Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory using reinforcement learning. One of the methods includes providing an output derived from the system output portion of the neural network output as a system output in the sequence of system outputs; selecting a memory access process from a predetermined set of memory access processes for accessing the external memory from the reinforcement learning portion of the neural network output; writing and reading data from locations in the external memory in accordance with the selected memory access process using the differentiable portion of the neural network output; and combining the data read from the external memory with a next system input in the sequence of system inputs to generate a next neural network input in the sequence of neural network inputs.

Abstract: Embodiments are directed to managing data correlation over a network. Role success models that correspond to roles and to success criteria may be provided. A student profile that includes skill vectors may be provided based on student information. Role success models may be employed to determine intermediate scores based on the skill vectors and the success criteria. A predictive score for the student that corresponds with a predicted performance of the student in the roles may be generated based on the one or more intermediate scores. Actions for the student may be determined based on a mismatch of the skill vectors and role skill vectors that correspond to the roles. In response to the student performing the actions: updating the one or more skill vectors based on a completion of the actions; and updating the predictive score based on the role success models and the updated skill vectors.

Abstract: Statistical modeling techniques based neural network models for generating intelligence reports is provided. The system obtains test dataset and training dataset, each of which include at least one of images and elements. Statistical modeling techniques are identified and selected based on the test dataset for normalizing the test dataset to obtain normalized dataset. The system further associates, using one or more clustering techniques a unique cluster head to at least one of (i) normalized elements set and (ii) normalized images set in the normalized dataset to obtain a labeled dataset. The labeled dataset is further analysed by integrated trained modeling techniques into neural network model(s) and intelligence reports are generated.

Abstract: A method includes training an artificial neural network with training data that comprises a sets of design parameter values for design parameters for circuit traces in a high speed communication link, determining an output formula that relates a sets of design parameters to a corresponding output parameter for the circuit traces in response to training the artificial neural network, running the output formula using a second set of design parameter values to obtain a corresponding set of output parameters for the circuit traces, determining that the corresponding set of output parameters differ from a set of modeled output parameters by less than a predefined percentage, and fabricating a circuit trace in a printed circuit board based upon the output formula in response to determining that the corresponding set of output parameters differ from the set of modeled output parameters by less than the predefined percentage.

Abstract: A commercial process with a dependent variable can be associated with a set of independent variables. The commercial process can continuously provide data collection opportunities. An intervention is designed using a model to predict the dependent outcome. The actual outcome of the intervention can be determined within the window of utility for these data. One objective is to improve intervention outcomes with prediction. Purely random outcomes (no model prediction) and outcomes resulting from the intervention (model operations) are aggregated into separate files—a sequence of control model data files and a sequence of model data files of operational data. These model data files and control model data files are used to analyze model performance and to react automatically when identified conditions warrant.

Abstract: A method includes receiving, by a processor, bias data categories. A data input from a user for classification in data categories is received. A classification machine learning model is utilized to classify the data input in at least one data category and determine a first confidence probability in a classification outcome. A bias filter machine learning model is utilized to determine a second confidence probability that the classification outcome of classifying the data input into the at least one data category is based on at least one bias characteristic associated with at least one bias data category. A gate machine learning model is utilized to determine when to output the classification outcome of classifying the data input into the at least one data category to a computing device of a user based at least in part on the first confidence probability, the second confidence probability, and a predefined bias threshold.

Abstract: The present disclosure provides methods for applying artificial neural networks to flow cytometry data generated from biological samples to diagnose and characterize cancer in a subject.

Abstract: Mechanisms are provided for validating a candidate answer to an input question. A candidate answer to an input question is identified using a natural language processing of the input question and a corpus of information from which the candidate answer is identified. A validator is selected to apply to the candidate answer based on a characteristic of a correct answer for the input question. The validator is applied to the candidate answer to evaluate whether or not criteria of the validator are met by the candidate answer. Validation information is generated based the evaluation of whether or not criteria of the validator are met by the candidate answer. The validation information is stored in a validation status object associated with the input question.

Abstract: Disclosed herein is a denoising device including a deriving part configured to, when corrupted noise data corrupted due to noises is received from source data, derive an estimated loss which is estimated when each symbol within noise data is reconstructed to the source data based on a predefined noise occurrence probability, a processor to process training of a defined learning model by including parameters related with the reconstruction of the source data from the noise data based on context composed of a sequence of neighbored symbols based on each symbol within the noise data and pseudo-training data using the estimated loss corresponding to the context, and an output part to output reconstructed data in which each symbol within the noise data is reconstructed to a symbol of the source data through a denoiser formed based on a result of the training processing.

Abstract: According to one embodiment, a learning apparatus includes a first rule generator, a feature value calculator, a related word extractor, a second rule generator, and a learning unit. The first rule generator generates a first rule to label the event candidate, the first rule including a keyword of the event candidate. The feature value calculator calculates feature values of other words included in the text other than the event candidate. The related word extractor extracts a related word relating to the keyword from the other words using the feature values. The second rule generator generates a second rule to label the event candidate, the second rule being different from the first rule and including the related word. The learning unit generates learning data associating the keyword, the related word, and labeled event candidate with each other.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving information regarding a temporal sequence of events; performing a temporal topic machine learning operation on the temporal sequence of events; generating a cognitive profile based upon the information generated by performing the temporal topic machine learning operation; and, generating a cognitive insight based upon the cognitive profile generated using the temporal topic machine learning operation.

Abstract: An online system maintains machine learning models that determine risk scores for content items indicating likelihoods of content items violating content policies associated with the machine learning models. When the online system obtains an additional content policy, the online system applies a maintained machine learning model to a set including content items previously identified as violating or not violating the additional content policy. The online system maps the risk scores determined for content items of the set to likelihoods of violating the additional content policy based on the identifications of content times in the set violating or not violating the additional content policy. Subsequently, the online system applies the maintained machine learning model to content items and determines likelihoods of the content items violating the additional content policy based on the mapping of risk scores to likelihood of violating the additional content policy.

Abstract: In some examples, a system includes an article of personal protective equipment (PPE) comprising one or more sensors, the one or more sensors configured to generate usage data that is indicative of an operation of the article of PPE; and at least one computing device comprising a memory and one or more computer processors that: receive the usage data that is indicative of the operation of the article of PPE; apply the usage data to a safety learning model that predicts a likelihood of an occurrence of a safety event associated with the article of PPE based at least in part on previously generated usage data that corresponds to the safety event; and perform, based at least in part on predicting the likelihood of the occurrence of the safety event, at least one operation.

Abstract: A method, system, and/or computer program product analyses event transactional related data to generate insights and predictions, which are pre-created to efficiently respond to requests for prediction/forecasting information, in order to improve the operation of the prediction-generating computer. One or more processors receive a series of structured data, where each entry (Ei) from the series of structured data has one or more time fields Tk and one or more attributes Aj. In response to determining that the series of structured data is transactional, one or more processors select a time field Tkr that meets an aggregation criterion, and then aggregate the transactional data from the time field Tkr into a time series data format. One or more processors consolidate results from a time series analysis and a regression analysis of the transformed transactional data to create a consolidated result, which is used to respond to a request for prediction/forecasting information.

Abstract: In one embodiments, one or more computer systems receive, from a client device of a user, a request to access content. The computer systems access a plurality of assets representing the content. The computer devices calculate, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content. The computer devices selects one of the assets based on the probability. The computer devices send, to the client device, the selected asset.

Abstract: Methods and apparatus for detecting abusive language are disclosed. In one embodiment, a set of character N-grams is ascertained for a set of text. Feature values for a plurality of features of the set of text are determined, based, at least in part, on the set of character N-grams. A computer-generated model is applied to the feature values for the plurality of features to generate a score for the set of text, where the model includes a plurality of weights, each of the weights corresponding to one of the features. It may then be determined whether the set of text includes abusive language based, at least in part, on the score.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio processing using neural networks. One of the systems includes multiple neural network layers, wherein the neural network system is configured to receive time domain features of an audio sample and to process the time domain features to generate a neural network output for the audio sample, the plurality of neural network layers comprising: a frequency-transform (F-T) layer that is configured to apply a transformation defined by a set of F-T layer parameters that transforms a window of time domain features into frequency domain features; and one or more other neural network layers having respective layer parameters, wherein the one or more neural network layers are configured to process frequency domain features to generate a neural network output.

Abstract: A method for using machine learning techniques to analyze past decisions made by administrators concerning account opening requests and to recommend whether an account opening request should be allowed or denied. Further, the machine learning techniques determine various other products that the customer may be interested in and prioritizes the choices of options that the machine learning algorithm determines appropriate for the customer.

Abstract: A controllable resistive element and method for updating the resistance of the same includes a state device configured to provide a voltage-controlled resistance responsive to a voltage input. A battery is configured to apply a voltage to the voltage input of the state device based on a charge stored in the battery. A write device is configured to charge the battery responsive to a write signal. An erase device is configured to discharge the battery responsive to an erase signal.

Abstract: Methods and systems for refactoring a problem include refactoring an original problem having a dimension that cannot be broken into an integer number of portions, each portion having a number of problem elements equal to a size of a systolic array, into a new problem having a dimension that can be broken into an integer number of portions, each portion having a number of problem elements equal to the size of the systolic array. The new problem is solved with the systolic array. The systolic array has a size defined by an integer number of processing elements and is configured to solve portions of problems having a number of problem elements equal to the number of processing elements.