Abstract: An HVAC controller is configured to receive signals from a plurality of sensors positioned in different spaces. The HVAC controller includes a controller that is configured to display one or more screens on a user interface that include a home screen including a selectable display element that indicates a number of the plurality of sensors that are currently being used by the controller in controlling the HVAC system. Upon selection of the selectable display element, the controller displays a sensor priority screen that includes a plurality of graphic constructs that each identify a building space and a current temperature for that building space. The controller is configured to control the HVAC system in accordance with the current temperature reported by each of the number of the plurality of sensors that are currently being used by the controller in controlling the HVAC system.

Abstract: Certain aspects involve optimizing neural networks or other models for assessing risks and generating explanatory data regarding predictor variables used in the model. In one example, a system identifies predictor variables. The system generates a neural network for determining a relationship between each predictor variable and a risk indicator. The system performs a factor analysis on the predictor variables to determine common factors. The system iteratively adjusts the neural network so that (i) a monotonic relationship exists between each common factor and the risk indicator and (ii) a respective variance inflation factor for each common factor is sufficiently low. Each variance inflation factor indicates multicollinearity among the common factors. The adjusted neural network can be used to generate explanatory indicating relationships between (i) changes in the risk indicator and (ii) changes in at least some common factors.

Abstract: There is provided a technique that includes: a main controller configured to execute a process recipe including a plurality of steps to perform a predetermined process on a substrate so as to acquire device data when executing the process recipe; and a storage part configured to store the acquired device data, wherein the main controller is configured to: acquire the device data in a predetermined specific step among the steps constituting the process recipe; calculate a value of the acquired device data in the specific step; compare the calculated value with a value of the device data in the specific step calculated at a time of previous execution of the process recipe; and generate an alarm when the calculated value shows a predefined tendency.

Abstract: A wafer supply device configured to supply a wafer divided into multiple dies to a supply position, the wafer supply device includes a die information storage section configured to store the number of dies for each rank allocated to each of the dies, a block information acquisition section configured to acquire a condition of dies to be mounted on a block provided on a board to be conveyed, a required block number acquisition section configured to acquire a required number of dies to be mounted on the block, and a producible number calculation section configured to calculate a number of blocks that can be produced based on a content stored in the die information storage section and a content acquired by the block information acquisition section and the required block number acquisition section.

Abstract: A control layer automation device comprises a processor, one or more control layer applications, a database, a wireless interface, a device memory. Each control layer application is configured to perform a discrete set of automation functions. The database comprises a plurality of operator device identifiers and the wireless interface allows the one or more control layer applications to communicate with a plurality of operator devices via the plurality of operator device identifiers. The device memory comprises the one or more control layer applications. The control layer application manager is configured to manage execution of the one or more control layer applications on the processor.

Abstract: At least one neural network accelerator performs operations of a first subset of layers of a neural network on an input data set, generates an intermediate data set, and stores the intermediate data set in a shared memory queue in a shared memory. A first processor element of a host computer system provides input data to the neural network accelerator and signals the neural network accelerator to perform the operations of the first subset of layers of the neural network on the input data set. A second processor element of the host computer system reads the intermediate data set from the shared memory queue, performs operations of a second subset of layers of the neural network on the intermediate data set, and generates an output data set while the neural network accelerator is performing the operations of the first subset of layers of the neural network on another input data set.

Abstract: The operation of an automatic data input and query system is controlled by well-defined control data. Certain control data may relate to data schemas and direct operations performed by the system to extract fields from machine data. Automatic methods may determine proper field extraction control information by analyzing a sample of data from a source, breaking the sample data into event segments, classifying the segments into groups based on a measure of similarity, determining an operable extraction rule for each group, and storing the resulting extraction model. Data patterns known by the system can be leveraged to perform the event breaking and field identification for the classifying. Embodiments may provide a user interface to view, interact with, and approve the computer-generated extraction model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

Abstract: An apparatus, a method, a method of manufacturing and apparatus, and a method of constructing an integrated circuit are provided. The apparatus includes a teacher network; a student network; a plurality of knowledge bridges between the teacher network and the student network, where each of the plurality of knowledge bridges provides a hint about a function being learned, and where a hint includes a mean square error or a probability; and a loss function device connected to the plurality of knowledge bridges and the student network. The method includes training a teacher network; providing hints to a student network by a plurality of knowledge bridges between the teacher network and the student network; and determining a loss function from outputs of the plurality of knowledge bridges and the student network.

Abstract: A surveillance system is coupled to a plurality of sensor data sources arranged at locations within a plurality of regions of a site under surveillance. The surveillance system accesses a threat model that identifies contextual events classified as threats. The surveillance system identifies at least one contextual event for a site in real-time by processing sensor data generated by the sensor data sources, and co-occurring contextual data for at least one of the regions. Each identified contextual event is classified as one of a threat and a non-threat by using the threat model.

Abstract: Systems, methods, and non-transitory computer readable media are configured to receive a uniform resource locator. A time and one or more features associated with the uniform resource locator can be provided to a first machine learning model. A prediction relating to a quantity of views the uniform resource locator achieves by the time can be received from the first machine learning model.

Abstract: Computer-implemented systems and methods build ensembles for deep learning through parallel data splitting by creating and training an ensemble of up to 2n ensemble members based on a single base network and a selection of n network elements. The ensemble members are created by the “blasting” process, in which training data are selected for each of the up to 2n ensemble members such that each of the ensemble members trains with updates in a different direction from each of the other ensemble members. The ensemble members may also be trained with joint optimization.

Abstract: The present teaching relates to generating user profiles with semantic knowledge. A first information associated with a user is obtained. One or more entities are identified from the first information. The one or more entities are augmented based on second information to generate a set of augmented entities. The set of augmented entities are clustered into a set of hierarchical clusters. A set of user profiles is generated based on the set of hierarchical clusters so that the user profile is to be used to personalize content recommendation.

Abstract: Technologies for providing convolutional neural networks are described. An analysis component determines an initial convolutional layer in a network architecture of a convolutional neural network and one or more subsequent convolutional layers in the network architecture. A replacement component replaces original convolutional kernels in the initial convolutional layer with initial sparse convolutional kernels, and replaces subsequent convolutional kernels in one or more subsequent convolutional layers with complementary sparse convolutional kernels. The complementary sparse kernels have a complementary pattern with respect to sparse kernels of a previous convolutional layer. Analyzing the network architecture and a trained model of a convolutional neural network can determine the original convolutional kernels and replace those kernels with sparse kernels based on similarity and/or weight in an initial layer, with sparse complementary kernels used in subsequent layers.

Abstract: Incremental generation of models with dynamic clustering. A first set of data is received. A first set of clusters based on the first set of data is generated. A respective first set of models for the first set of clusters is created. A second set of data is received. A second set of clusters, based on the second set of data and based on a subset of the first set of data, is generated. A respective second set of models for the second set of clusters, based on a subset of the first set of models and based on the second set of data, is created.

Abstract: A method of analyzing unstructured messages is provided. The method includes extracting a content feature from an embedding associated with each message from a pair of unstructured messages using a neural network, generating, based on extracted content features, a text similarity score between the pair of messages using a second neural network, combining the generated text similarity score with additional data associated with the messages to generate a total similarity score, and generating a message thread based on the generated total similarity score for the pair of messages selected from the plurality of unstructured messages.

Abstract: A method of automating a fraud classification process includes generating or updating fraud classification rules, at least by training a machine learning program using fraud classifications of a plurality of financial accounts and financial transaction data associated with those accounts. The method also includes retrieving first financial transaction data associated with a first financial account, and selecting, by applying the fraud classification rules to the first financial transaction data, a first fraud classification. The first fraud classification may be selected from among a plurality of predetermined fraud classifications. The method also includes causing an indication of the first fraud classification to be displayed to one or more people via one or more respective computing device user interfaces, the indication further specifying at least the first financial account.

Abstract: Techniques to mimic a target food item using artificial intelligence are disclosed. A formula generator learns from open source and proprietary databases of ingredients and recipes. The formula generator is trained using features of the ingredients and using recipes. Given a target food item, the formula generator determines a formula that matches the given target food item and a score for the formula. The formula generator may generate, based on user-provided control definitions, numerous formulas that match the given target food item and may select an optimal formula from the generated formulas based on score.

Abstract: A method may include a processor training a machine learning model with a training data set, computing a data distribution of the training data set, processing a stream of new data to determine a likelihood of the new data from the data distribution that is computed, incrementing a counter when the likelihood of the new data is less than a first threshold, and retraining the machine learning model when the counter exceeds a second threshold.

Abstract: A motion processing analysis method, system, and computer program product include selecting a first spatial graticule size, determining that a physical entity is associated with a first spatial graticule during a first timeframe and that the physical entity is associated with a second spatial graticule during a second timeframe, as a result of determining that the physical entity is associated with the first spatial graticule during the first timeframe and that the physical entity is associated with the second spatial graticule during the second timeframe, adding to a sum, determining that the sum is beyond an acceptable range, and as a result of determining that the sum beyond the acceptable range, selecting a second spatial graticule size.