a clear advantage over pan-notch inhibitors.

Abstract: A speech recognition neural network system includes an encoder neural network and a decoder neural network. The encoder neural network generates an encoded sequence from an input acoustic sequence that represents an utterance. The input acoustic sequence includes a respective acoustic feature representation at each of a plurality of input time steps, the encoded sequence includes a respective encoded representation at each of a plurality of time reduced time steps, and the number of time reduced time steps is less than the number of input time steps. The encoder neural network includes a time reduction subnetwork, a convolutional LSTM subnetwork, and a network in network subnetwork. The decoder neural network receives the encoded sequence and processes the encoded sequence to generate, for each position in an output sequence order, a set of sub string scores that includes a respective sub string score for each substring in a set of substrings.

Abstract: A real time medical communication system for sending Notifications of medical Alerts includes a data translation layer for receiving real time medical data from one or more sources via a network and an Alerts engine. The Alerts engine may include a message processing module including an entity extraction module configured to extract entities from the real time medical data; and a fragment generation module configured to define fragments comprising events of interest for defining one or more medical Alerts. The Alerts engine may further include an Alert generation module that may include fragment query and evaluation modules for analyzing received real time medical data for defined fragments and generating one or more medical Alerts therefrom. A Notification module may also be provided for sending Notifications of Alerts to users.

Abstract: In clinical documentation, mere documentation of a condition in a patient's records may not be enough. To be considered sufficiently documented, the patient's record needs to show that no documentation drop-offs (DDOs) have occurred over the course of the patient's stay. However, DDOs can be extremely difficult to detect. To solve this problem, the invention trains time-sensitive deep learning (DL) models on a per condition basis using actual and/or synthetic patient data. Utilizing an ontology, grouped concepts can be generated on the fly from real-time hospital data and used to generate time-series data that can then be analyzed by trained time-sensitive DL models to determine whether a DDO for a condition has occurred during the stay. Non-time-sensitive models can be used to detect all the conditions documented during the stay. Outcomes from the models can be compared to determine whether to notify a user that a DDO has occurred.

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating a data set that associates each text segment in a vocabulary of text segments with a respective numeric embedding. In one aspect, a method includes providing, to an image search engine, a search query that includes the text segment; obtaining image search results that have been classified as being responsive to the search query by the image search engine, wherein each image search result identifies a respective image; for each image search result, processing the image identified by the image search result using a convolutional neural network, wherein the convolutional neural network has been trained to process the image to generate an image numeric embedding for the image; and generating a numeric embedding for the text segment from the image numeric embeddings for the images identified by the image search results.

Abstract: A cloud system may create and support multiple network offerings for virtual machines in a cloud zone. Physical networks comprising sets of network elements, such as routers, gateways, firewalls, load balancers, and other network hardware, may be created and updated within a zone. Network offerings may be defined and associated, using tags or other techniques, with virtual machine networks, physical networks and/or network elements. Cloud end users may request specific network offerings when creating virtual machines, or may request to move existing virtual machines from one network offering to another. The cloud system may use the requested network offering to identify the virtual machine network, physical network, and/or network elements corresponding to the requested network offering. The cloud system may allocate a new virtual machine network and configure the network elements within the associated physical network to provide network services to the virtual machine.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating network outputs using insertion operations.

Abstract: A method of facilitating configuration of at least one sensor with a data transmitter communicatively coupled to an analysis engine for a building management system, wherein the application is configured to be run on a mobile device and interact with the at least one sensor during the installation. The method includes communicating, by the application, with the at least one sensor to display a visual indicator, capturing, by a camera of the mobile device, visual data representative of the visual indicator, and associating the at least one sensor with a circuit of a building power system based on the captured visual data.

Abstract: In clinical documentation, mere documentation of a condition in a patient's records may not be enough. To be considered sufficiently documented, the patient's record needs to show that no documentation drop-offs (DDOs) have occurred over the course of the patient's stay. However, DDOs can be extremely difficult to detect. To solve this problem, the invention trains time-sensitive deep learning (DL) models on a per condition basis using actual and/or synthetic patient data. Utilizing an ontology, grouped concepts can be generated on the fly from real-time hospital data and used to generate time-series data that can then be analyzed by trained time-sensitive DL models to determine whether a DDO for a condition has occurred during the stay. Non-time-sensitive models can be used to detect all the conditions documented during the stay. Outcomes from the models can be compared to determine whether to notify a user that a DDO has occurred.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

Abstract: A clinical documentation improvement (CDI) smart scoring method may include predicting, via per-condition diagnosis machine learning (ML) models and based on clinical evidence received by a system, a probability that a medical condition is under-documented and, via per-condition documentation ML models and based on documentation received by the system, a probability that a medical condition is over-documented. The under- and over-documentation scores are combined in view of special indicators and queryability factors, which can also be evaluated using ML query prediction models, to generate an initial CDI score. This CDI score can be further adjusted, if necessary or desired, to account for factors such as length of stay, payer, patient location, CDI review timing, etc. The final CDI score can be used to prioritize patient cases for review by CDI specialists to quickly and efficiently identify meaningful CDI opportunities.

Abstract: A method of facilitating configuration of at least one sensor with a data transmitter communicatively coupled to an analysis engine for a building management system, wherein the application is configured to be run on a mobile device and interact with the at least one sensor during the installation. The method includes communicating, by the application, with the at least one sensor to display a visual indicator, capturing, by a camera of the mobile device, visual data representative of the visual indicator, and associating the at least one sensor with a circuit of a building power system based on the captured visual data.

Abstract: A building management system including a local power system that delivers power to devices at a location, a data collector system coupled to the local power system, to monitor aggregate power used at a location, including at least one circuit based sensor configured to collect power usage data, each of the at least one sensors being clamped onto a circuit basis, and a data transmitter coupled to the at least one sensor and communicating the collected power usage data over a network to a cloud analyzer system, a tracker application configured to provide real-time reporting, alerts, and control via the network, and to be executed by a processor in an operating system (OS), in a native or virtual environment, wherein the tracker interacts with an analysis engine to map out energy use inside of a building on an individual circuit basis.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating network outputs using insertion operations.

Abstract: A real time medical communication system for sending Notifications of medical Alerts includes a data translation layer for receiving real time medical data from one or more sources via a network and an Alerts engine. The Alerts engine may include a message processing module including an entity extraction module configured to extract entities from the real time medical data; and a fragment generation module configured to define fragments comprising events of interest for defining one or more medical Alerts. The Alerts engine may further include an Alert generation module that may include fragment query and evaluation modules for analyzing received real time medical data for defined fragments and generating one or more medical Alerts therefrom. A Notification module may also be provided for sending Notifications of Alerts to users.

Abstract: A clinical documentation improvement (CDI) smart scoring method may include predicting, via per-condition diagnosis machine learning (ML) models and based on clinical evidence received by a system, a probability that a medical condition is under-documented and, via per-condition documentation ML models and based on documentation received by the system, a probability that a medical condition is over-documented. The under- and over-documentation scores are combined in view of special indicators and queryability factors, which can also be evaluated using ML query prediction models, to generate an initial CDI score. This CDI score can be further adjusted, if necessary or desired, to account for factors such as length of stay, payer, patient location, CDI review timing, etc. The final CDI score can be used to prioritize patient cases for review by CDI specialists to quickly and efficiently identify meaningful CDI opportunities.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating network outputs using insertion operations.