Abstract: The disclosure is directed to an ensemble learning prediction apparatus. The apparatus includes a loss module, a diversity module, a sample weight module, and an integrating weight module. The loss module, the diversity module and the sample weight module calculate a loss, a diversity and a sample weight, respectively. An ensemble weight is learned by an object function built by the loss, diversity and the sample weight. The integrating weight module calculates an adaptive ensemble weight by integrating the ensemble weight and previous ensemble weights at a plurality of previous time points.

Abstract: Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements performs flow based computations on wavelets of data. Each processing element has a compute element and a routing element. Each compute element has memory. Each router enables communication via wavelets with nearest neighbors in a 2D mesh. A compute element receives a wavelet. If a control specifier of the wavelet is a first value, then instructions are read from the memory of the compute element in accordance with an index specifier of the wavelet. If the control specifier is a second value, then instructions are read from the memory of the compute element in accordance with a virtual channel specifier of the wavelet. Then the compute element initiates execution of the instructions.

Abstract: A ground truth expansion system that generates an expanded set of synthetic questions and selects a targeted subset of questions for machine learning training. The machine learning may be used to train an automated inquiry system that responds to questions received from individuals about subject matter of interest. The automated inquiry system is particularly suitable for use in, for example, responding to questions raised by insured individuals about their healthcare benefits.

Abstract: Provided is an information processing apparatus including a status recognition unit that recognizes a status of a reference apparatus on the basis of information on a status of an apparatus corresponding to the reference apparatus, the reference apparatus serving as a reference when a behavior recognition mode for deciding a status of behavior is set and a behavior-recognition-mode setting unit that sets the behavior recognition mode for a setting target apparatus for which the behavior recognition mode is to be set on the basis of the recognized status of the reference apparatus.

Abstract: Systems and methods are described for facilitating operation of a plurality of computing devices. Data indicative of enumerated resources of a computing device is collected. The data is collected without dependency on write permissions to a file system of the one computing device. A condition of the computing device is determined based on historical data associated with enumerated resources of other computing devices. The identified condition can be updated as updated historical data becomes available. A communication to the computing device may be sent based on the identified condition.

Abstract: A computer implemented method comprising accessing a decision service, determining a subset of the decision logic, inserting a causal probe into the decision service, receiving a query at the interface of the decision service, executing the decision logic to determine the one or more outputs for the decision service for the received query, and outputting the one or more outputs and the causal history from the decision service for the received query. The causal history can be accessed at a later date and used to generate a causal model that can be used to determine an explanation for the original decision.

Abstract: Described herein is a system and method for providing a conversation session with an artificial intelligence entity in a user interface. Once the conversation session with the artificial intelligence entity has been initiated, other individuals and/or artificial intelligence entities may be invited to join the conversation. In addition, other users may view the interactions between the individuals and the artificial intelligence entities without participating in the conversation. Although the other users are not participating in the conversation, the user interface enables these users to provide comments about the interactions. These comments may be used to train the artificial intelligence entities.

Abstract: In order to facilitate the entity resolution and entity activity tracking and indexing, systems and methods include receiving first source records from a first database and second source records from a record database. A candidate set of second source records is determined by a heuristic search in the set of second source records. A candidate pair feature vector associated with each candidate pair of first and second source records is generated. An entity matching machine learning model predicts matching first source records for each candidate second source record based on the respective candidate pair feature vector. An aggregate quantity associated with the matching first source records is aggregated from a quantity associated with each first source record, and a quantity index for each candidate second source record is determined based the aggregate quantities. Each quantity index is displayed to a user.

Abstract: A system for providing adaptive metric pruning includes a processor; a memory; and one or more modules stored in the memory and executable by a processor to perform operations including: receive, by a collector, metadata associated with the business transaction running in a monitored environment; train a machine learning system by providing training data and an anticipated result for the training data to the machine learning system to generate rules for retaining given metadata; predict a retention requirement for the received metadata by providing the received metadata to the machine learning system to apply the generated rules and generate a result for retaining the received metadata; and provide a user interface to display the generated result for retaining the received metadata including a recommendation on how to retain the received metadata according to the result for retaining the received metadata.

Abstract: A method and system for identifying and prioritizing business useful insights from hidden patterns. This invention relates to data mining techniques and more particularly to identify and prioritize insights from a plurality of insights present in a large set of data. Insight exploration is a method and system that enables the user to generate actionable insights, prioritize them for a given data. This falls broadly within the field of data mining. The primary achievement of this invention is to take a rule in if-then format and then systematically process them to identify actionable information from them. In that process, the system automatically prioritizes the rules, generates other rules and analyzes the path that leads to desired behavioral changes.

Abstract: A camera device and camera system for video-based workplace safety is provided. The camera device includes at least one imaging sensor configured to capture one or more video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate a plurality of embedding vectors based on a plurality of observations. The observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on. The subject and object are constant. The processor is further configured to generate predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The processor is configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate harm.

Abstract: Systems and methods for training a recursive neural network (RNN) is provided. The method includes generating, by the processor using the RNN, a plurality of embedding vectors based on a plurality of observations, wherein the observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on, wherein the subject and object are constant. The method further includes generating, by the processor, predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The method also includes initiating, by the processor, based on the predictions, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

Abstract: The present invention relates to recurrent neural network. In particular, the present invention relates to how to implement and accelerate a recurrent neural network based on an embedded FPGA. Specifically, it proposes an overall design processing method of matrix decoding, matrix-vector multiplication, vector accumulation and activation function. In another aspect, the present invention proposes an overall hardware design to implement and accelerate the above process.

Abstract: Embodiments of the invention relate to a storage system organized into a hierarchy of storage tiers, with at least one tier reflecting a high performance tier and at least one tier reflecting a lower performance tier. The high performance tier has a capacity restriction and has a limited quantity of blocks and pages may be placed in the tier. Assessments are conducted and a preferred selection of blocks and pages are recommended for placement; the recommendation is based on the assessment. The recommendation is converted to an actual placement, resulting in placement of at least one block, an in one embodiment at least one page, in the high performance tier.

Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

Abstract: A multi-horizon predictor system that predicts a future parameter value for multiple horizons based on time-series data of the parameter, external data, and machine-learning. For a given time horizon, a time series data splitter splits the time into training data corresponding to a training time period, and a validation time period corresponding to a validation time period between the training time period and the given horizon. A model tuner tunes the prediction model of the given horizon fitting an initial prediction model to the parameter using the training data thereby using machine learning. The model tuner also tunes the initial prediction model by adjusting an effect of the external data on the prediction to generate a final prediction model for the given horizon using the validation data. A multi-horizon predictor causes the time series data splitter and the model tuner to operate for each of multiple horizons.

Abstract: Technologies are provided for implementing temporal and spatio-temporal spiking neural networks (SNNs) using neuromorphic hardware devices. Temporal synapse circuits, with associated weight values, can be used to control spike times of connected neuron circuits. The controlled spike times of multiple neuron circuits can be used to temporally encode information in a neural network in neuromorphic hardware. Neuron circuits in a state space detection layer can be organized into multiple subsets. Neuron circuits in different subsets can be connected to output neuron circuits in an output layer by separate temporal synapse circuits. Spiking signals sent from the neuron circuits in the state space detection layer via separate temporal synapse circuits can cause associated output neuron circuits to generate output spiking signals at different times. The various spike times of the output neuron circuits can be aggregated to produce an output signal for the network.

Abstract: System and techniques for receiving text input into electronic devices and predicting a relevant image or label. In a first aspect, the system and techniques comprise receiving text input by a user and a prediction function trained on sections of text associated with an image or label. The prediction function is configured to receive the text input by the user, determine the relevance of the text input by the user to the sections of text associated with the image or label, and predict, based on the sections of text associated with the image or label the relevance of the image or label to the text input by the user. The systems and techniques reduce the burden of entering an image or label.

Abstract: A machine learning apparatus that learns laser machining condition data of a laser machining system includes: a state amount observation unit that observes a state amount of the laser machining system; an operation result acquisition unit that acquires a machined result of the laser machining system; a learning unit that receives an output from the state amount observation unit and an output from the operation result acquisition unit, and learns the laser machining condition data in association with the state amount and the machined result of the laser machining system; and a decision-making unit that outputs laser machining condition data by referring to the laser machining condition data learned by the learning unit.

Abstract: A system for using hash keys to preserve privacy across multiple tasks is disclosed. The system may provide training batch(es) of input observations each having a customer request and stored task to an encoder, and assign a hash key(s) to each of the stored tasks. The system may provide a new batch of input observations with a new customer request and new task to the encoder. The encoder may generate a new hash key assigned to the new customer request and determine whether any existing hash key corresponds with the new hash key. If so, the system may associate the new batch of input observations with the corresponding hash key and update the corresponding hash key such that it is also configured to provide access to the new batch of input observations. If not, the system may generate a new stored task and assign the new hash key to it.