Abstract: A method is provided for reinforcement learning. The method includes obtaining, by a processor device, a first set and a second set of state-action tuples. Each of the state-action tuples in the first set represents a respective good demonstration. Each of the state-action tuples in the second set represents a respective bad demonstration. The method further includes training, by the processor device using supervised learning with the first set and the second set, a neural network which takes as input a state to provide an output. The output is parameterized to obtain each of a plurality of real-valued constraint functions used for evaluation of each of a plurality of action constraints. The method also includes training, by the processor device, a policy using reinforcement learning by restricting actions predicted by the policy according to each of the plurality of action constraints with each of the plurality of real-valued constraint functions.

Abstract: Mechanisms are provided for detecting interesting decision rules from a set of decision rules in a tree ensemble. Each tree in the tree ensemble is traversed in order to assign each individual data record from a set of data records to an identified leaf node in each tree. Predicted values are determined for the tree ensemble based on predictions provided by each leaf node to which each individual data record is assigned. Interesting sub-indices for decision rules from the set of decision rules are determined and, for each decision rule corresponding to the leaf nodes in the tree ensemble, the sub-indices are combined into interestingness index It. The decision rules are ranked corresponding to the leaf nodes in the tree ensemble according to the associated value of the interestingness index It and a subset of the decision rules corresponding to the leaf nodes in the tree ensemble are reported.

Abstract: Methods, systems and computer program products generating diverse and representative set of samples from a large amount of transaction data are disclosed. A data sampling system receives transaction records. Each transaction record has multiple text segments. The system selects a subset of transaction records that contain least frequently appeared text segments. The system determines a respective vector representation for each selected transaction record. The system can measure similarity between transaction records based on the vector representations. The system assigns the selected transaction records to multiple clusters based on the vector representations and designated dimensions of importance. The system identifies one or more anchors that include transaction records on boundaries between clusters. The system filters the subset of transaction records by removing transaction records that are close to the anchors.

Abstract: We present the architecture of a high-performance constraint solver R-Solve that extends the gains made in SAT performance over the past fifteen years on static decision problems to problems that require on-the-fly adaptation, solution space exploration and optimization. R-Solve facilitates collaborative parallel solving and provides an efficient system for unrestricted incremental solving via Smart Repair. R-Solve can address problems in dynamic planning and constrained optimization involving complex logical and arithmetic constraints.

Abstract: We present the architecture of a high-performance constraint solver R-Solve that extends the gains made in SAT performance over the past fifteen years on static decision problems to problems that require on-the-fly adaptation, solution space exploration and optimization. R-Solve facilitates collaborative parallel solving and provides an efficient system for unrestricted incremental solving via Smart Repair. R-Solve can address problems in dynamic planning and constrained optimization involving complex logical and arithmetic constraints.

Abstract: A method of identifying an optimum treatment for a patient suffering from coronary artery disease, comprising: (i) providing patient information selected from: (a) status in the patient of one or more coronary disease associated biomarkers; (b) one or more items of medical history information selected from prior condition history, intervention history and medication history; (c) one or more items of diagnostic history, if the patient has a diagnostic history; and (d) one or more items of demographic data; (ii) aggregating the patient information in: (a) a Bayesian network; (b) a machine learning and neural network; (c) a rule-based system; and (d) a regression-based system; (iii) deriving a predicted probabilistic adverse event outcome for each intervention comprising percutaneous coronary intervention by placement of a bare metal stent, or a drug-coated stent; or by coronary artery bypass grafting; and (iv) determining the intervention having the lowest predicted probabilistic adverse outcome.

Abstract: A system for generating digital models of nitrogen availability based on field data, weather forecast data, and models of water flow, temperature, and crop uptake of nitrogen and water is provided. In an embodiment, field data and forecast data are received by an agricultural intelligence computing system. Based on the received data, the agricultural intelligence computing system models changes in temperature of different soil layers, moisture content of different soil layers, and loss of nitrogen and water to the soil through crop uptake, leaching, denitrification, volatilization, and evapotranspiration. The agricultural intelligence computing system creates a digital model of nitrogen availability based on the temperature, moisture content, and loss models.

Abstract: Methods, systems and computer program products for query processing are provided herein. A computer-implemented method includes receiving a first query from a user, determining whether the first query is capable of being answered using symbolic reasoning performed on data of a symbolic knowledge base, and executing the symbolic reasoning to generate a first query answer in response to a determination that the first query is capable of being answered using the symbolic reasoning. Axioms are extracted from a plurality of documents when it is determined that a second query is not capable of being answered using the symbolic reasoning. The method further includes determining whether the axioms are consistent with the symbolic knowledge base, and generating a second query answer based on the axioms in response to a determination that the one or more axioms are consistent with the symbolic knowledge base.

Abstract: An apparatus, a program-stored storage medium and a method with an inference engine can execute inference using a minimum ruleset in various applications. The apparatus includes: a machine learning engine being a classifying-type engine configured to include adapted-to-category learning models each generated by using each adapted-to-category set of teacher data, the adapted-to-category set being obtained by classifying teacher data for each category, and to use the learning models to output a category data corresponding to the inputted object data; a ruleset selector configured to select, from rulesets each prepared for each category and stored in a rule base, a ruleset corresponding to the category data outputted from the machine learning engine; and a rule engine configured to execute inference to the inputted object data by using the ruleset selected by the ruleset selector, and to output the inference result.

Abstract: Systems, methods, and non-transitory computer readable media can determine one or more actions that a user is likely to take on a page associated with a social networking system, based on one or more first machine learning models. One or more card types that correspond to the one or more actions can be ranked based on a second machine learning model. One or more cards can be generated based on the ranked card types, and each card can include a recommended action associated with the page.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying user behavior as anomalous. One of the methods includes obtaining user behavior data representing behavior of a user in a subject system. An initial model is generated from training data, the initial model having first characteristic features of the training data. A resampling model is generated from the training data and from multiple instances of the first representation for a test time period. A difference between the initial model and the resampling model is computed. The user behavior in the test time period is classified as anomalous based on the difference between the initial model and the resampling model.

Abstract: Techniques described herein include systems and methods for evaluating an unsupervised machine learning model. In some embodiments, the system identifies item-to-item similarity values based on historical transaction data. The system may also generate collection data for a number of users based on the historical transaction data. Similarity matrices may be created for each pair of users that include rows associated with a first collection and columns associated with a second collection. Each data field in the similarity matrix may indicate an item-to-item similarity value as identified by the system. In some embodiments, a similarity score may be calculated for the user pair based on the item-to-item similarity values included in the similarity matrix. In some embodiments, the system may generate a graphical summary representation of the similarity matrix.

Abstract: A collection of clusters are selected to be used in training in an active learning workflow when using clusters to train supervised entity resolution in data sets. A collection of records is provided wherein each record in the collection has a cluster membership. A collection of record pairs is also provided, each record pair containing two distinct records from the collection of records, and each record pair having a similarity score. A collection of clusters is generated with uncertainty from the collection of records and the collection of record pairs. A subset of the collection of clusters with uncertainty is then selected using weighted sampling, wherein a function of the cluster uncertainty is used as the weight in the weighted sampling. The subset of the collection of clusters with uncertainty is the collection of clusters for training in and active learning workflow when using clusters to train supervised entity resolution in data sets.

Abstract: A computational system can include digital circuitry and analog circuitry, for instance a digital processor and a quantum processor. The quantum processor can operate as a sample generator providing samples. Samples can be employed by the digital processing in implementing various machine learning techniques. For example, the digital processor can operate as a restricted Boltzmann machine. The computational system can operate as a quantum-based deep belief network operating on a training data-set.

Abstract: A technique for generating soft labels for training is disclosed. A teacher model having a teacher side class set is prepared. A collection of class pairs for respective data units is obtained. Class pairs includes classes labelled to corresponding data units from the teacher side class set and a student side class set different from the teacher side class set. A training input is fed into the teacher model to obtain a set of outputs for the teacher side class set. A set of soft labels for the student side class set is calculated from the set of the outputs by using at least an output obtained for a class within a subset of the teacher side class set having relevance to the member of the student side class set, based at least in part on observations in the collection of the class pairs.

Abstract: Mechanisms are provided for detecting interesting decision rules from a set of decision rules in a tree ensemble. Each tree in the tree ensemble is traversed in order to assign each individual data record from a set of data records to an identified leaf node in each tree. Predicted values are determined for the tree ensemble based on predictions provided by each leaf node to which each individual data record is assigned. Interesting sub-indices for decision rules from the set of decision rules are determined and, for each decision rule corresponding to the leaf nodes in the tree ensemble, the sub-indices are combined into interestingness index It. The decision rules are ranked corresponding to the leaf nodes in the tree ensemble according to the associated value of the interestingness index It and a subset of the decision rules corresponding to the leaf nodes in the tree ensemble are reported.

Abstract: The present disclosure relates to a system and a method for identifying a drunk passenger of a car hailing order. The system may perform the method to: obtain a plurality of samples from historical car hailing orders stored in a database; for each of the plurality of samples, using an application, extract a plurality of features including a passenger feature set, a driver feature set, and an order feature set, wherein the order feature set includes drunk-hotspot-relating features; and train a preliminary classification model based on the plurality of features and the plurality of samples to obtain a drunk model.

Abstract: A neural network machine translation method comprises: obtaining a to-be-translated source sentence; converting the source sentence into a vector sequence; determining candidate objects corresponding to the vector sequence according to a prefix tree which is pre-obtained and built based on a target sentence database, and determining a target sentence as a translation result according to the candidate objects.

Abstract: Systems and methods are provided for performing multi-objective optimizations with a relatively large number of objectives to which optimization is to be performed. The objectives of the optimization problem may be partitioned to two or more subsets (e.g., overlapping or non-overlapping subsets) of objectives, and partial optimization(s) may be performed using a subset or combination of subsets of the objectives. One or more of the partial optimizations may use one or more pareto-optimized chromosomes from a prior partial optimization. A final full optimization may be performed according to all of the objectives of the optimization problem and may use one or more chromosomes of any preceding partial optimization as a starting point for finding a final solution to the optimization problem. Any variety of processes may be employed to mitigate archive explosion that may be associated with relatively large objective sets.

Abstract: An online system distributes content items describing events to one or more users of the online system. The online system receives, an event from a third-party system, the event associated with one or more content items. The online system determines a vector representation of users based on a first neural network and a vector representation of an event based on a second neural network. The online system jointly trains the first neural network and second neural network based on labels describing user entity relationships. The online system determines a likelihood of attendance of an event by a user based on a distance between the vector representation of the user and the vector representation of the entity. The online system provides the content associated with the event to users of the online system based on the likelihood of attendance of the event by the users.