Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a control policy for a vehicles or other robot through the performance of a reinforcement learning simulation of the robot.

Abstract: A method for performing program analysis includes receiving programs of a first platform that have been assigned a first label and programs of the first platform that have been assigned a second label. Each of the programs of the first platform is expressed as platform-independent logical features. A discriminatory model or classifier is trained, using machine learning, based on the expression of the programs of the first platform as platform-independent logical features, to distinguish between programs of the first label and programs of the second label. An unlabeled program of a second platform is received and is expressed as platform-independent logical features. The trained discriminatory model or classifier is used to determine if the unlabeled program warrants the first label or the second label, based on the expression of the unlabeled program as platform-independent logical features.

Abstract: Approaches are provided for answering an inquiry of a cognitive distributed network. An approach includes receiving the inquiry at the cognitive distributed network. The approach further includes determining a classification for the inquiry based on natural language of the inquiry. The approach further includes classifying the inquiry as a single question class. The approach further includes determining, by at least one computing device, a type of introspection to be used by the cognitive distributed network on the inquiry. The approach further includes generating an answer to the inquiry based on the determined type of introspection.

Abstract: A method for performing program analysis includes receiving programs of a first platform that have been assigned a first label and programs of the first platform that have been assigned a second label. Each of the programs of the first platform is expressed as platform-independent logical features. A discriminatory model or classifier is trained, using machine learning, based on the expression of the programs of the first platform as platform-independent logical features, to distinguish between programs of the first label and programs of the second label. An unlabeled program of a second platform is received and is expressed as platform-independent logical features. The trained discriminatory model or classifier is used to determine if the unlabeled program warrants the first label or the second label, based on the expression of the unlabeled program as platform-independent logical features.

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for an adaptive oracle-trained learning framework for automatically building and maintaining models that are developed using machine learning algorithms. In embodiments, the framework leverages at least one oracle (e.g., a crowd) for automatic generation of high-quality training data to use in deriving a model. Once a model is trained, the framework monitors the performance of the model and, in embodiments, leverages active learning and the oracle to generate feedback about the changing data for modifying training data sets while maintaining data quality to enable incremental adaptation of the model.

Abstract: The machine learning apparatus includes: a state data observing unit which observes state data of the laser apparatus, including data output from a reflected light detecting unit for measuring a reflected light amount; an operation result acquiring unit which acquires a success/failure result indicating whether the machining has been started successfully by the laser beam output from a laser oscillator; a learning unit which learns light output command data by associating the light output command data with the state data of the laser apparatus and the success/failure result of the machining start; and a decision making unit which determines the light output command data by referring to the light output command data learned by the learning unit.

Abstract: The present invention discloses a micro-grid distributed energy resource bidding method based on artificial immunity including the following steps: processing the collected information by a bidding unit agent to form artificial immune antigen of quotation environmental; performing solving based on artificial immune algorithm to obtain antibody meeting the interest of a distributed energy resource; and decoding the antibody to obtain a bidding scheme of the distributed energy resource. The present invention utilizes artificial immune intelligent algorithm with strong ability of information processing and self-adaption, thus solving the problem of uncontrollable bidding under complicated environment. Uncertainty problem resulted by the intermittent power supply is overcomed by the capability of self-adaption and defect tolerance of artificial immunity during bidding process. In addition, the coordination of entire micro-grid MAS is improves by coordinated evolution of artificial immunity.

Abstract: An artificial intelligence system for predicting hours of operation for merchants. The system may include a processor, a database, and a storage medium storing instructions. When executed, the instructions configure the processor to: receive a request for hours of operation for the merchants; obtain, from the database, a set of credit card authorizations associated with the merchants; generate input model features based on the set of credit card authorizations; obtain ground-truth data associated with the merchants; generate a training dataset based on the ground truth data and the set of credit card authorizations; determine an hours-of-operation model based on the training data set; calculate the total prediction of hours of operation using the hours-of-operation model.

Abstract: It is disclosed a method comprising obtaining a target spectrum, obtaining a set of non-target spectra, the set of non-target spectra comprising one or more non-target spectra, summing the target spectrum and the set of non-target spectra to obtain a mixture spectrum, and training an artificial neural network by using the mixture spectrum as input of the neural network and by using a spectrum which is based on the target spectrum as desired output of the artificial neural network.

Abstract: A system is disclosed for anticipating and rendering unnecessary human action in a smart home or other connected environment. Sensor data and data from smart appliances may be used to determine and predict human user behavior to a degree that allows an automated system to act upon the appliances or other devices even before the human user is able to act, allowing the human user's past actions to program the automated system without conscious effort by the human user to define the conditions under which an action should be taken.

Abstract: Technologies are generally described for methods and systems in a machine learning environment. In some examples, a method may include retrieving training data from a memory. The training data may include training inputs and training labels. The methods may further include determining a set of datasets based on the training inputs. The methods may further include determining a set of out of sample errors based on the training inputs and based on test data. Each out of sample error may correspond to a respective dataset in the set of datasets. The methods may further include generating alternative distribution data based on the set of out of sample errors. The alternative distribution data may be used to determine weights to be applied to the training data.

Abstract: A residential home characteristics inferring method and system that receives information about energy usage by an energy user, determines using a processor and the received information about energy usage average daily usage during a heating season and average daily usage during a shoulder season, and identifies the fuel type used for heating by the energy user using the determined average daily usage during the heating season and the determined average daily usage during the shoulder season.

Abstract: In some aspects, a method may include initializing a first array and a second array with a random voltage value, passing a forward pass by pulsing an input voltage value from an input of the first array and an input of the second array, and reading output voltage values at an output of the first array and an output of the second array. The method may further include passing a backward pass into the inputs of both of the first and second arrays, and reading voltage values at the inputs of the first and second arrays. The method may further include updating, with the first array, a first matrix update on the first array, updating, with the second array, a first matrix update on the second, and updating, with the second array, a second matrix update on the second array.

Abstract: In some aspects, a method may include initializing a first array and a second array with a random voltage value, passing a forward pass by pulsing an input voltage value from an input of the first array and an input of the second array, and reading output voltage values at an output of the first array and an output of the second array. The method may further include passing a backward pass into the inputs of both of the first and second arrays, and reading voltage values at the inputs of the first and second arrays. The method may further include updating, with the first array, a first matrix update on the first array, updating, with the second array, a first matrix update on the second, and updating, with the second array, a second matrix update on the second array.

Abstract: According to an aspect, a heterogeneous graph in a data store is accessed. The heterogeneous graph includes a plurality of nodes having a plurality of node types. The nodes are connected by edges having a plurality of relation types. One or more intermediary graphs are created based on the heterogeneous graph. The intermediary graphs include intermediary nodes that are the relation types of the edges of the heterogeneous graph and include intermediary links between the intermediary nodes based on shared instances of the nodes between relation types in the heterogeneous graph. The intermediary graphs are traversed to find sets of relations based on intermediary links according to a template. An inference rule is extracted from the heterogeneous graph based on finding sets of relations in the intermediary graphs. The inference rule defines an inferred relation type between at least two of the nodes of the heterogeneous graph.

Abstract: A decision tree multi-processor system includes a plurality of decision tree processors that access a common feature vector and execute one or more decision trees with respect to the common feature vector. A related method includes providing a common feature vector to a plurality of decision tree processors implemented within an on-chip decision tree scoring system, and executing, by the plurality of decision tree processors, a plurality off decision trees, by reference to the common feature vector. A related decision tree-walking system includes feature storage that stores a common feature vector and a plurality of decision tree processors that access the common feature vector from the feature storage and execute a plurality of decision trees by comparing threshold values of the decision trees to feature values within the common feature vector.

Abstract: Technologies are described herein for active machine learning. An active machine learning method can include initiating active machine learning through an active machine learning system configured to train an auxiliary machine learning model to produce at least one new labeled observation, refining a capacity of a target machine learning model based on the active machine learning, and retraining the auxiliary machine learning model with the at least one new labeled observation subsequent to refining the capacity of the target machine learning model. Additionally, the target machine learning model is a limited-capacity machine learning model according to the description provided herein.

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for providing confidence rankings based on temporal semantics. Responsive to receiving an input question, a set of candidate answers is identified from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain. A confidence score is associated with each of the candidate answers and each confidence score associated with each candidate answer is refined based on a set of temporal characteristics identified in the input question. A set of temporally refined candidate answers is then provided to the user.