Abstract: A user device may obtain sensor data related to a physical environment. The user device may process the sensor data to determine that a potential threat exists in the physical environment and a threat score associated with the potential threat. The user device may determine that the threat score satisfies a threat score threshold. The user device may obtain, based on determining that the threat score satisfies the threat score threshold, additional information related to the physical environment. The user device may generate, based on the additional information related to the physical environment and at least one of the sensor data, information indicating the potential threat in the physical environment, or the threat score associated with the potential threat, threat determination information associated with the physical environment. The user device may perform, based on the threat determination information associated with the physical environment, one or more actions.

Abstract: In certain embodiments, document-based resolution of user inquiries may be facilitated. A predicted intent of the user is determined based on chat activity information associated with the user. A response to a user inquiry may be provided to the user via a chat interface based on the predicted intent. User response may be obtained for the response, which may indicate a failure in providing a resolution to the user (e.g., regarding a user inquiry). Upon detecting a failure in providing the resolution, a document associated with the user and matching the predicted intent may be obtained and presented to via the chat interface. The document may have content related to the predicted intent. The document may be presented as a response to the user response to seek a confirmation from the user regarding its relevance to the user inquiry.

Abstract: Methods, systems, and computing devices for visualizing natural language processing algorithm processes are described herein. A plurality of categories may be determined. Each color of a plurality of colors may correspond to the categories. Text content may be processed using a natural language processing algorithm. Confidence values indicating, for each of a plurality of portions of the text content, a degree of confidence corresponding to one or more of the plurality of categories may be determined. Display colors may be determined based on the confidence values. A user interface comprising a visualization of the text content may be displayed, and the user interface may be configured to show each portion of the text content using a display color such that the user interface indicates changes in confidence across the plurality of characters.

Abstract: Disclosed herein are system, method, and computer program product embodiments for a text-to-speech system. An embodiment operates by identifying a portion of content of the document, that is to be replaced with a summary associated with the content responsive to a request for an audible version of the document. A first request for the audible version of the document is received. A first summary of the content at a first level of detail is generated. The first summary is audibly output. A second request for additional information is received. A second summary of the content at different level of detail is generated. The second summary of the content at the second level of detail is audibly output.

Abstract: Methods and systems are described herein for improvements to authenticate users, particularly authenticating a user based on data known to the user. For example, methods and systems allow for users to be securely authenticated based on data known to the users over remote communication networks without storing the data known to the users. Specifically, methods and systems authenticate users by requiring users to select images that are known to the users. For example, the methods and systems may generate synthetic images based on the user's own images and require the user to select the synthetic image, from a set of a set of images, that is known to the user to authenticate the user. Moreover, the methods and systems alleviate storage and privacy concerns by not storing the data known to the users.

Abstract: A secure method for resetting the password for an account is disclosed. During the setup of the account, the user can provide the service provider with a media file, and when the user asks the service provider to reset the password for the account, the user will be prompted with several media files. The user can be asked to identify the media file that the user provided to the service provider at the time of the setup of the account. If the user properly identifies the media file, the password will be reset.

Abstract: Systems, methods, articles of manufacture, and computer program products to: train a prediction model using a machine learning process, the prediction model configured to estimate whether further application of a hyperparameter tuning technique will cause an improvement in at least one of the hyperparameters; select the hyperparameters using the tuning technique; apply the prediction model to determine if further adjustment of the hyperparameters is likely to improve the success metric; and terminate the tuning technique when: accuracy of the prediction model in predicting improvement in a hyperparameter is above a predetermined accuracy threshold, and the prediction model predicts that further application of the tuning technique will not result in an improvement to the hyperparameter; or the accuracy of the prediction model in predicting improvement in the parameter is below the predetermined accuracy threshold, and an accuracy of hyperparameter adjustment is determined to be below a predetermined adjustment

Abstract: Systems and methods for classifying data are disclosed. For example, a system may include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving training data comprising a class. The operations may include training a data classification model using the training data to generate a trained data classification model. The operations may include receiving additional data comprising labeled samples of an additional class not contained in the training data. The operations may include creating a synthetic data generator. The operations may include training the synthetic data generator to generate synthetic data corresponding to the additional class. The operations may include generating a synthetic classified dataset comprising the additional class. The operations may include retraining the trained data classification model using the synthetic classified dataset.

Abstract: Systems and methods for architecture embeddings for efficient dynamic synthetic data generation are disclosed. The disclosed systems and methods may include a system for generating synthetic data configured to perform operations. The operations may include retrieving a set of rules associated with a first data profile and generating, by executing a hyperparameter search, a plurality of hyperparameter sets for generative adversarial networks (GANs) that satisfy the set of rules. The operations may include generating mappings between the hyperparameter sets and the first data profile and storing the mappings in a hyperparameter library. The operations may include receiving a request for synthetic data, the request indicating a second data profile and selecting, from the mappings in the hyperparameter library, a hyperparameter set mapped to the second data profile. The operations may include building a GAN using the selected hyperparameter set and generating, using the GAN, a synthetic data set.

Abstract: Systems and methods for ATM fraud detection are presented. ATM fraud detection may be provided in the context of including a currency sensor in the ATM to count currency notes. ATM fraud detection may be obtained by using a currency sensor, such as a scanner, to image and count any currency notes that remain after being dispensed to a user, and determining if the count is correct for the currency notes dispensed. A count discrepancy resulting from removal of some but not all dispensed currency notes would indicate attempted theft or fraud.

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: Systems and methods for formatting data are disclosed. For example, a system may include at least one memory storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving data comprising a plurality of sequences of data values and training a recurrent neural network model to output conditional probabilities of subsequent data values based on preceding data values in the data value sequences. The operations may include generating conditional probabilities using the trained recurrent neural network model and the received data. The operations may include determining a data format of a subset of the data value sequences, based on the generated conditional probabilities, and reformatting at least one of the data value sequences according to the determined data format.

Abstract: The present disclosure provides systems and methods for synthetic data generation. A recurrent neural network can be trained for synthetic data generation by obtaining a sequence of elements and determining, using a classifier, that the sequence corresponds to a token. In response to the determination, a recurrent neural network configured to use a first vocabulary including the elements can be modified to use a second vocabulary, the second vocabulary including the token and the first vocabulary. The modified recurrent neural network can be trained using the token and the sequence of elements. The trained recurrent neural network can be used to generate synthetic data. A classifier can detect sequences of elements in the synthetic data corresponding to tokens. The tokens can replace the sequences of elements in the generated synthetic data and can be provided to the trained recurrent neural network to continue synthetic data generation.

Abstract: Exemplary embodiments relate to the secure storage of security questions through an immutable log, such as a blockchain. The security questions may be stored in a centralized location, accessible from an application or browser tab running on the user's device. When a security question is required, such as to perform a password reset on a website, the website may interact with the application or browser tab, which retrieves the question(s) from the blockchain. The user may enter their answers to the question(s), which may be hashed by the application or tab. The hashed answers may be entered into the original requesting website, which may verify with the blockchain that the correct answers have been provided. Thus, the requesting website sees neither the questions nor the answers. Additional security features may include logging requests for questions, so that a user can determine if a security question may have been compromised.

Abstract: Exemplary embodiments pertain to new techniques for classifying or labeling organized data. A major impediment to implementing high-quality machine learning is the lack of readily accessible labeled data. In some cases, data can be classified using a classifier, but these solutions can be inaccurate and slow. Exemplary embodiments address the problem of obtaining accurate labeled data in a timely manner by applying a classifier configured to operate on character-level embeddings. Among other advantages, this can help the classifier to recognize information contained within a data unit, such as a cell of a table. The classifier may operate within the organizational structure of the data, such as by operating across a particular row or column of a table. Because data within a particular row or column is often temporally organized (e.g., transactions that are logged in chronological order), row- or column-based approaches can yield more accurate results.

Abstract: Described herein are embodiments for managing comments in a program code file. A system may select program code and compile it to an intermediary code. The system may compare the intermediary code to a library of intermediary code snippets associated with comments. Based on the comparison, a system may recognize the code to be obsolete. In some embodiments, a system may generate one or more recommendations to update a code. Based on received feedback regarding a recommendation, a system may accordingly update a code.

Abstract: A method includes storing, by one or more processors of one or more computing devices, a plurality of datasets in a non-transitory computer memory associated with the one or more computing devices. A plurality of index representations is generated where each one of the plurality of index representations includes a compressed representation of a respective one of the plurality of datasets. The plurality of index representations is stored in the non-transitory computer memory. A sample dataset is received by the one or more processors. A sample dataset representation is generated that includes a compressed representation of the sample dataset. A determination that at least one of the plurality of datasets is most similar to the sample dataset based on the sample dataset representation and the plurality of index representations is performed.

Abstract: Methods for generating data models using a generative adversarial network can begin by receiving a data model generation request by a model optimizer from an interface. The model optimizer can provision computing resources with a data model. As a further step, a synthetic dataset for training the data model can be generated using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric. The computing resources can train the data model using the synthetic dataset. The model optimizer can evaluate performance criteria of the data model and, based on the evaluation of the performance criteria of the data model, store the data model and metadata of the data model in a model storage. The data model can then be used to process production data.

Abstract: Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second sub set.

Abstract: An exemplary system, method, and computer-accessible medium can include, for example, (a) receiving a dataset(s), (b) determining if a misclassification(s) is generated during a training of a model(s) on the dataset(s), (c) generating a synthetic dataset(s) based on the misclassification(s), and (d) determining if the misclassification(s) is generated during the training of the model(s) on the synthetic dataset(s). The dataset(s) can include a plurality of data types. The misclassification(s) can be determined by determining if one of the data types is misclassified. The dataset(s) can include an identification of each of the data types in the dataset(s).