Abstract: A method for autofilling an electronic form is provided. Elements of the electronic form are identified. A value for each identified elements of the electronic form is determined. The electronic form is automatically filled with the determined values. During the automatically filling of the electronic form, the determined value is provided in a field corresponding to each of the elements. A user input is received on the provided value. The received user input includes a correction to a first value provided in a first field of the electronic form. An autofill application is trained using the received user input.

Abstract: Machine learning models are powerful artificial intelligence tools that can make determinations based on a variety of factors. Unlike a simple linear model, however, determining the contribution of each variable to the outcome of a machine learning model is a challenging task. It may be unclear which factors contributed heavily toward a particular outcome of the machine learning model and which factors did not have a major effect on the outcome. Being able to accurately determine the underlying causative factors for a machine learning-based decision, however, can be important in several contexts. The present disclosure describes techniques that allow for training and use of non-linear machine learning models, while also preserving causal information for outputs of the models. Relative weight calculations for machine learning model variables can be used to accomplish this, in various embodiments.

Abstract: This invention relates to an artificial memory system and a method of continuous learning for predicting and anticipating human operator's action as response to ego-intention as well as environmental influences during machine operation. More specifically the invention relates to an architecture with artificial memory for interacting with dynamic behaviors of a tool and an operator, wherein the architecture is a first neural network having structures and mechanisms for abstraction, generalization and learning, the network implementation comprising an artificial hierarchical memory system.

Abstract: A processing apparatus applied in an artificial neuron is disclosed. The processing apparatus comprises a parser, a lookup array, a summing circuit and a MAC circuit. The parser parses one of M packets to extract a non-zero weight value from a header of the one packet, to identify a plurality of bit positions with a specified digit from a payload of the one packet, and to output the non-zero weight value and the bit positions in parallel. The lookup array contains N synapse values and is indexed by the bit positions in parallel to generate a plurality of match values. The summing circuit sums up the match values to generate a sum value. The MAC circuit generates a product of the non-zero weight value and the sum value, and generates an accumulate value based on the product and at least one previous accumulate value.

Abstract: A learning means 71 learns, based on learning data containing the meaning of a column in a table and the meaning of the table, a model indicating regularity between the meaning of the column in the table and the meaning of the table. An estimation means 72 estimates the meaning of the table based on the meaning of a column of a table to be input and the model.

Abstract: System and method for automatically generate therapy plan parameters by use of an integrate model with extended applicable regions. The integrated model integrates multiple predictive models from which a suitable predictive model can be selected automatically to perform prediction for a new patient case. The integrated model may operate to evaluate prediction results generated by each predictive model and the associated prediction reliabilities and selectively output a satisfactory prediction. Alternatively, the integrated model may select a suitable predictive model by a decision hierarchy in which each level corresponds to divisions of a patient data feature set and divisions on a subordinate level are nested with divisions on a superordinate level.

Abstract: An original set of rules are transformed into a resulting set of generalized rules in a rule management system. An original set of rules stored in a data structure for transforming into a resulting set of rules are accessed. The original set of rules is automatically processed by building a compact description of one or more rules in the original set of rules and their actions in the form of logical constraints and solving constraints to find a solution that represents a case and an applied action, building a family of cases by taking all logical tests or their negation that are satisfied by the solution, and generalizing the family of cases by removal of specific logical tests which do not apply to the action, resulting in a most-general rule.

Abstract: Implementations disclose identifying content appropriate for children algorithmically without human intervention. A method includes identifying, by a processing device, entities corresponding to topics relevant to children, determining, by the processing device, a children's affinity score for each of the identified entities, and selecting, by the processing device, content based on the children's affinity score for the identified entities corresponding to the content.

Abstract: Methods for controlling the resistance of a controllable resistive element include determining an amount of electrical resistance change for the controllable resistive element. A concentration difference is determined for a charge carrier ion in a resistor layer of the controllable resistance element that corresponds to the electrical resistance change for the controllable resistive element. A duration and amplitude of a current pulse is determined that changes the charge carrier ion concentration by the determined difference. A positive or negative current pulse is applied to a controllable resistive element for the determined duration.

Abstract: An approach is provided for automatically generating and processing concept vectors by extracting concept sequences from one or more content sources and generating a first concept vector for a first concept by supplying the concept sequences as inputs to a vector learning component, such that the first concept vector comprises information interrelating the first concept to other concepts in the concept sequences which is inferred from the concept sequences.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing consistent processing in a machine learning system are disclosed. A real-time processing request may be received and processed by both a preferred machine learning model and a fallback machine learning model. Processing for the preferred machine learning model may include obtaining additional information. A determination may be made regarding whether the processing of the real-time request by the preferred machine learning model has completed as of an expiration of an acceptable latency period. If the preferred model has not completed as of the expiration of an acceptable latency period, the response to the real-time request may be generated from the fallback model output. If the preferred model has completed prior to or by the expiration of the acceptable latency period, the response to the request may be generated from the preferred model output.

Abstract: The present disclosure is directed to a decision support system or tool based on a Bayesian Network (BN) framework. The diagnostic support tool is created by using advanced Probabilistic Risk Assessment (PRA) method(s) to construct Bayesian Networks (BNs) that form a Bayesian Decision Support Process (BDSP) to provide science-based decision support for understanding and managing events in complex systems. In an embodiment, the PRA method(s) may include Discrete Dynamic Event Trees (DDETs) and simulations.

Abstract: One or more processors receive one or more variations to one or more first instruction elements in a first instruction set that indicate one or more second instruction elements of a second instruction set. One or more processors determine whether the one or more first instruction elements exceed a threshold of variability. One or more processors determine whether the one or more first instruction elements and the one or more second instruction elements are substantially equivalent. One or more processors determine whether a first outcome of the first instruction set is substantially similar to a second outcome of the second instruction set.

Abstract: A device identifies training data and scoring data for a model, and removes bias from the training data to generate unbiased training data. The device trains the model with the unbiased training data to generate trained models, and processes the trained models, with the scoring data, to generate scores for the trained models. The device selects a trained model, from the trained models, based on model metrics and the scores, and processes a training sample, with the trained model, to generate first results, wherein the training sample is created based on the unbiased training data and production data. The device processes a production sample, with the trained model, to generate second results, wherein the production sample is created based on the production data and the training sample. The device provides the trained model for use in a production environment based on the first results and the second results.

Abstract: An AUC-maximized high-accuracy classification method and system for imbalanced datasets integrates an under-sampling-and-ensemble strategy, a true-outliers-removing strategy and a fake-outliers-concealing strategy, with the hope to effectively and robustly enhance both the AUC and the accuracy metrics in imbalanced classification. Applying under-sampling to construct multiple sub-datasets and assembling classification results of multiple classifiers greatly decline the risk of misclassification and lead to highly accurate and robust results in imbalanced classification task. Moreover, this invention pays attention to detect and identify extremely hidden outliers in a sub-dataset which includes a sub-majority dataset and the entire minority dataset. In this way, more hidden outliers can be located and thus exert less influence on the decision boundary, which contributes to both high AUC and accuracy.

Abstract: Systems and methods are provided for suggesting actions for selected text based on content displayed on a mobile device. An example method can include converting a selection made via a display device into a query, providing the query to an action suggestion model that is trained to predict an action given a query, each action being associated with a mobile application, receiving one or more predicted actions, and initiating display of the one or more predicted actions on the display device. Another example method can include identifying, from search records, queries where a website is highly ranked, the website being one of a plurality of websites in a mapping of websites to mobile applications. The method can also include generating positive training examples for an action suggestion model from the identified queries, and training the action suggestion model using the positive training examples.

Abstract: Graphical interactive model selection is provided. A basis function is fit to each plurality of observation vectors defined for each value of a group variable. Basis results are presented within a first sub-window of a first window of a display. Functional principal component analysis (FPCA) is automatically performed on each basis function. FPCA results are presented within a second sub-window of the first window. An indicator of a request to perform functional analysis using the FPCA results based on a predefined factor variable is received in association with the first window. A model is trained using an eigenvalue and an eigenfunction computed as a result of the FPCA for each plurality of observation vectors using the factor variable value as a model effect. (G) Trained model results are presented within a third sub-window of the first window of the display.

Abstract: The present invention solves a problem that there may be a case that an estimated value of regression cannot be calculated depending on a discrimination result when a regression method is applied after a discrimination method, and has a purpose to obtain an estimating equation with high accuracy even when the number of sample groups to which the regression method is applied is small. An estimating equation that satisfies the regression and discrimination at the same time can be obtained by combining a discrimination evaluation function that evaluates discrimination accuracy and a regression evaluation function that evaluates regression accuracy, calculating a combination evaluation function, and optimizing the combination evaluation function.

Abstract: Provided is an information processing apparatus which determines a discharge condition for a chip removal apparatus which discharges an object in order to remove chips, wherein the information processing apparatus observes data indicating a removal efficiency of the chips as a state variable representing a current state of an environment, acquires label data indicating the discharge condition, and learns the state variable and the label data in association with each other.

Abstract: After the temperature response to a single period of heating (SAR segment) is determined, temperature increases for an arbitrary timecourse of heating is determined based upon a convolution of the temperature response curve for a sequence of different SAR segments.