Abstract: A method of training an artificial neural network having a series of layers and at least one weight matrix encoding connection weights between neurons in successive layers. The method includes receiving, at an input layer of the series of layers, at least one input, generating, at an output layer of the series of layers, at least one output based on the at least one input, generating a reward based on a comparison of between the at least one output and a desired output, and modifying the connection weights based on the reward. Modifying the connection weights includes maintaining a sum of synaptic input weights to each neuron to be substantially constant and maintaining a sum of synaptic output weights from each neuron to be substantially constant.

Abstract: Methods and systems are provided for monitoring a fuel injector of an internal combustion engine. In one embodiment, a method includes: receiving a set of feature data, the feature data sensed from a fuel injector during a fuel injection event; processing, by a processor, the set of feature data with a decision tree model to generate a prediction of a fault status; and selectively generating, by the processor, a notification signal based on the prediction.

Abstract: Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

Abstract: Methods and systems are provided for monitoring a fuel injector of an internal combustion engine. In one embodiment, a method includes: receiving a set of feature data, the feature data sensed from a fuel injector during a fuel injection event; processing, by a processor, the set of feature data with a decision tree model to generate a prediction of a fault status; and selectively generating, by the processor, a notification signal based on the prediction.

Abstract: An autonomous vehicle, system and method for operating the autonomous vehicle. The system includes a plurality of solution modules, a state module, a hypothesis resolver and a navigation module. The plurality of solution modules each provide a solution for a future state of an agent. The state module that provides an environmental state. The hypothesis resolver receives the environmental state and the plurality of solutions, selects a solution from the plurality of solutions based on the environmental state and determines a reward for the solution, the reward indicating a confidence level of the solution for the environmental state. The navigation module navigates the autonomous vehicle based on the selected solution.

Abstract: A method of training an artificial neural network having a series of layers and at least one weight matrix encoding connection weights between neurons in successive layers. The method includes receiving, at an input layer of the series of layers, at least one input, generating, at an output layer of the series of layers, at least one output based on the at least one input, generating a reward based on a comparison of between the at least one output and a desired output, and modifying the connection weights based on the reward. Modifying the connection weights includes maintaining a sum of synaptic input weights to each neuron to be substantially constant and maintaining a sum of synaptic output weights from each neuron to be substantially constant.

Abstract: Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

Abstract: A system and method is provided for thermally conditioning a sleep environment and managing skin temperature of a user. The thermal system and method include a heat exchanger and controller configured to conductively cool and heat a user during sleep and at other times. The thermal system provides for management of skin temperature of a user, such that sleep comfort and/or quality may be improved, and the thermal system may take advantage of reduced sensitivity of a sleeper during deep sleep for more aggressive thermal manipulation of skin temperature via the conductive cooling. In addition, the thermal system may be further configured to condition the sleep environment when the user is not present based on pre-sleep or maintenance considerations.

Abstract: A communication device having automated filtering based on mental state decisions of the present invention includes a brainwave sensing device that has sensors positioned on a user which can wirelessly communicate the mental state(s) of the user through a signal conditioner to portable electronic device. Subsequently, when the portable electronic device receives signals from a communication system, such as a call or a message, the calls or messages can be either be allowed or interrupted and stored depending on the mental state of the user. Thus, by using the mental state of the user, the portable electronic device can control the communication between the device and a telephone or message system to prevent interruptions during periods of intense focus, for example. In addition, this application provides methods for operating the communication device having automated filtering based on mental state decisions of the present invention.

Abstract: A communication device having automated filtering based on mental state decisions of the present invention includes a brainwave sensing device that has sensors positioned on a user which can wirelessly communicate the mental state(s) of the user through a signal conditioner to portable electronic device. Subsequently, when the portable electronic device receives signals from a communication system, such as a call or a message, the calls or messages can be either be allowed or interrupted and stored depending on the mental state of the user. Thus, by using the mental state of the user, the portable electronic device can control the communication between the device and a telephone or message system to prevent interruptions during periods of intense focus, for example. In addition, this application provides methods for operating the communication device having automated filtering based on mental state decisions of the present invention.

Abstract: A method and system comprising: generating at least one slice image by carpeting a multitude of digital images based upon a two-dimensional (2-D) reference system, each of the multitude of digital images associated with a location in the 2-D reference system and each showing a representation of an arborization and/or landmark such that digital images not showing a representation of an arborization and/or landmark are excluded; carpeting the multitude of digital images together to create a slice image; aligning the slice image with other similarly created slice images using landmark information to determine the amount of 2-D rotation and/or translation to be applied to each slice image; vectorizing the representation of the arborization on each slice image, the vectorization creating a series of segments; assigning a type to at least one of the series of segments based on a unique characteristic of arborization; and grouping related segments together.

Abstract: A neuronal measurement tool including: an input module, a grouping module, a metric selection module, a statistical test selection module, a raw measurement module, a clustering module and a statistical test module. The input module inputs digitally reconstructed neuronal morphologies. The grouping module groups the digitally reconstructed neuronal morphologies into groups. The metric selection module selects at least one metric of interest. The statistical test selection module selects a statistical test method. The raw measurement module gathers raw measurements associated with the metric(s) of interest on the digitally reconstructed neuronal morphologies. The clustering module clusters the raw measurements into groups and the statistical test module performs the statistical test method between the raw measurements clustered in the groups.

Abstract: An arborization reconstructor comprising a slice image generator, a vectorizer, a segment typer, and an arborization grouper. The slice image generator constructs at least two slice images by carpeting digital images based upon a 2-D reference system. Each of the digital images is associated with a location in the 2-D reference system. Each of the slice images has a different z-coordinate and at least one of the digital images shows a representation of at least a part of an arborization. The vectorizer is configured to vectorize at least one representation of an arborization on at least one slice image where the vectorization creating a series of segments. The segment typer assigns a type to segments based on a unique characteristic and the arborization grouper clusters related segments that represent at least one arborization.