Abstract: A method for building a factual database of concepts and entities that are related to the concepts through a learning process. Training content (e.g., news articles, books) and a set of entities (e.g., Bill Clinton and Barack Obama) that are related to a concept (e.g., Presidents) is received. Groups of words that co-occur frequently in the textual content in conjunction with the entities are identified as templates. Templates may also be identified by analyzing parts-of-speech patterns of the templates. Entities that co-occur frequently in the textual content in conjunction with the templates are identified as additional related entities (e.g., Ronald Reagan and Richard Nixon). To eliminate erroneous results, the identified entities may be presented to a user who removes any false positives. The entities are then stored in association with the concept.

Abstract: A bedding system uses a convolutional neural network (CNN)-based machine vision to makes adjustments for comfort and/or support. The machine vision process identities a body position by using a trained CNN that receives a pressure image and identifies a body position. The body position may be determined by classifying the pressure image into a predetermined body position classification. The machine vision process includes at least one trained CNN that determines joint locations. The machine vision tracks pressure accumulated at joints over time.

Abstract: Technologies and implementations for training a predictive intelligence associated with electronic discovery (e-discovery) are generally disclosed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, of training a global policy neural network. One of the methods includes initializing a plurality of instances of the robotic task. For each instance of the robotic task, the method includes generating a trajectory of state-action pairs by selecting actions to be performed by the robotic agent while performing the instance of the robotic task in accordance with current values of the parameters of the global policy neural network, and optimizing a local policy controller that is specific to the instance on the trajectory of state-action pairs for the instance. The method further includes generating training data for the global policy neural network using the local policy controllers, and training the global policy neural network on the training data to adjust the current values of the parameters of the global policy neural network.

Abstract: Methods, systems and apparatus that provide for perceptual, cognitive, and motor behaviors in an integrated system implemented using neural architectures. Components of the system communicate using artificial neurons that implement neural networks. The connections between these networks form representations—referred to as semantic pointers—which model the various firing patterns of biological neural network connections. Semantic pointers can be thought of as elements of a neural vector space, and can implement a form of abstraction level filtering or compression, in which high-dimensional structures can be abstracted one or more times thereby reducing the number of dimensions needed to represent a particular structure.

Abstract: A computing device selects decision variable values. A lower boundary value and an upper boundary value is defined for a decision variable. (A) A plurality of decision variable configurations is determined using a search method. The value for the decision variable is between the lower boundary value and the upper boundary value. (B) A decision variable configuration is selected. (C) A model of the model type is trained using the decision variable configuration. (D) The model is scored to compute an objective function value. (E) The computed objective function value and the selected decision variable configuration are stored. (F) (B) through (E) is repeated for a plurality of decision variable configurations. (G) The lower boundary value and the upper boundary value are updated using the objective function value and the decision variable configuration stored. Repeat (A)-(F) with the lower boundary value and the upper boundary value updated in (G).

Abstract: Methods, apparatus, systems and articles of manufacture to analyze time series data are disclosed. An example method includes sub sampling time series data collected by a sensor to generate one or more candidate samples of interest within the time series data. Feature vectors are generated for respective ones of the one or more candidate samples of interest. Classification of the feature vectors is attempted based on a model. In response to a classification of one of the feature vectors, the classification is stored in connection with the corresponding candidate sample.

Abstract: Systems and methods are disclosed for communication-based automated guidance. In one implementation, a first communication is received from a first user via a first device and in relation to a first user parameter. A second communication is received from the first user via a second device and in relation to a second user parameter. A response to the second communication is generated based on the first communication, the first user parameter, and the second user parameter. The generated response is provided to the second device.

Abstract: A computer-implemented system and method identify Pareto optimal candidate paths between an origin and a destination for which no other candidate path is strictly better on one of a predefined set of criteria and at least as good on all the others. A constraint is defined for each of the criteria, based on user input. A set of Pareto optimal candidate paths is identified, from an origin to a destination, which respect these constraints. The identification may include, in a search graph composed of nodes connected by edges, iteratively advancing each of a set of possible paths from an origin node by exactly one exit node and updating labels of the exit nodes reached. The exit node labels each include a value for each of the criteria. Labels of reached exit nodes that are dominated by another label of that reached node are removed. Pareto optimal candidate path(s) is/are identified.

Abstract: A device may receive a first sample. The device may identify a plurality of second samples that are similar to the first sample. The plurality of second samples may correspond to service tickets that have previously been processed. The device may obtain or determine log information identifying a plurality of events associated with the first sample. The device may determine respective probabilities of occurrence corresponding to the plurality of second samples. A probability of occurrence, for a particular second sample, may identify a likelihood of receiving a corresponding service ticket within a particular time period of occurrence of the plurality of events. The device may assign ranks to the plurality of second samples based on the respective probabilities of occurrence. The device may provide information identifying the ranks and the plurality of second samples.

Abstract: A machine learning system for evaluating at least one characteristic of a heart valve, an inflow tract, an outflow tract or a combination thereof may include a training mode and a production mode. The training mode may be configured to train a computer and construct a transformation function to predict an unknown anatomical characteristic and/or an unknown physiological characteristic of a heart valve, inflow tract and/or outflow tract, using a known anatomical characteristic and/or a known physiological characteristic the heart valve, inflow tract and/or outflow tract. The production mode may be configured to use the transformation function to predict the unknown anatomical characteristic and/or the unknown physiological characteristic of the heart valve, inflow tract and/or outflow tract, based on the known anatomical characteristic and/or the known physiological characteristic of the heart valve, inflow tract and/or outflow tract.

Abstract: Methods and apparatuses are described for automated predictive product recommendations using reinforcement learning. A server captures historical activity data associated with a plurality of users. The server generates a context vector for each user, the context vector comprising a multidimensional array corresponding to historical activity data. The server transforms each context vector into a context embedding. The server assigns each context embedding to an embedding cluster. The server determines, for each context embedding, (i) an overall likelihood of successful attempt and (ii) an incremental likelihood of success associated products available for recommendation. The server calculates, for each context embedding, an incremental income value associated with each of the likelihoods of success. The server aggregates (i) the overall likelihood of successful attempt, (ii) the likelihoods of success, and (iii) the incremental income values into a recommendation matrix.

Abstract: Apparatus and methods for processing neural network models are provided. The apparatus can comprise a plurality of identical artificial intelligence processing dies. Each artificial intelligence processing die among the plurality of identical artificial intelligence processing dies can include at least one inter-die input block and at least one inter-die output block. Each artificial intelligence processing die among the plurality of identical artificial intelligence processing dies is communicatively coupled to another artificial intelligence processing die among the plurality of identical artificial intelligence processing dies by way of one or more communication paths from the at least one inter-die output block of the artificial intelligence processing die to the at least one inter-die input block of the artificial intelligence processing die.

Abstract: A method includes determining a set of k extreme values of a dataset of elements in a constant time irrespective of the size of the dataset. A method creates a set of k indicators, each indicator associated with one multi-bit binary number in a large dataset of multi-bit binary numbers. The method includes arranging the multi-bit binary numbers such that each bit n of each said multi-bit binary number is located in a different row n of an associative memory array, starting from a row storing a most significant bit (MSB), adding an indicator to the set for each multi-bit binary number having a bit with an extreme value in the row and continuing the adding until said set contains k indicators.

Abstract: A computer-implemented method for automatically analyzing log contents received via a network and detecting content-level anomalies is presented. The computer-implemented method includes building a statistical model based on contents of a set of training logs and detecting, based on the set of training logs, content-level anomalies for a set of testing logs. The method further includes maintaining an index and metadata, generating attributes for fields, editing model capability to incorporate user domain knowledge, detecting anomalies using field attributes, and improving anomaly quality by using user feedback.

Abstract: Various embodiments described herein relate to methods and apparatus for robust classification. Many real-world datasets suffer from missing or incomplete data. By assigning weights to certain features of a dataset based on which feature(s) are missing or incomplete, embodiments of the prevention can provide robustness and resilience to missing data.

Abstract: Disclosed herein is an enhanced device personalization that personalizes a user's experience with a device, e.g., a multi-user device. Rather than personalizing based on the specific user(s) that are using, an active entity, which represents a type of consumption, may be generated and used to make recommendations for personalizing an experience using the device. In a case of a multi-user device, each user's experience is personalized by determining an active entity for the user's experience and without knowledge of which user is using the device.

Abstract: An artificial intelligence audio apparatus includes a sensing part which is configured to sense a current location and a temperature and/or a humidity thereof and sense whether a human exists in the current location; and a controller which is configured to receive weather information of the current location from an external server using location information of the current location, determine whether a predetermined greeting should be output when the human exists in the current location, and in response to determining that the predetermined greeting should be output, extract at least one of a greeting voice and a greeting text, from greeting data stored in a storage, which corresponds with a current time, at least one of the temperature and the humidity, and the weather information of the current location, and output the extracted at least one of the greeting voice and the greeting text.

Abstract: Methods and systems of using machine learning to create a trusted model that improves the operation of a computer system controller are provided herein. In some embodiments, a machine learning method includes training a model using input data, extracting the model, and determining whether the model satisfies the trust-related constraints. If the model does not satisfy the trust-related constraint, modifying at least one of: the model using one or more model repair algorithms, the input data using one or more data repair algorithms, or a reward function of the model using one or more reward repair algorithms, and re-training the model using at least one of the modified model, the modified input data, or the modified reward function. If the model satisfies the trust-related constraints, providing the model as a trusted model that enables a computer system controller to perform system actions within predetermined guarantees.

Abstract: A system and method are disclosed for collecting and analyzing data in a cognitive fabric. The system can include a network of intelligent nodes, each node being configured for sharing or receiving data as a function of analytic processing to be performed at the node.