Abstract: Described are a system, method, and computer program product for optimizing a predictive condition classification model and automatically enacting reactive measures based thereon. The method includes receiving event data representative of a plurality of events. The method also includes receiving the predictive condition classification model configured to categorize each event as satisfying a condition or not. The predictive condition classification model is configured to order the plurality of events by likelihood of satisfying the condition. The method includes generating a performance evaluation dataset and plotting data configured to cause a visual display to represent at least two model performance metrics of the performance evaluation dataset on a same output plot. The method includes automatically rejecting a top percent of the plurality of events for suspected satisfaction of the condition, determined at least partially from a customized rejection algorithm or a preset rejection algorithm.

Abstract: Described herein is a conversation engine that can be used in a system such as a personal digital assistant or search engine that combines a dynamic knowledge graph built during execution of a request and one or more static knowledge graphs holding long term knowledge. The conversation engine comprises a state tracker that holds the dynamic knowledge graph representing the current state of the conversation, a policy engine that selects entities in the dynamic knowledge graph and executes actions provided by those entities to move the state of the conversation toward completion, and a knowledge graph search engine to search the static knowledge graph(s). The conversation is completed by building the dynamic knowledge graph over multiple rounds and chaining together operations that build toward completion of the conversation. Completion of the conversation results in completion of a request by a user.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining communication data streams, extracting data relevant to a point of view of a user, and generating a point of view record in a knowledge base that may be utilized by another user communicating with the user.

Abstract: Herein are techniques for exploring hyperparameters of a machine learning model (MLM) and to train a regressor to predict a time needed to train the MLM based on a hyperparameter configuration and a dataset. In an embodiment that is deployed in production inferencing mode, for each landmark configuration, each containing values for hyperparameters of a MLM, a computer configures the MLM based on the landmark configuration and measures time spent training the MLM on a dataset. An already trained regressor predicts time needed to train the MLM based on a proposed configuration of the MLM, dataset meta-feature values, and training durations and hyperparameter values of landmark configurations of the MLM. When instead in training mode, a regressor in training ingests a training corpus of MLM performance history to learn, by reinforcement, to predict a training time for the MLM for new datasets and/or new hyperparameter configurations.

Abstract: A method includes fusing multi-modal sensor data from a plurality of sensors having different modalities. At least one region of interest is detected in the multi-modal sensor data. One or more patches of interest are detected in the multi-modal sensor data based on detecting the at least one region of interest. A model that uses a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A perception indication of the post-processing result is output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

Abstract: The disclosure provides a method, a system and a storage medium for predicting power load probability density based on deep learning. The method comprises: S101, collecting power load data of a user, meteorological data and air quality data in a preset historical time period, and dividing the collected data into a training set and a test set; S102, determining a deep learning model for predicting power load; S103, inputting the test set into the deep learning model for predicting power load, and obtaining power load prediction data of the user at different quantile points in a third time interval; S104, performing kernel density estimation and obtaining a probability density curve of the power load of the user in the third time interval.

Abstract: In one embodiment, a system is configured to identify, based on predetermined criteria, a first set of users of an online system who belong to a population segment. The system may monitor activities performed by the first set of users on the online system over a predetermined period of time and store the monitored activities as time-series data. A feature set associated with the first set of users may be generated by transforming the time-series data into a frequency domain. The system may train a machine-learning model using the feature set and other feature sets to determine whether activities associated with a given set of users exhibit diurnal behavior pattern. Using the trained machine-learning model, the system may determine whether activities performed by a second set of users on the online system exhibit diurnal behavior pattern.

Abstract: A distributed system may implement identifying correlated workloads for resource allocation. Resource data for resources hosted at resource hosts in a distributed system may be analyzed to determine behavioral similarities. Historical behavior data or resource configuration data, for instance, may be compared between resources. Behaviors between resources may be identified as correlated according to the determined behavioral similarities. An allocation of one or more resource hosts in the distributed system may be made for a resource based on the behaviors identified as correlated. For instance, resources may be migrated from a current resource host to another resource host, new resources may be placed at a resource host, or resources may be reconfigured into different resources. Machine learning techniques may be implemented to refine techniques for identifying correlated behaviors.

Abstract: System and method of detecting friction in a website comprising a plurality of webpages and links includes a database sever, an application executed by a processor, and a management dashboard. The application extracts text data and web usage data from the website, segments the website into three funnel stages, identifies an anomaly in the web usage data, quantifies the impacts of the webpages and links, identifies the friction and the underlying root cause, and displays the friction in the management dashboard.

Abstract: Presence of malicious code can be identified in one or more data samples. A feature set extracted from a sample is vectorized to generate a sparse vector. A reduced dimension vector representing the sparse vector can be generated. A binary representation vector of reduced dimension vector can be created by converting each value of a plurality of values in the reduced dimension vector to a binary representation. The binary representation vector can be added as a new element in a dictionary structure if the binary representation is not equal to an existing element in the dictionary structure. A training set for use in training a machine learning model can be created to include one vector whose binary representation corresponds to each of a plurality of elements in the dictionary structure.

Abstract: A computer system includes a processor and a memory connected to the processor, and manages pieces of reward function information for defining rewards for states and actions of the control targets for each of the control targets. The pieces of reward function information includes first reward function information for defining the reward of a first control target and second reward function information for defining the reward of a second control target. When updating the first reward function information, the processor compares the rewards of the first reward function information and the second reward function information with each other, specifies a reward, which is reflected in the first reward function information from rewards set in the second reward function information, updates the first reward function information on the basis of the specified reward, and decides an optimal action of the first control target by using the first reward function information.

Abstract: Disclosed are systems and methods providing for automation of enterprise and other processes. The systems and methods involve receiving historical process data, applying process mining techniques and generating process models. The process models can be used to identify automation candidates. One or more automation tools designed and configured for the identified automation candidates can be deployed to automate or to increase the efficiency of the process. In one embodiment, automation tools include artificial intelligence networks, which can label a set of input data according to determined or preconfigured domain-specific labels. An aggregator module can combine the similarly labeled data as part of automating a process or to increase the efficiency of a process.

Abstract: Embodiments of the present invention provide a computer-implemented method for performing unsupervised time-series feature learning. The method generates a set of reference time-series of random lengths, in which each length is uniformly sampled from a predetermined minimum length to a predetermined maximum length, and in which values of each reference time-series in the set are drawn from a distribution. The method generates a feature matrix for raw time-series data based on a set of computed distances between the generated set of reference time-series and the raw time-series data. The method provides the feature matrix as an input to one or more machine learning models.

Abstract: In some aspects, computer-implemented methods of identifying patterns in time-series social-media data. In an embodiment, the method includes applying a deep-learning methodology to the time-series social-media data at a plurality of temporal resolutions to identify patterns that may exist at and across ones of the temporal resolutions. A particular deep-learning methodology that can be used is a recursive convolutional Bayesian model (RCBM) utilizing a special convolutional operator. In some aspects, computer-implemented methods of engineering outcome-dynamics of a dynamic system. In an embodiment, the method includes training a generative model using one or more sets of time-series data and solving an optimization problem composed of a likelihood function of the generative model and a score function reflecting a utility of the dynamic system.

Abstract: This present disclosure relates to systems and methods for providing an Adaptive Analytical Behavioral and Health Assistant. These systems and methods may include collecting one or more of patient behavior information, clinical information, or personal information; learning one or more patterns that cause an event based on the collected information and one or more pattern recognition algorithms; identifying one or more interventions to prevent the event from occurring or to facilitate the event based on the learned patterns; preparing a plan based on the collected information and the identified interventions; and/or presenting the plan to a user or executing the plan.

Abstract: Training query intents are allocated for multiple training entities into training time intervals in a time series based on a corresponding query intent time for each training query intent. Training performance results for the multiple training entities are allocated into the training time intervals in the time series based on a corresponding performance time of each training performance result. A machine learning model for a training milestone of the time series is trained based on the training query intents allocated to a training time interval prior to the training milestone and the training performance results allocated to a training time interval after the training milestone. Target performance for the target entity for an interval after a target milestone in the time series is predicted by inputting to the trained machine learning model target query intents allocated to the target entity in a target time interval before the target milestone.

Abstract: Techniques are provided for anomaly detection in time-series data using state inference and machine learning. An exemplary method comprises: obtaining detected states of a plurality of data samples in temporal data, wherein each data sample in the temporal data has a corresponding detected state; obtaining a likelihood that each of the data samples belongs to the corresponding detected state; obtaining a distribution of likelihoods of the data samples indicating a number of observations of each of a plurality of likelihood values; training, using a supervised learning technique, an anomaly detection model that, given the distribution of likelihoods and one or more anomaly thresholds, generates a quality score for each of the anomaly thresholds; and selecting at least one anomaly threshold based on the quality score, wherein the trained anomaly detection model is applied to detect anomalies in new temporal data samples using the selected at least one anomaly threshold.

Abstract: A computer-implemented method for generating an interpretable kernel embedding for heterogeneous data. The method can include identifying a set of base kernels in the heterogeneous data; and creating multiple sets of transformed kernels by applying a unique composition rule or a unique combination of multiple composition rules to the set of base kernels. The method can include fitting the multiple sets into a stochastic process model to generate fitting scores that respectively indicate a degree of the fitting for each of the multiple sets; storing the fitting scores in a matrix; and standardizing the matrix to generate the interpretable kernel embedding for the heterogeneous data.

Abstract: Computer systems and computer-implemented methods train and/or operate, once trained, a machine-learning system that comprises a plurality of generator-detector pairs. The machine-learning computer system comprises a set of processor cores and computer memory that stores software. When executed by the set of processor cores, the software causes the set of processor cores to implement a plurality of generator-detector pairs, in which: (i) each generator-detector pair comprises a machine-learning data generator and a machine-learning data detector; and (ii) each generator-detector pair is for a corresponding cluster of data examples respectively, such that, for each generator-detector pair, the generator is for generating data examples in the corresponding cluster and the detector is for detecting whether data examples are within the corresponding cluster.