Abstract: A system including a confidence assessment module that implements a neural network to assess the likelihood that codes associated with a patient's encounter with a healthcare organization are accurate. The confidence assessment module may also be incrementally trained.

Abstract: A method for automatically generating a machine learning system which ascertains as a function of an input variable time series an output variable time series approximating an actual output variable time series, the machine learning system ascertaining a value of the output variable assigned to the predefinable point in time as a function of input and output variable values at the points in time, which are in a predefinable time interval, prior to a predefinable point in time, only a subset of the values of the input variable within the interval and of the values of the output variable being incorporated when ascertaining the output variable assigned to the predefinable point in time, the subset being selected so that it includes available input variable values and the output variable values assigned to the points in time within the interval, which are in a predefinable equidistant selection raster within the interval.

Abstract: A convolutional neural network (CNN) processing method and a CNN processing device are provided. The CNN processing method includes: acquiring an intensity type of a first module in a CNN model; in response of determining that the intensity type of the first module is a computation-intensity type, deploying the first module with an application specific integrated circuit (ASIC), where the first module occupies multiple arithmetic unit resources of the ASIC; acquiring the multiple arithmetic unit resources of the ASIC which are occupied by the first module; obtaining a first resource merging module by merging identical arithmetic unit resources among the multiple arithmetic unit resources of the ASIC which are occupied by the first module; and operating the first resource merging module by the ASIC.

Abstract: Provided are a data processing apparatus and method for merging and processing deterministic knowledge and non-deterministic knowledge. The data processing apparatus and method may efficiently process various real-time and large-scale data to convert the data into knowledge by merging and processing non-deterministic knowledge and also deterministic knowledge perceived by an expert. Thus, it is possible to adaptively operate in accordance with a dynamically changing application service environment by converting a conversion rule for converting collected data generated from an application service system into semantic data, a context awareness rule for perceiving context information from given information, and a user query for searching for knowledge information into knowledge and gradually augmenting the knowledge information in accordance with an application service environment.

Abstract: A system and method for determining an optimal solution to an optimization problem in a swarm of candidate solutions is provided. The invention comprises generating a population of random particles, where each particle is representative of a candidate solution. Further, a best particle is identified from the generated population of particles. The best particle is representative of an optimal solution. The population of particles is categorised into similar and non-similar particle groups by applying one or more multivariate measurement techniques, and similarity between the particles of the non-similar particle group with best particle is updated by applying an imitation technique. The generated population is updated with updated particles and a new best particle is evaluated from said population. Furthermore, final best particle is determined by further updating the population of particles until one or more target conditions are achieved.

Abstract: An approach is provided for completing a decision logic. For statements in a syntax tree of the decision logic and using a symbolic execution technique, path expression(s) that refer to respective input object(s) are identified. A statement in the decision logic is detected that modifies an attribute value of a path expression included in the path expression(s) and that refers to an input object included in the input object(s). A copy instruction is inserted as a new node in the syntax tree so that the attribute value of the path expression is a copy of the input object. Responsive to inserting the copy instruction, the path expression is prevented from modifying the input object.

Abstract: A training task optimization system includes a processor. The processor is configured to receive training environment information of a training task. The training environment information at least carries information corresponding to training samples in the training task. The processor is configured to calculate a memory distribution for the training task based on memory factors, the training samples and a neural network, and select a mini-batch size that is fit to the memory distribution. In response to the training environment information, the processor is configured to output the mini-batch size for execution of the training task.

Abstract: A facility providing systems and methods for discovering novel features to use in machine learning techniques. The facility receives, for a number of subjects, one or more sets of data representative of some output or condition of the subject over a period of time or capturing some physical aspect of the subject. The facility then extracts or computes values from the data and applies one or more feature generators to the extracted values. Based on the outputs of the feature generators, the facility identifies novel feature generators for use in at least one machine learning process and further mutates the novel feature generators, which can then be applied to the received data to identify additional novel feature generators.

Abstract: Methods and systems may be used for transfer learning of neural networks. According to one example, a method includes: grouping data objects of a first training set into a plurality of clusters; training a base model using a first cluster of the plurality of clusters, the base model being a neural network having a plurality of nodes; generalizing the base model to obtain a generalized base model, the generalizing the base model including setting a portion of the plurality of nodes to have random or predetermined weights; determining that the first cluster is, out of the plurality clusters, most similar to a second training set; and training the generalized base model using the second training set to obtain a trained model.

Abstract: A method of assessing chemical products includes: receiving input data including identification of a chemical substance at a processing device; evaluating a regulatory impact of the chemical substance based on at least one of global regulation data, regional regulation data and jurisdiction-specific regulation data, and outputting a regulatory impact assessment; evaluating potential hazards posed by the chemical substance based on available data related to characteristics of the chemical substance by comparing the characteristics to a plurality of criteria including environmental criteria, toxicity criteria related to effects on human health, and physical criteria related to hazards encountered during material transportation and handling, and outputting a chemical hazard assessment; and generating a chemical assessment report indicating potential impact due to use of the chemical substance, the chemical assessment report indicating chemical assessment results that include the regulatory impact assessment and

Abstract: Systems and methods for realigning streams of neuron outputs are provided. An example method may include generating, by a processing unit, neuron outputs including at least a first neuron output and a second neuron output, generating, by at least one further processing unit, further neuron outputs including at least a further first neuron output and a further second neuron output, receiving, by a synchronization module communicatively coupled to the processing unit and the further processing unit, the neuron outputs, wherein the neuron outputs and the further neuron outputs are received in an arbitrary order, and ordering, by the synchronization module, the first neuron output, the further first neuron output, the second neuron output and the further second neuron output according to a further order, the further order being different from the arbitrary order.

Abstract: Aspects for performing neural network operations are described herein. The aspects may include a first neural network processing module configured to process at least a portion of neural network data and an on-chip interconnection module communicatively connected to the first neural network processing module and one or more second neural network processing modules. The on-chip interconnection module may include a first layer interconnection module configured to communicate with an external storage device and one or more second layer interconnection modules respectively configured to communicate with the first neural network processing module and the one or more second neural network processing modules. Further, the first neural network processing module may include a neural network processor configured to perform one or more operations on the portion of the neural network data and a high-speed storage device configured to store results of the one or more operations.

Abstract: A mobile energy storage system and a method are provided for supplying power to entities at disparate locations. The system includes a set of vehicles. Each of the vehicles in the set includes a battery set having one or more batteries for storing power. Each of the vehicles in the set further includes a power connector having an end connected to the battery set and another end for connecting to a power transfer switch at the entities. The system also includes a central server for scheduling vehicles in the set to provide power to the entities responsive to energy charging requests issued by the entities.

Abstract: A correlithm object processing system that includes a trainer configured to send a node entry request to a node engine that triggers the node engine to generate an entry in a node table. The trainer is further configured to receive a source correlithm object and a target correlithm object in response to sending the node entry request. The trainer is further configured to send a real world input value and the source correlithm object to a sensor engine which triggers the sensor engine to generate an entry in a sensor table linking the real world input value and the source correlithm object. The trainer is further configured to send a real world output value and the target correlithm object to an actor engine which triggers the actor engine to generate an entry in an actor table linking the real world output value and the target correlithm object.

Abstract: A power tap includes a housing having a top surface, a bottom surface, and at least one side surface. A first male connector is integrated with a substantially planar portion of the bottom surface and arranged for substantially permanent electromechanical coupling to a first female connector that is integrated with a streetlight luminaire. A second female connector is integrated with a substantially planar portion of the top surface and arranged to receive a second male connector that is integrated with an electronic control device. Each male connector and each female connector is compliant with a roadway area lighting standard promoted by a standards body. The power tap also includes power conversion circuitry arranged to receive a higher voltage input signal and to produce at least one lower voltage output signal.

Abstract: A distributed machine learning framework implemented with heterogeneous data platforms reduces data copying and exploits memory/computation resources of the different data platforms. A configuration component includes information to set up the system. A persistency component manages storage of data and a model trained by machine learning. A proxy repository includes predefined proxies for communication between heterogeneous data platform nodes and execution of the machine learning procedure. A machine learning execution component comprises three layers. A bottom work node layer within the data platform performs computations of the machine learning procedure. A middle server node layer comprising one server node per data platform, communicates with the work nodes to coordinate jobs on that data platform. An upper layer comprises a central server node communicating with server nodes and coordinating jobs of the different platforms.

Abstract: In an example embodiment, a warm-start training solution is used to dramatically reduce the computational resources needed to train when retraining a generalized additive mixed-effect (GAME) model. The problem of retraining time is particularly applicable to GAME models, since these models take much longer to train as the data grows. In the past, the strategy to reduce computational resources during retraining was to use less training data, but this affects the model quality, especially for GAME models, which rely on fine-grained sub-models at, for example, member or item levels. The present solution addresses the computational resources issues without sacrificing GAME model accuracy.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for identifying a driver of a vehicle. Measurement values representing the movement of a vehicle are received from one or more sensors measuring features relating to the movement of the vehicle. Instantaneous dimensions for measuring driver identification are defined. For each dimension statistical features within a given time frame are calculated and a feature map is built, including the time frame and the statistical features. A set of driving features is extracted from the feature map. The set of extracted driving features is compared with previously extracted sets of driving features to create a set of similarity metrics between two drivers. A classification model is trained based on the similarity metrics and is used with the similarity metrics to determine whether data pertaining to a new trip segment should be associated with a known or unknown driver.

Abstract: A controllable resistive element and methods for controlling the resistance of the same include a resistor layer formed in contact with a shared read/write electrode and a read electrode, the resistor layer having a resistivity that depends on a concentration of charge carrier ions. An electrolyte layer is formed on the resistor layer. A reservoir layer is formed on the electrolyte layer and in contact with a write electrode.

Abstract: Disclosed is a method for training memristive learning systems (MLSs) using stochastic learning algorithms and the training system apparatus designed to implement the stochastic learning algorithms.