Abstract: A method to prioritize email such that a number of interruptions experienced by a user is reduced may include obtaining a threshold cognitive load of a user and a threshold importance; in response to receiving an email in an inbox of the user, determining an importance of the received email; comparing the importance thereof with the threshold importance; and based on the importance thereof not satisfying the threshold importance, determining a priority thereof with respect to emails in the inbox. The method includes determining a cognitive cost of the received email and that the user is handling a first group of emails, and comparing the priority of the received email with a priority of emails of the first group of emails; obtaining a current cognitive load of the user; and identifying a second group of emails; and presenting the second group of emails to the user.

Abstract: According to an aspect of an embodiment, a method may include receiving vocal input that includes conversational language describing a computer program to be generated. The method may also include generating input text based on the vocal input. The input text may be representative of the conversational language describing the computer program. The method may additionally include generating an intent layout based on the input text. The method may include generating an execution layout based on the intent layout. The execution layout may include computer programming language based on the intent layout. The method may also include generating the computer program based on the computer programming language included in the execution layout.

Abstract: A method of generating computer-readable code may include receiving multiple user functions as designated by a user. The method may also include, for each of the user functions, locating at least one library associated with a given user function within a domain interface file (DIF), where the at least one library identifies a constructor of the given user function. The method may additionally include, based on the constructor, identifying one or more constructor libraries in the DIF that include functions that yield the constructor when executed. The method may additionally include retrieving code from the libraries associated with the user functions and the one or more constructor libraries that include functions that yield the constructor when executed. The method may also include combining the retrieved code into a single program, and providing the single program such that the single program is accessible by an end-user different from the user.

Abstract: A method of tuning a generative model may be provided. A method may include receiving, at a first generative adversarial network (GAN), a first input identifying an item and at least one user-defined attribute for the item. The method may also include generating, via the first GAN, a first image of the item based on the first input. Further, the method may include receiving, at a second GAN, the first image and a second input indicative of a desire for more or less of the at least one user-defined attribute. Moreover, the method may include generating, via the second GAN, a second image of the item based on the first image and the second input.

Abstract: A method of generating computer-readable code may include receiving multiple user functions as designated by a user. The method may also include, for each of the user functions, locating at least one library associated with a given user function within a domain interface file (DIF), where the at least one library identifies a constructor of the given user function. The method may additionally include, based on the constructor, identifying one or more constructor libraries in the DIF that include functions that yield the constructor when executed. The method may additionally include retrieving code from the libraries associated with the user functions and the one or more constructor libraries that include functions that yield the constructor when executed. The method may also include combining the retrieved code into a single program, and providing the single program such that the single program is accessible by an end-user different from the user.

Abstract: A method of generating text having related purposes using a generative adversarial network (GAN) includes receiving a limited dataset including real data with related cognitive value types (types). The method includes applying loss functions to portions of the real data. The portions of the real data are each identified as having one of the types. The loss functions ensure alignment of the portions with corresponding types. The method includes embedding the real data into an encoder output that includes an embedded vector for the cognitive value types. The method includes generating an additional parameter set supplemental to the real data and configured to enhance an expressiveness of a model. The method includes generating statements based on the additional parameter set and the encoder output. The statements include a style of one of the cognitive value types and are related to a common issue addressed by the GAN.

Abstract: A method of generating text using an adversarial network includes receiving a limited dataset. The limited dataset includes real data having actual parameters and actual sentences. The method includes receiving content data that includes a concept related to a portion of the real data or that causes an issue of the real data. The method includes generating relationships between the real data and the content data. The method includes embedding the content data with the real data in an encoder output that includes content vector embedding. The method includes generating an additional parameter set that includes additional parameters and one or more additional statements. The additional parameter set may be supplemental to the real data and configured to enhance an expressiveness of a model. The method includes generating explanatory statement based on the additional parameter set and the relationships.

Abstract: A method may include directing display of a dataset menu listing datasets representative of graphs. The method may include identifying features in the datasets as corresponding to nodes and edges. The method may include selecting local or global mapping to map categorical feature values to numeric values. Local mapping may be selected in response to a distribution of feature values not corresponding across different graphs. Global mapping may be selected in response to a distribution of the feature values corresponding across different graphs. The method may include directing display of configuration settings that indicate the selection between local and global mapping for training a classification model. The method may include obtaining selected configuration settings. The method may include providing the selected configuration settings and datasets to a machine learning backend, which may utilize the machine learning algorithm, datasets, and selected configuration settings to train the classification model.

Abstract: A method to create and to link user profiles in a social networking system may include dynamically determining a current progress level of a first user with respect to a goal of the first user based on data received from a sensor or user input. The method may include, in response to determining that the current progress level of the first user satisfies the threshold progress level with respect to a goal of the first user, changing a user profile of the first user to include an indication that the first user has reached an achievement level with respect to the goal of the first user. The method may include selecting the user profile of the first user of the social networking system from multiple user profiles of other users of the social networking system based on the indication and presenting the user profile to a second user.

Abstract: A method may include extracting feature information from a user history including multiple goal messages. Each of the multiple goal messages may include visual media and text, and may be associated with a goal indicated as completed. Extracting the feature information from the user history may include performing feature detection on the visual media of the multiple goal messages. The feature information from the user history may be analyzed for correlations between features and the completion indications of the associated goals. Feature information may be extracted from a generic goal message. A probability of a user indicating completion of a goal associated with the generic goal message may be determined based at least in part on the feature information from the generic goal message and the correlations between the features included in the multiple goal messages and the indications of the associated goals having been completed.

Abstract: A method may include obtaining a multiple known objects and a player construct, comparing the player construct to the known objects, and determining whether the comparison exceeds a matching threshold. If a comparison exceeds the matching threshold, the player construct is assigned to a class associated with one of the known objects, and a meaningfulness measurement can be determined. The meaningfulness measurement may be based on a quantity of player constructs, including the first player construct, a similarity between elements in the class, and a similarity between the class and one or more other classes. The player construct may be created using physical blocks embedded with sensors or electronic blocks.

Abstract: According to an aspect of an embodiment, a method may include obtaining a data set that includes categories (or features), and a target criteria. The method may further include obtaining a first decision tree model using the data set. The method may further include ranking the categories based on the first decision tree model and removing low-ranking categories from the data set. The method may further include generating a second decision tree model using the data set. The second decision tree model may include branch nodes. Each of branch nodes may represent a branch criteria. The method may further include pruning a branch node. The method may further include designating a remaining branch nodes as a rule node. The method may further include generating a rule based on the branch criteria of the rule node and presenting the rule in a graphical user interface.

Abstract: A method includes receiving, via a network, a join request from a client device for a user to access a digital community. The join request includes a membership eligibility assertion. The method further includes verifying the membership eligibility assertion. The method also includes granting access to the digital community based on the verifying. The method includes receiving a question from the client device via a graphical user interface associated with the digital community. The method also includes identifying a solution to the question, wherein the solution includes an asset. The method further includes sending the solution to the client device via the network.

Abstract: A method may include generating a personalized rating vector associated with a querying user. The personalized rating vector may relate personalized ratings to options. The personalized rating vector may be generated via element-wise multiplication of a user vector, a relevance weight, and a characteristics vector. The user vector may relate user ratings to the querying user and to the options. The relevance weight may be associated with a characteristic of the querying user. The characteristics vector may relate characteristics ratings to a user characteristic and to the options. The user characteristic may correspond at least in part to the characteristic of the querying user. The method may further include generating a recommendation for the querying user based at least in part on the personalized rating vector, the recommendation associated with at least one option of the options of the personalized rating vector.

Abstract: A method may include receiving a first vocal input, which may include conversational language describing a portion of a command to be generated for a voice assistant. The method may include determining a structure of the command based on the first vocal input. The method may include generating a template for the command based on the structure. The template may include a particular sequence of segments. The method may include providing a prompt for a second vocal input that includes conversational language. The second vocal input may correspond to at least one segment of the particular sequence. The method may include receiving the second vocal input. The method may include assigning one or more portions of the first and the second vocal input to corresponding segments of the particular sequence. The method may include generating an executable representation of the command, which may include the particular sequence of segments.

Abstract: A method may include obtaining one or more assumptions from a user, where the assumptions may be associated with a target result in a machine learning system. The method may also include identifying multiple variables, where the variables may represent causality candidates for the target result. The method may additionally include estimating a causal effect for each of the variables, and generating a causality explanation of the target result based on the causal effects for the variables. The method may also include providing the causality explanation to the user.

Abstract: A method may include obtaining data input including one or more words. The method may include determining a set of expressed emotions and a set of expressed emotion probabilities based on the one or more words. The method may include obtaining a set of likelihood probabilities. Each likelihood probability may correspond to a conditional probability of an expressed emotion given an experienced emotion of a group of experienced emotions. The method may include determining a set of experienced emotions of the group of experienced emotions and a set of experienced emotion probabilities based on the set of expressed emotion probabilities and the set of likelihood probabilities. The method may include selecting an experienced emotion of the set of experienced emotions based on the selected experienced emotion corresponding to the highest experienced emotion probability of the set of experienced emotion probabilities. The method may include presenting the selected experienced emotion.

Abstract: A method of tuning a generative model may be provided. A method may include receiving, at a first generative adversarial network (GAN), a first input identifying an item and at least one user-defined attribute for the item. The method may also include generating, via the first GAN, a first image of the item based on the first input. Further, the method may include receiving, at a second GAN, the first image and a second input indicative of a desire for more or less of the at least one user-defined attribute. Moreover, the method may include generating, via the second GAN, a second image of the item based on the first image and the second input.

Abstract: A method of real peak detection includes optimizing a scoring function using training signals with known peaks and known features. The method includes receiving an input signal measured from a mobile sensor and representative of a cyclic biological process. The method includes filtering the input signal to remove low and high frequency noise. The method includes identifying candidate peaks and troughs within a selected time range of the input signal. The method includes extracting a feature that describes properties of the two or more candidate peaks. The method includes scoring the candidate peaks using the scoring function, selecting a real peak as the candidate peak with the highest score, and generating a biologic interval data set with the real peak and another peak that is representative of health markers. The method includes assessing a condition of the patient based on the biologic interval data set.

Abstract: A method to change a behavior of a user includes receiving state data indicative of a current state of a user. The method includes receiving sensor data generated by one or more sensors, the sensor data indicative of one or more behaviors of the user. The method includes receiving payment from the user to purchase a virtual attribute, at least a portion of the payment to be returned to the user responsive to an improvement to the one or more behaviors over an earn-back time period. The method includes determining a behavior-based virtual attribute of the user based on the sensor data. The method includes estimating a future state of the user from the current state of the user, the behavior-based virtual attribute, and the purchased virtual attribute. The method includes generating graphical data including a visualization of the future state of the user to display to the user.