Abstract: A method of generating a predictor to classify data includes: training each of a plurality of first classifiers arranged in a first level on current training data; operating each classifier of the first level on the training data to generate a plurality of predictions; combining the current training data with the predictions to generated new training data; and training each of a plurality of second classifiers arranged in a second level on the new training data. The first classifiers are classifiers of different classifier types, respectively and the second classifiers are classifiers of the different classifier types, respectively.

Abstract: System and method of generating an executable action item in response to natural language dialogue are disclosed herein. A computing system receives a dialogue message from a remote client device of a customer associated with an organization, the dialogue message comprising an utterance indicative of an implied goal. A natural language processor of the computing system parses the dialogue message to identify one or more components contained in the utterance. The planning module of the computing system identifies the implied goal. The computing system generates a plan within a defined solution space. The computing system generates a verification message to the user to confirm the plan. The computing system transmits the verification message to the remote client device of the customer. The computing system updates an event queue with instructions to execute the action item according to the generated plan upon receiving a confirmation message from the remote client device.

Abstract: The invention concerns a query response device comprising: an input adapted to receive user queries; a memory (106) adapted to store one or more routing rules; one or more live agent engines (116) configured to support interactions with one or more live agents; one or more virtual assistant engines (120) configured to support interactions with one or more virtual assistants instantiated by an artificial intelligence module (103); and a routing module (104) coupled to said live agent engines and to said virtual assistant engines, the routing module comprising a processing device configured: to select, based on content of at least a first user message from a first user relating to a first user query and on said one or more routing rules, a first of said live agent engines or a first of said virtual assistant engines; and to route one or more further user messages relating to the first user query to the selected engine.

Abstract: A device that estimates the travel speed of a mobile body obtains a speed similarity of a travel speed associated with a road subject to estimation and a travel speed associated with each section of a map. The device also obtains an environment similarity degree of environment information corresponding to a section including the subject road and environment information corresponding to each section. A section similar to the section including the subject road is selected based on the total similarity degree, which is calculated based on the speed similarity and the environment similarity, to set the travel speed associated with the selected section as a travel speed of a corresponding time period on the subject road.

Abstract: Systems and methods use machine learning techniques to resolve location ambiguity in search queries. In one aspect, a dataset generator generates a training dataset using query logs of a search engine. A training engine applies a machine learning technique to the training dataset to generate a location disambiguation model. A location disambiguation engine uses the location disambiguation model to resolve location ambiguity in subsequent search queries.

Abstract: A method, system and/or computer program product predicts viewing activity of a new posting to an activity stream. A first computer transmits a new posting to an activity stream in a second computer, where the new posting is available to a potential viewer set. Based on identified viewer information about one or more members of the potential viewer set, a prediction is made of viewing activity of the new posting by the potential viewer set. This predicted viewing activity is based on identified viewer information about members of the potential viewer set, and describes a predicted likelihood of the potential viewer set viewing the new posting. The derived predicted viewing activity of the new posting by the potential viewer set is then presented at the first computer.

Abstract: Described is a secure system for generic pattern matching. In operation, the system determines if a pattern p, as presented by a second party, is within a textual pattern T, as maintained by a first party. In making such a determination, the system uses a series of binary value matrices and corresponding pairs of encrypted permuted matrices. Challenge bits are then used to generate permutations and later verify correctness of the various encrypted permuted matrices. If it is determined that pattern p is within text T, the, for example, an access protocol is initiated.

Abstract: A method for generating a project saturation model for one or more projects is provided. Historical project data is analyzed to define a plurality of project change factors for one or more proposed projects. A plurality of scoring values associated with the plurality of project change factors is received for each of the one or more proposed projects. One or more saturation model components are generated based on the historical project data and based on the received plurality of scoring values for each of the proposed projects. A saturation model is generated by combining the saturation model components for each of the proposed projects. The saturation model identifies risks associated with a corresponding project.

Abstract: Predefined relation items on paths traversing predefined entities of a knowledge base are collected and feature sets are assembled from the collected relation items. A classifier is computed for the feature sets and a relation score of a query pair of the entities is computed using the classifier.

Abstract: A method of determining a set of prescribed actions includes receiving a configuration script identifying a set of influencers, a set of performance indicators, a model type, a target time, and a prescription method. The method further includes deriving a model of the model type based on data associated with the set of influencers or with the set of performance indicators. The method also includes projecting a set of future influencer values associated with the set of influencers and projecting a set of future indicator values of the set of performance indicators at the target time using the model. The method can further include prescribing using the prescription method and based on projecting using the model a set of prescribed actions associated with the subset of actionable influencers. The method also includes displaying the set of prescribed actions.

Abstract: Predefined relation items on paths traversing predefined entities of a knowledge base are collected and feature sets are assembled from the collected relation items. A classifier is computed for the feature sets and a relation score of a query pair of the entities is computed using the classifier.

Abstract: A processing apparatus is disclosed for representing cognitively biased selection behavior of a consumer as a learnable model with high prediction accuracy taking into account even feature values of a product and the consumer. The processing apparatus generates a selection model obtained by modeling selection behavior of a selection entity that selects at least one choice out of presented input choices. The processing apparatus includes an acquiring unit to acquire training data including a plurality of input feature vectors that indicate features of a plurality of the choices presented to the selection entity and an output feature vector that indicates a feature of an output choice. The processing apparatus further includes an input combining unit to combine the plurality of input vectors to generate an input combined vector, and a learning processing unit to learn a selection model on the basis of the input combined vector and the output vector.

Abstract: A computing device determines a sparse feature representation for a machine learning model. Landmark observation vectors are randomly selected. Neighbor observation vectors are randomly selected that are less than a predefined distance from a selected landmark observation vector. The observation vectors are projected into a neighborhood subspace defined by principal components computed for the neighbor observation vectors. A distance vector includes a distance value computed between each landmark observation vector and each observation vector of the projected observation vectors. Nearest landmark observation vectors are selected from the landmark observation vectors for each observation vector. A second distance vector that includes a second distance value computed between each observation vector and each landmark observation vector is added to a feature distance matrix, where the second distance value is zero for each landmark observation vector not included in the nearest landmark observation vectors.

Abstract: A mechanism is provided in a data processing system for determining comprehensiveness of a question paper given a syllabus of topics. An answer and evidence generator of a question answering system executing on the data processing system finds one or more answers based on the syllabus of topics for each question in the question paper. The answer and evidence generator identifies evidence for the one or more answers in the syllabus for each question in the question paper. A concept identifier of the question answering system identifies a set of concepts in the syllabus corresponding to the evidence for each question in the question paper to form a plurality of sets of concepts. The mechanism determines a value for a comprehensiveness metric for the question paper with respect to the syllabus of topics based on the plurality of sets of concepts.

Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.

Abstract: The disclosed herein relates to a method for failure rate prediction of a feature of a system under development. The method is executed by a processor coupled to a memory. The method includes defining a feature state of the feature during a predetermined time interval, the predetermined time interval being associated with a development stage of the system. The method also includes assigning a first defect class value to the feature for the predetermined time interval, the first defect class value configured to indicate a first condition and selecting, when a defect is reported for the feature, a second defect class value indicating a second condition, the second condition being associated with a higher failure rate than the first condition. The method can be embodied in system and a computer program product.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining data defining a sequence for an aptamer, the aptamer comprising a string of nucleobases; encoding the data defining the sequence for the aptamer as a neural network input; and processing the neural network input using a neural network to generate an output that characterizes how strongly the aptamer binds to a particular target molecule, wherein the neural network has been configured through training to receive the data defining the sequence and to process the data to generate predicted outputs that characterize how strongly the aptamer binds to the particular target molecule.

Abstract: A method is described that includes executing a convolutional neural network layer on an image processor having an array of execution lanes and a two-dimensional shift register. The two-dimensional shift register provides local respective register space for the execution lanes. The executing of the convolutional neural network includes loading a plane of image data of a three-dimensional block of image data into the two-dimensional shift register.

Abstract: The techniques herein include using an input context to determine a suggested action. One or more explanations may also be determined and returned along with the suggested action. The one or more explanations may include (i) one or more most similar cases to the suggested case (e.g., the case associated with the suggested action) and, optionally, a conviction score for each nearby cases; (ii) action probabilities, (iii) excluding cases and distances, (iv) archetype and/or counterfactual cases for the suggested action; (v) feature residuals; (vi) regional model complexity; (vii) fractional dimensionality; (viii) prediction conviction; (ix) feature prediction contribution; and/or other measures such as the ones discussed herein, including certainty. In some embodiments, the explanation data may be used to determine whether to perform a suggested action.

Abstract: A computing device predicts an event or classifies an observation. A trained labeling model is executed with unlabeled observations to define a label distribution probability matrix used to select a label for each observation. Unique combinations of observations selected from the unlabeled observations are defined. A marginal distribution value is computed from the label distribution probability matrix. A joint distribution value is computed between observations included in each combination. A mutual information value is computed for each combination as a combination of the marginal distribution value and the joint distribution value computed for the respective combination. A predefined number of observation vector combinations is selected from the combinations that have highest values for the computed mutual information value. Labeled observation vectors are updated to include each observation vector included in the selected observation vector combinations with a respective obtained label.