Abstract: A general framework for cross-validation of any supervised learning algorithm on a distributed database comprises a multi-layer software architecture that implements training, prediction and metric functions in a C++ layer and iterates processing of different subsets of a data set with a plurality of different models in a Python layer. The best model is determined to be the one with the smallest average prediction error across all database segments.

Abstract: A system, method, and apparatus are provided for automatically establishing an inferred (‘follow’) relationship between a first member and a second member of a user community. Based on passive and/or active signals indicating affinity of the first member for the second member, the system determines whether an inferred connection from the first member to the second member would improve the first member's network within the user community. A potential improvement may be observed if the potential connection would improve some aspect or characteristic of a target or ideal network identified for the first member, and/or if there is more than a threshold level of affinity between the members. The first member's network may be pruned, if necessary, to accommodate a connection to the second member if, for example, the connection would violate a constraint associated with the target or ideal network.

Abstract: A mechanism is provided in a data processing system for predicting and enhancing ingestion time for a set of input documents. The mechanism receives a set of documents to be added to a corpus of the data processing system. The mechanism records document features of each document within the set of documents using an annotation engine within the data processing system. The mechanism predicts an ingestion time for each document within the set of documents based on the document characteristics and a machine learning model. The mechanism assigns the set of documents to data processing system resources to be processed based on the predicted ingestion time for each document.

Abstract: A system for monitoring an environment may include an input device for monitoring and capturing pattern-based states of a model of the environment. The system may also include a 5 thalamobot embodied in at least a first processor, in which the first processor is in communication with the input device. The thalamobot may include at least one filter for monitoring captured data from the input device and for identifying at least one state change within the captured data. The system may also include at least one critic and/or at least one recognition system.

Abstract: Systems and methods for probabilistic semantic sensing in a sensory network are disclosed. The system receives raw sensor data from a plurality of sensors and generates semantic data including sensed events. The system correlates the semantic data based on classifiers to generate aggregations of semantic data. Further, the system analyzes the aggregations of semantic data with a probabilistic engine to produce a corresponding plurality of derived events each of which includes a derived probability. The system generates a first derived event, including a first derived probability, that is generated based on a plurality of probabilities that respectively represent a confidence of an associated semantic datum to enable at least one application to perform a service based on the plurality of derived events.

Abstract: A method of training a neural network includes encouraging one or more filters in the neural network to have a low rank.

Abstract: A technology for path determination using robust optimization is provided. In accordance with one aspect, a network graph of a network is generated. The network graph comprises nodes corresponding to points in the network, and edges which connect the nodes. Costs for each edge of the network are determined and modeled using reference point, upper bound and lower bound parameters. A user input which includes a source node, destination node, and cost target may be received from a client device. A resultant path connecting the source node and destination node are determined by solving a target-oriented robust optimization problem, which optimizes a cost of the resultant path based on the modeled costs of the edges. The resultant path is displayed on a user interface of the client device.

Abstract: A computer implemented method of generating decision options. Sensor data is received from a plurality of sensors and presented visually to two or more users. Those users can then analyze the images and enter tag data which is received and stored along with the sensor data. The sensor and tag data are then input to a computer implemented decision support algorithm along with a stored operational plan. The algorithm then outputs one or more decision options which can assist a human decision maker in making a decision. The invention enables such a decision maker to make a decision quickly which complies with a previously stored operational plan and is likely to be correct since it is based on inputs from multiple human users. The invention is capable of being easily scaled to deal with a high volume of sensor data and a large number of users.

Abstract: A system and method for training a system for monitoring administration of medication. The method includes the steps of a method for training a medication administration monitoring apparatus, comprising the steps of defining one or more predetermined medications and then acquiring information from one or more data sources of a user administering medication. A first network is trained to recognize a first step of a medication administration sequence, and then a second network is trained to recognize a second step of a medication administration sequence based upon the training of the first network.

Abstract: A front-end system collects user attribute value data and organizes the data into one or more training data sets and one or more test data sets. The front-end system provides at least some of the test data sets to an input layer of a machine learning system. Within the machine learning system, one or more predictive models are constructed. At an output layer, the predictive models provide output data that includes at least a value indicative of whether a user will upgrade service levels based at least in part on the attribute values logically associated with the respective user. A back-end system generates upgrade offers for subsequent communication to those users identified as being likely to upgrade.

Abstract: Systems and methods for training a neural network to optimize network performance, including sampling an applied dropout rate for one or more nodes of the network to evaluate a current generalization performance of one or more training models. An optimized annealing schedule may be generated based on the sampling, wherein the optimized annealing schedule includes an altered dropout rate configured to improve a generalization performance of the network. A number of nodes of the network may be adjusted in accordance with a dropout rate specified in the optimized annealing schedule. The steps may then be iterated until the generalization performance of the network is maximized.

Abstract: In accordance with an embodiment, described herein is a system and method for logistic matrix factorization of implicit feedback data, with application to media environments or streaming services. While users interact with an environment or service, for example a music streaming service, usage data reflecting implicit feedback can be collected in an observation matrix. A logistic function can be used to determine latent factors that indicate whether particular users are likely to prefer particular items. Exemplary use cases include providing personalized recommendations, such as personalized music recommendations, or generating playlists of popular artists.

Abstract: Technical solutions are described to accelerate training of a multi-layer convolutional neural network. According to one aspect, a computer implemented method is described. A convolutional layer includes input maps, convolutional kernels, and output maps. The method includes a forward pass, a backward pass, and an update pass that each include convolution calculations. The described method performs the convolutional operations involved in the forward, the backward, and the update passes based on a first, a second, and a third perforation map respectively. The perforation maps are stochastically generated, and distinct from each other. The method further includes interpolating results of the selective convolution operations to obtain remaining results. The method includes iteratively repeating the forward pass, the backward pass, and the update pass until the convolutional neural network is trained. Other aspects such as a system, apparatus, and computer program product are also described.

Abstract: The present disclosure contemplates a variety of improved methods and systems for creating a unique user experience using an ambient operating system connected to a variety of disparate IoT devices. The described solution includes a curated scene or set of actions initiated by an assistant device. For example, the assistant device detects it is a weekday morning and initiates actions associated with the wakeup routine such as opening the blinds, making coffee and notifying the user of the current traffic report.

Abstract: Systems and methods are provided for automatically scoring a constructed response. The constructed response is processed to generate a plurality of numerical vectors that is representative of the constructed response. A model is applied to the plurality of numerical vectors. The model includes an input layer configured to receive the plurality of numerical vectors, the input layer being connected to a following layer of the model via a first plurality of connections. Each of the connections has a first weight. An intermediate layer of nodes is configured to receive inputs from an immediately-preceding layer of the model via a second plurality of connections, each of the connections having a second weight. An output layer is connected to the intermediate layer via a third plurality of connections, each of the connections having a third weight. The output layer is configured to generate a score for the constructed response.

Abstract: Various implementations for simplified product configuration using table-based rule editing, rule conflict resolution through voting, and efficient model compilation are described. In one example implementation, a rule definition table is provided for presentation to a user. One or inputs defining a rule for a model using the rule definition table are received. The rule is compiled into a compiled rule that is executable during evaluation of the model and the model is evaluated based on the compiled rule. Numerous additional implementations are also described.

Abstract: A method, system, and computer program product for weight adjusted composite model for forecasting in anomalous environments are provided in the illustrative embodiments. A base forecasting model and a second forecasting model are combined to form a composite model, the base forecasting model configured to forecast an event in a time series, the second forecasting model configured to represent an anomalous portion of data in the time series. A mixing algorithm is combined with the composite model to adjust a set of weights associated with the composite model. Upon identifying a future period in which the event is to be forecasted, using the mixing algorithm, a subset of the set of weights is adjusted to from a weight adjusted composite model. The weight adjusted composite model is executed to forecast the event in the future period.

Abstract: Systems and methods for training a neural network to optimize network performance, including sampling an applied dropout rate for one or more nodes of the network to evaluate a current generalization performance of one or more training models. An optimized annealing schedule may be generated based on the sampling, wherein the optimized annealing schedule includes an altered dropout rate configured to improve a generalization performance of the network. A number of nodes of the network may be adjusted in accordance with a dropout rate specified in the optimized annealing schedule. The steps may then be iterated until the generalization performance of the network is maximized.

Abstract: A computer-implemented method for determining the volume of activation of neural tissue. In one embodiment, the method uses one or more parametric equations that define a volume of activation, wherein the parameters for the one or more parametric equations are given as a function of an input vector that includes stimulation parameters. After receiving input data that includes values for the stimulation parameters and defining the input vector using the input data, the input vector is applied to the function to obtain the parameters for the one or more parametric equations. The parametric equation is solved to obtain a calculated volume of activation.

Abstract: A system and method is disclosed for predicting user behavior in response to various tasks and or/applications. This system can be a neural network-based joint model. The neural network can include a base neural network portion and one or more task-specific neural network portions. The artificial neural network can be initialized and trained using data from multiple users for multiple tasks and/or applications. This user data can be related to characteristics and behavior, including age, gender, geographic location, purchases, past search history, and customer reviews. Additional task-specific neural network portions can be added to the neural network and may be trained using a task-specific subset of the training data. The joint model can be used to predict user behavior in response to an identified task and/or application. The tasks and/or applications can relate to use of a website by users.