Abstract: A computer-implemented method includes: initializing model parameters for training a neural network; performing a forward pass and backpropagation for a first minibatch of training data; determining a new weight value for each of a plurality of nodes of the neural network using a gradient descent of the first minibatch; for each determined new weight value, determining whether to update a running mean corresponding to a weight of a particular node; based on a determination to update the running mean, calculating a new mean weight value for the particular node using the determined new weight value; updating the weight parameters for all nodes based on the calculated new mean weight values corresponding to each node; assigning the running mean as the weight for the particular node when training on the first minibatch is completed; and reinitializing running means for all nodes at a start of training a second minibatch.

Abstract: A vital signs monitoring system includes a peak pattern detection module configured to output a peak prediction signal from sensor signals based on a peak prediction algorithm; a vital sign estimating module configured to estimate a vital sign based on the peak prediction signal; an activity and context detector module configured to output a context signal based on at least one environmental condition and/or activity level of the person; and a concept drift detection module configured to output a drift signal based on drift detected in the estimated vital sign. The peak pattern prediction module is configured to update the peak prediction algorithm based on the context signal and the drift signal.

Abstract: A method of operating a heating ventilation and air conditioning (HVAC) system of a structure, includes collecting first sensor data corresponding to a parameter of the HVAC system, collecting second sensor data that is different than the first sensor data, and generating clustered data by clustering the first sensor data and the second sensor data into a plurality of data clusters with a controller. The method also includes forming a transactional dataset based on at least the first sensor data, the second sensor data, and the clustered data with the controller, performing association rule mining (ARM) on the transactional dataset to generate a plurality of rules for each data cluster of the plurality of data clusters with the controller, and changing an operating characteristic of the HVAC system based on the plurality of rules with the controller to optimize the parameter.

Abstract: A computer-implemented method includes: initializing model parameters for training a neural network; performing a forward pass and backpropagation for a first minibatch of training data; determining a new weight value for each of a plurality of nodes of the neural network using a gradient descent of the first minibatch; for each determined new weight value, determining whether to update a running mean corresponding to a weight of a particular node; based on a determination to update the running mean, calculating a new mean weight value for the particular node using the determined new weight value; updating the weight parameters for all nodes based on the calculated new mean weight values corresponding to each node; assigning the running mean as the weight for the particular node when training on the first minibatch is completed; and reinitializing running means for all nodes at a start of training a second minibatch.

Abstract: A method of operating a heating ventilation and air conditioning (HVAC) system of a structure, includes collecting first sensor data corresponding to a parameter of the HVAC system, collecting second sensor data that is different than the first sensor data, and generating clustered data by clustering the first sensor data and the second sensor data into a plurality of data clusters with a controller. The method also includes forming a transactional dataset based on at least the first sensor data, the second sensor data, and the clustered data with the controller, performing association rule mining (ARM) on the transactional dataset to generate a plurality of rules for each data cluster of the plurality of data clusters with the controller, and changing an operating characteristic of the HVAC system based on the plurality of rules with the controller to optimize the parameter.

Abstract: A method of training a supervised neural network to solve an optimization problem that involves minimizing an error function ƒ(?) where ? is a vector of independent and identically distributed (i.i.d.) samples of a target distribution £t is proposed. The method includes generating an adversarial probabilistic regularizer (APR) ?£t(?) using a discriminator of a generative adversarial network. The discriminator receives samples from ? and samples from a regularizer distribution pr as inputs. The APR ?£t(?) is then added to the error function ƒ(?) for each training iteration of the supervised neural network.

Abstract: A vital signs monitoring system includes a peak pattern detection module configured to output a peak prediction signal from sensor signals based on a peak prediction algorithm; a vital sign estimating module configured to estimate a vital sign based on the peak prediction signal; an activity and context detector module configured to output a context signal based on at least one environmental condition and/or activity level of the person; and a concept drift detection module configured to output a drift signal based on drift detected in the estimated vital sign. The peak pattern prediction module is configured to update the peak prediction algorithm based on the context signal and the drift signal.

Abstract: A search framework for finding effective architectural building blocks for deep convolutional neural networks is disclosed. The search framework described herein utilizes a building block which incorporates branch and skip connections. At least some operations of the architecture of the building block are undefined and treated as hyperparameters which can be automatically selected and optimized for a particular task. The search framework uses random search over the reduced search space to generate a building block and repeats the building block multiple times to create a deep convolutional neural network.

Abstract: A search framework for finding effective architectural building blocks for deep convolutional neural networks is disclosed. The search framework described herein utilizes a building block which incorporates branch and skip connections. At least some operations of the architecture of the building block are undefined and treated as hyperparameters which can be automatically selected and optimized for a particular task. The search framework uses random search over the reduced search space to generate a building block and repeats the building block multiple times to create a deep convolutional neural network.

Abstract: A prognostics module includes a systems analysis module and a determination module. The systems analysis module is configured to obtain operational information corresponding to a system-wide operation of a multi-element system. The multi-element system includes multiple elements communicatively coupled by at least one common communication link. The determination module is configured to determine a future health of at least one of the multiple elements of the multi-element system using the operational information corresponding to the system-wide operation of the multi-element system.

Abstract: A system and method for text-mining to conduct diagnostics and prognostics using temporal multi-dimensional sensor observations is disclosed. A computer device stores historical time-series data for a plurality of systems. The computer device collects current time-series data from one or more sensors of a first system. The computer device compares the current time-series data to the historical time-series data to identify patterns in both the current time-series data and the historical time-series data. The computer device generates a failure likelihood prediction for the first system based on the identified patterns in the current time-series data and the historical time-series data.

Abstract: A prognostics module includes a systems analysis module and a determination module. The systems analysis module is configured to obtain operational information corresponding to a system-wide operation of a multi-element system. The multi-element system includes multiple elements communicatively coupled by at least one common communication link. The determination module is configured to determine a future health of at least one of the multiple elements of the multi-element system using the operational information corresponding to the system-wide operation of the multi-element system.

Abstract: A method, medium, and system to receive actual operational flight data for an engine of a particular type and configuration; train a neural network to generate an indicator of the health of the engine based on multiple different inputs to the neural network at a time the flight data was acquired; determine a deterioration factor for the engine, based at least in part, on an operational climate for the engine; and provide a record of the determined deterioration factor.

Abstract: A prognostics module includes a systems analysis module and a determination module. The systems analysis module is configured to obtain operational information corresponding to a system-wide operation of a multi-element system. The multi-element system includes multiple elements communicatively coupled by at least one common communication link. The determination module is configured to determine a future health of at least one of the multiple elements of the multi-element system using the operational information corresponding to the system-wide operation of the multi-element system.