Abstract: Systems and methods are provided for performing multi-objective optimizations with a relatively large number of objectives to which optimization is to be performed. The objectives of the optimization problem may be partitioned to two or more subsets (e.g., overlapping or non-overlapping subsets) of objectives, and partial optimization(s) may be performed using a subset or combination of subsets of the objectives. One or more of the partial optimizations may use one or more pareto-optimized chromosomes from a prior partial optimization. A final full optimization may be performed according to all of the objectives of the optimization problem and may use one or more chromosomes of any preceding partial optimization as a starting point for finding a final solution to the optimization problem. Any variety of processes may be employed to mitigate archive explosion that may be associated with relatively large objective sets.

Abstract: An online system distributes content items describing events to one or more users of the online system. The online system receives, an event from a third-party system, the event associated with one or more content items. The online system determines a vector representation of users based on a first neural network and a vector representation of an event based on a second neural network. The online system jointly trains the first neural network and second neural network based on labels describing user entity relationships. The online system determines a likelihood of attendance of an event by a user based on a distance between the vector representation of the user and the vector representation of the entity. The online system provides the content associated with the event to users of the online system based on the likelihood of attendance of the event by the users.

Abstract: A multi-stage machine learning and recognition system comprises multiple individual machine learning systems arranged in multiple stages, where data is passed from a machine learning system in one stage to one or more machine learning systems in a subsequent, higher-level stage of the structure according to the logic of the machine learning system. The multi-stage machine learning system can be arranged in a final stage and one or more non-final stages, where the one or more non-final stages direct data generally towards a selected one or more machine learning systems within the final stage, but less than all of the machine learning systems in the final stage. The multi-stage machine learning system can additionally include a learning coach and data management system, which is configured to control the distribution of data throughout the multi-stage structure of machine learning systems by observing the internal state of the structure.

Abstract: A facility for optimizing machine learning models is described. The facility obtains a description of a machine learning model and a hardware target for the machine learning model. The facility obtains optimization result data from a repository of optimization result data. The facility optimizes the machine learning model for the hardware target based on the optimization result data.

Abstract: A trained recurrent neural network having a set of control policies learned from application of a template dataset and one or more corresponding template deep network architectures may generate a deep network architecture for performing a task on an application dataset. The template deep network architectures may have an established level or performance in executing the task. A deep network based on the deep network architecture may trained to perform the task on the application dataset. The control policies of the recurrent neural network may be updated based on the performance of the trained deep network.

Abstract: A method for selectively dropping out feature elements from a tensor is disclosed. The method includes generating a mask that has a plurality of mask elements. Each mask element includes a corresponding plurality of bits representing either a first value or a second value, to indicate whether a corresponding feature element of the tensor output by a neural network layer is to be dropped out or retained. Each mask element of the plurality of mask elements of the mask is compressed to generate a corresponding compressed mask element of a plurality of compressed mask elements of a compressed mask, thereby generating the compressed mask from the mask. Each compressed mask element of the plurality of compressed mask elements includes a corresponding single bit. Feature elements are selectively dropped from the tensor, based on the compressed mask.

Abstract: A method for security and/or automation systems is described. In one example, the method may include receiving scheduling data associated with a schedule for each of two or more users at a home automation system. The method may further include comparing the received scheduling data for each of the two or more users, and deriving an alert based, at least in part, on the comparing. The method may further include communicating the alert to at least one of the two or more users.

Abstract: A facility for optimizing machine learning models is described. The facility obtains a description of a machine learning model and a hardware target for the machine learning model. The facility obtains optimization result data from a repository of optimization result data. The facility optimizes the machine learning model for the hardware target based on the optimization result data.

Abstract: Techniques are disclosed for a computer system to predict a next sample for a data stream that specifies data values of one or more variables. A current subset of data values and previous subsets of data values is determined, and polyline simplification techniques may then be used on the subset to produce a reduced-sample current subset of data values that are converted to an angular coordinate system. A space partitioning data structure such as a k-dimensional tree that stores converted reduced-sample previous subsets of the data stream may then be traversed to determine one or more nearest neighbors to the current subset. The predicted next sample for the data stream may be generated from the nearest neighbors. The space partitioning data structure may be updated to include the current subset, and the process may be repeated with a new current subset.

Abstract: A prediction model generation system is provided that is capable of generating a prediction model for accurately predicting a relationship between an ID of a record in first master data and an ID of a record in second master data. Co-clustering means 71 performs co-clustering processing for performing co-clustering on first IDs and second IDs in accordance with first master data, second master data, and fact data indicating a relationship between each of the first IDs and each of the second IDs. Prediction model generation means 72 performs prediction model generation processing for generating a prediction model for each combination of a first ID cluster and a second ID cluster. The prediction model uses the relationship between each of the first IDs and each of the second IDs as an objective variable. The first ID cluster serves as a cluster of the first IDs. The second ID cluster serves as a cluster of the second IDs.

Abstract: A neural network runs a known input data set using an error free power setting and using an error prone power setting. The differences in the outputs of the neural network using the two different power settings determine a high level error rate associated with the output of the neural network using the error prone power setting. If the high level error rate is excessive, the error prone power setting is adjusted to reduce errors by changing voltage and/or clock frequency utilized by the neural network system. If the high level error rate is within bounds, the error prone power setting can remain allowing the neural network to operate with an acceptable error tolerance and improved efficiency. The error tolerance can be specified by the neural network application.

Abstract: Conversation user interfaces that are configured for virtual assistant interaction may include tasks to be completed that may have repetitious entry of the same or similar information. User preferences may be learned by the system and may be confirmed by the user prior to the learned preference being implemented. Learned preferences may be identified in near real-time on large collections of data for a large population of users. Further, the learned preferences may be based at least in part on previous conversations and actions between the system and the user as well as user-defined occurrence thresholds.

Abstract: A method, system and computer-usable medium for performing cognitive computing operations comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching for incorporation into a cognitive graph; defining a cognitive persona within the cognitive graph, the cognitive persona corresponding to an archetype user model, the cognitive persona comprising a set of nodes in the cognitive graph; associating a user with the cognitive persona; and, performing a cognitive computing operation based upon the cognitive persona associated with the user.

Abstract: A system for generating learning data is provided. The system for generating the learning data includes a data incorporating part configured to generate new data by filtering plant data based on a warning condition to incorporate the plant data for one configuration of a plant into existing learning data and a learning data generating part configured to differentiate a weight applied to the new data and the existing learning data, respectively, by comparing the number of the new data and the number of the existing learning data, and generate new learning data by combining the new data with the existing learning data to which the weight is applied.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: An apparatus, method, and computer program product are provided to adjust and modify input signals used in connection with predictive models by detecting events, such as changes in operating parameters of data objects and/or related systems and calculating adjusted decay rates to be applied to time-series data associated with times prior to an occurrence of an event. In some example implementations, an indication of an event associated with a given datastream is received, in a manner which indicates the change in an operating parameter and the time at which the change occurred. Based at least in part on the indication of the event associated with the datastream, a second decay rate associated with the set of time-series data is determined and applied to the set of time-series data, such that an updated future performance level can be calculated by a predictive model.

Abstract: A method for generating an alimentary instruction set identifying a list of supplements, comprising receiving information related to a biological extraction and physiological state of a user and generating a diagnostic output based upon the information related to the biological extraction and physiological state of the user. The generating comprises identifying a condition of the user as a function of the information related to the biological extraction and physiological state of the user and a first training set. Further, the generating includes identifying a supplement related to the identified condition of the user as a function of the identified condition of the user and a second training set. Further, the method includes generating, by an alimentary instruction set generator operating on a computing device, a supplement plan as a function of the diagnostic output, said supplement plan including the supplement related to the identified condition of the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving a plurality of activation inputs; forming a plurality of vector inputs from the plurality of activation inputs, each vector input comprising values from a distinct region within the multi-dimensional matrix; sending the plurality of vector inputs to one or more cells along a first dimension of the systolic array; generating a plurality of rotated kernel structures from each of the plurality of kernel; sending each kernel structure and each rotated kernel structure to one or more cells along a second dimension of the systolic array; causing the systolic array to generate an accumulated output based on the plurality of value inputs and the plurality of kernels; and generating the layer output from the accumulated output.

Abstract: The present invention concerns methods and apparatus for perturbing a known contextualization of an underlying proposition adopted by a group of subjects that are considered in a quantum representation. Initially, the subjects belonging to the group exhibit the known contextualization modulo the proposition and also have known measurable indications in the known contextualization. Perturbation is due to injection into the group of a disruptive subject that exhibits a Fermi-Dirac (F-D) anti-consensus statistic modulo the underlying proposition. A monitoring unit and a statistics module are deployed to collect and study subsequent measurable indications from subjects in the group after injection of the disruptive subject and upon re-confronting of the underlying proposition. The perturbation is thus detected and changes in the quantum representation due to it are estimated.

Abstract: Embodiments of the present invention include a system, computer-implemented method, and a computer program product. A non-limiting example of the method includes a processor utilizing a model having a plurality of parameters. The processor compares a current value of a model parameter to a prior value of the model parameter. Based at least in part on comparing the current value of the model parameter to the prior value of the model parameter, a determination is made that the model being utilized by the processor has changed. The current value of the model parameter is transmitted by the processor.