Abstract: A computerized efficient machine learning method for classification of data and new class discovery inputs labeled data and unlabeled data into a computer memory for a computerized machine tool to perform (a) initial supervised learning using the labeled data to generate a classifier, (b) semi-supervised learning using the labeled data, the classifier and the unlabeled data to generate an updated classifier and high confidence data, (c) active learning using the updated classifier and the unlabeled data to generate a data label request and receive new class labeled data to generate augmented labeled data, (d) new class discovery using the updated classifier and the data label request to generate data of potential new classes and receive labels for potential new class data to generate new class labeled data, and (e) supervised learning using the high confidence data, the labeled data and the augmented labeled data to generate an output classifier.

Abstract: An operational parameter setting supporting system for setting an operational parameter that specifies an operation of a component mounting apparatus is configured to include in an input unit into which a setting value of a component parameter and a setting value of the operational parameter that corresponds to the component parameter are input, a storage in which a correlation table in which the component parameter and the operational parameter that corresponds to the component parameter are associated with other is stored, and a rule table creation processor that creates a rule table from the setting value of the component parameter and the setting value of the operational parameter that are input into the input unit, and from the correlation table that is stored in the storage.

Abstract: A system for processing social media data includes a platform with a social media acquisition module configurable to collect a plurality of social media statements. The platform further includes an analysis engine configurable to analyze the plurality of social media statements according to a first sentiment model to generate first analytics data. The analysis engine is configurable to present the first analytics data to a client user, including a display of a sentiment value for each of the social media statements. The platform further includes a feedback queue configurable to receive feedback from the client user on at least a portion of the sentiment values; a model modification module configurable to modify the first sentiment model based on the feedback to result in a modified sentiment model; and a database configurable to store the modified sentiment model as a personalized sentiment model for the client user.

Abstract: The disclosed computer-implemented method for efficiently classifying data objects may include (1) receiving a data object to be classified according to a group of rules, where each rule includes one or more clauses, (2) creating, for each rule, a rule evaluation job that directs a rule evaluation processor to evaluate the data object according to the clauses within the rule, where the rule evaluation processor evaluates the clauses in increasing order of estimated processing time, (3) submitting the rule evaluation jobs created for the rules to rule evaluation queues for processing by the rule evaluation processor, where the rule evaluation jobs are submitted in decreasing order of estimated processing time, (4) receiving an evaluation result for each rule evaluation job, and (5) in response to receiving the evaluation results, classifying the data object according to the evaluation results. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The invention pertains to a method of manufacturing a population of parts produced with a manufacturing device, based on the analysis of at least one statistical indicator representative of a characteristic dimension of the parts, according to which: a) a sample comprising a number n of parts is collected from among the parts produced with the manufacturing device; b) the characteristic dimension of each part of the sample is measured, and a measured value of the statistical indicator is calculated for the sample; c) a mathematical expectation of the proportion of parts which are noncompliant with respect to a specification regarding the characteristic dimension is calculated, said calculation being performed on the basis of the measured value of the statistical indicator for the sample collected and of the number n of parts of the sample; d) the mathematical expectation of the proportion of parts that are noncompliant calculated is compared with a threshold value of proportion of noncompliant parts; e) the m

Abstract: Systems and methods are disclosed which provide a way to diagnose frailty using an upper extremity (and/or other body portions) frailty assessment. Within this method, several parameters can be calculated based on the kinematics (e.g., pure motion without including forces) and kinetics (e.g., analysis of forces and moments) of, for example, joint flexion/extension. An ordinal and/or continuous frailty score can be determined based on calculated markers of frailty, such as slowness, weakness, flexibility, and/or exhaustion, while performing a short-duration upper extremity task. Patients can be classified as non-frail, pre-frail, or frail.

Abstract: An actuator simulator card that is programmable with one or more actuator simulation models is provided. The actuator simulator card may include a first interface configured to communicate with a programmable computer, a second interface configured to communicate with an actuator controller, and a simulation module in communication with each of the first interface and the second interface. The simulation module may be configured to receive at least one actuator simulation model corresponding to at least one actuator from the first interface, receive excitation signals and command signals for operating the actuator from the second interface, and determine simulated feedback signals based on the excitation signals, the command signals, and the actuator simulation model.

Abstract: A method and a machine learning relationship determination system (MLRDS) for determining primary key-foreign key (PK-FK) relationships among data in tables of a target database through machine learning (ML) are provided. The MLRDS selects columns of the tables in the target database and identifies inclusion dependency (ID) pairs from the selected columns. The MLRDS receives training data and validation data from a source database, computes PK-FK features for the inclusion dependency pairs, the training data, and the validation data, and generates trained ML models and validated ML models using the PK-FK features. The MLRDS determines an optimum algorithm decision threshold for a selected machine learning classification algorithm (MLCA), using which the MLRDS determines a resultant on whether the inclusion dependency pair is a PK-FK pair or a non-PK-FK pair. The MLRDS performs majority voting on the resultant for multiple MLCAs to confirm the PK-FK relationships between the inclusion dependency pairs.

Abstract: A power distribution control system having a string of power assets comprising at least two different power assets selected from sources, stores and responsive loads is disclosed. The assets and associated local routers communicate with a central server and attempt to fulfil high level aims of the server by negotiating times and quantities of power transfer between themselves. Preferably a database stores parameters in relation to the power assets. Preferably a control system at the server anticipates future activity, such as future peaks in demand or supply, in the grid, and local power assets prepare in response. Preferably the power assets communicate between themselves on a peer-to-peer basis and collectively confirm to the server their ability to modify their collective behavior in response to an event in the grid.

Abstract: A method, system and computer program product for accelerating a deep neural network (DNN) in a field-programmable gate array (FPGA) are disclosed. The method includes receiving a DNN net file and weights, converting the received DNN net file to one or more source files, generating an executable FPGA bit file using the one or more source files, and downloading the executable FPGA bit file from the DNN conversion platform to the FPGA. Converting of the received DNN net file and the weights to the one or more source files can further include analyzing the DNN net file to identify a plurality of neural layers, decomposing one or more neural layers of the plurality of neural layers to one or more operation blocks, instantiating the one or more source files, based on the one or more operation blocks.

Abstract: A machining program management apparatus is used for managing an alteration made to a machining program stored in a plurality of machine tools. The machining program management apparatus acquires, at predetermined intervals set in advance, a piece of machining program updating information including a last update date and time of the machining program stored in each machine tool, identifies a machining program to which an alteration is made, on the basis of the piece of machining program updating information, creates a piece of information on the alteration, and updates a piece of machining program information corresponding to the machining program to which the alteration is made.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning using goals and observations. One of the methods includes receiving an observation characterizing a current state of the environment; receiving a goal characterizing a target state from a set of target states of the environment; processing the observation using an observation neural network to generate a numeric representation of the observation; processing the goal using a goal neural network to generate a numeric representation of the goal; combining the numeric representation of the observation and the numeric representation of the goal to generate a combined representation; processing the combined representation using an action score neural network to generate a respective score for each action in the predetermined set of actions; and selecting the action to be performed using the respective scores for the actions in the predetermined set of actions.

Abstract: The present invention is directed to a method for booting a system-on-chip (SoC) including the steps of directly executing a boot software from an on-chip magnetic random access memory (MRAM) residing on a same semiconductor as the SoC; storing an operating system (OS) software and an application software on an external MRAM; directly executing the operating system software from the external MRAM by the SoC without loading the operating system into a volatile memory; directly executing the application software from the external MRAM by the SoC, wherein the external MRAM is coupled to the SoC and is configured for permanently storing the operating system software and the application software.

Abstract: Described herein are systems and methods for determining how to automatically answer questions like “Where did Harry Potter go to school?” Carefully built knowledge graphs provide rich sources of facts. However, it still remains a challenge to answer factual questions in natural language due to the tremendous variety of ways a question can be raised. Presented herein are embodiments of systems and methods for human inspired simple question answering (HISQA), a deep-neural-network-based methodology for automatic question answering using a knowledge graph. Inspired by human's natural actions in this task, embodiments first find the correct entity via entity linking, and then seek a proper relation to answer the question—both achieved by deep gated recurrent networks and neural embedding mechanism.

Abstract: Technologies for light exposure analysis include a computer configured to collect light data of an environment and a remote computer communicatively coupled to the computer. The remote computer is configured to receive/retrieve health information for one or more users and analyze the health information to generate a health profile for each of the one or more users. Additionally, the remote computer is configured to determine whether any correlations exist between the health profiles and the light data. The remote computer is further configured to analyze the collected light data against one or more health profiles to determine a desired lighting condition for a user based at least in part on the correlations between the health profiles and the light data. Other embodiments are described and claimed.

Abstract: An apparatus and a method. The apparatus includes a first recurrent network in a first layer; a second recurrent network in a second layer connected to the first recurrent network; a distant input gate connected to the second recurrent network; a first highway gate connected to the distant input gate and the second recurrent network; a first elementwise product projection gate connected to the distant input gate, the highway gate, and the second recurrent network; a second highway gate connected to the first recurrent network and the second recurrent network; and a second elementwise product projection gate connected to the first recurrent network, the second highway gate, and the second recurrent network.

Abstract: A Cloud Based System of remotely controlling service and diagnostic devices using a computer based hardware system, computer software, an Artificial Intelligence means comprising computer software and algorithms, a data storage means, a Global Geo-Positioned Local Device management means, and a communications network. While the exemplary device was initially designed as a “Cloud Capable” Battery Device Command and Control Service Oriented System, it is understood that the disclosed Cloud Capable Battery Device Management System is not limited to the Battery Device Service Industry; rather, it may be uniquely suited to other non-battery industry Device Command and Control applications.

Abstract: Systems, methods, and apparatuses are provided for permeability prediction. The method acquires data associated with one or more geological formations, calculates, using processing circuitry and a trained Hidden Markov model, log-likelihood values to group the data into a plurality of clusters, and trains an artificial neural network for each of the plurality of clusters when the mode of operation is training mode. Further, the method acquires one or more formation properties corresponding to a geological formation, determines using the trained Hidden Markov model, a log-likelihood score associated with the one or more formation properties, identifies a cluster associated with the one or more formation properties as a function of the log-likelihood score, and predicts a permeability based at least in part on the one or more formation properties and a trained artificial neural network associated with the identified cluster when the mode of operation is forecasting mode.

Abstract: Technologies for pre-memory phase initialization include a computing device having a processor with a cache memory. The computing device may determine whether a temporary memory different from the cache memory of the processor is present for temporary memory access prior to initialization of a main memory of the computing device. In response to determining that temporary memory is present, a portion of the basic input/output instructions may be copied from a non-volatile memory of the computing device to the temporary memory for execution prior to initialization of the main memory. The computing device may also initialize a portion of the cache memory of the processor as Cache as RAM for temporary memory access prior to initialization of the main memory in response to determining that temporary memory is not present. After initialization, the main memory may be configured for subsequent memory access. Other embodiments are described and claimed.

Abstract: A system and method is described herein for performing at least one industrial process at each facility of a plurality of facilities based on an industrial process standard generated by reducing functional, and trend line outlier bias in data of one or more process parameters as measured by one or more sensors. Outliers are removed from the data set through an objective method. Bias is determined based on absolute, relative error, or both. Error values are computed from the data, model coefficients, or trend line estimates. Outlier data records are removed when the error values are greater than or equal to one or more criteria.