Abstract: Individual identification and tracking are provided via combined video and LiDAR systems. In various embodiments, a virtual plane may be generated. A video frame including the virtual plane is recorded via a first imaging modality. One or more objects are detected in the video frame when the one or more objects enters the virtual plane. An identifier is assigned to each of the one or more objects. One or more three-dimensional shapes are detected at the second imaging modality when the one or more three-dimensional shapes enters the virtual plane. For each of the one or more objects, a corresponding shape of the one or more three-dimensional shapes is determined. Each identifier is assigned to the respective corresponding shape of the one or more three-dimensional shapes. After assigning each identifier, a plurality of positional data is recorded for each of the one or more three-dimensional shapes.

Abstract: A system of convolutional neural networks (CNNs) that synthesize middle non-existing frames from pairs of input frames includes a coarse CNN that receives a pair of images acquired at consecutive points of time, a registration module, a refinement CNN, an adder, and a motion-compensated frame interpolation (MC-FI) module. The coarse CNN outputs from the pair of images a previous feature map, a next feature map, a coarse interpolated motion vector field (IMVF) and an occlusion map, the registration module uses the coarse IMVF to warp the previous and next feature maps to be aligned with pixel locations of the IMVF frame, and outputs registered previous and next feature maps, the refinement CNN uses the registered previous and next feature maps to correct the coarse IMVF, and the adder sums the coarse IMVF with the correction and outputs a final IMVF.

Abstract: System and method for explaining driving behavior actions of autonomous vehicles. Combined sensor information collected at a scene understanding module is used to produce a state representation. The state representation includes predetermined types of image representations that, along with a state prediction, are used by a decision making module for determining one or more weighted behavior policies. A driving behavior action is selected and performed based on the determined one or more behavior policies. Information is then provided indicating why the selected driving behavior action was chosen in a particular driving context of the autonomous vehicle. In one or more embodiments, a user interface is configured to depict the predetermined types of image representations corresponding with the driving behavior action performed via the autonomous vehicle.

Abstract: The systems and methods described herein may generate multi-modal embeddings with sub-symbolic features and symbolic features. The sub-symbolic embeddings may be generated with computer vision processing. The symbolic features may include mathematical representations of image content, which are enriched with information from background knowledge sources. The system may aggregate the sub-symbolic and symbolic features using aggregation techniques such as concatenation, averaging, summing, and/or maxing. The multi-modal embeddings may be included in a multi-modal embedding model and trained via supervised learning. Once the multi-modal embeddings are trained, the system may generate inferences based on linear algebra operations involving the multi-modal embeddings that are relevant to an inference response to the natural language question and input image.

Abstract: The embodiments of the present disclosure provide a method, system and server for utilizing barcode. The method includes: a server receiving a decoding request sent by a user terminal, the decoding request comprising a barcode image associated with a smart device, or a code value of a barcode presented in the barcode image associated with the smart device; the barcode server acquiring state information associated with the code value of the barcode; returning operation information associated with the user if the state information is a second state information; or sending configuration address information to the user terminal for configuring the smart device, and changing the state information associated with the code value, if the state information is a first state information.

Abstract: A package for an integrated circuit is marked with an encoded image (e.g., a two-dimensional barcode). The encoded image is scanned by a scanner to obtain manufacturing parameters. In one approach, a method includes: fabricating, in a manufacturing facility, a physical product using a manufacturing process, where the physical product is fabricated according to specifications, and the manufacturing process includes manufacturing steps performed in the manufacturing facility; marking the physical product with an encoded image, where the encoded image encodes parameters that include the specifications; and transporting the physical product to a storage facility, where the storage facility includes a scanner configured to scan the encoded image to obtain the parameters.

Abstract: Various embodiments are generally directed to techniques to provide an orientationless transaction card. Embodiments include a transaction card having a substrate comprising one or more laminated layers and a chip comprising processing circuitry, and memory, the chip embedded within the substrate. The transaction card may also include a first contact pad coupled with the chip, the first contact pad embedded on a first side of the substrate at a first location and a second contact pad embedded on the first side of the substrate at a second location. Further, the transaction card includes an antenna embedded within the substrate, the antenna to couple the chip with the second contact pad.

Abstract: The invention relates to a smart label and a system that allows the handling of the label. The smart label system is formed by a) a smart label having a hidden message that becomes visible in the event of an attempt to remove the label from an item to which it is affixed; b) a chip with an antenna embedded with the label; c) an electronic mobile device for communicating with the chip; and d) an algorithm on the chip and on the electronic mobile device for unique encoded reading (padlock) encryption.

Abstract: Methods and apparatus for hierarchical reinforcement learning (RL) algorithm for network function virtualization (NFV) server power management. A first RL model at a first layer is trained by adjusting a frequency of the core of processor while performing a workload to obtain a first trained RL model. The trained RL model is operated in an inference mode while training a second RL model at a second level in the RL hierarchy by adjusting a frequency of the core and a frequency of processor circuitry external to the core to obtain a second trained RL model. Training may be performed online or offline. The first and second RL models are operated in inference modes during online operations to adjust the frequency of the core and the frequency of the circuitry external to the core while executing software on the plurality of cores of to perform a workload, such as an NFV workload.

Abstract: The embodiments described herein aim to improve environmental sensing by providing a computationally efficient and accurate means for fusing sensor data and using this fused data to control sensors to focus on areas that would most reduce the uncertainty in the sensing system. In this way, the system can direct sensors to focus on the most important areas and features within the environment in order to provide the most effective sensor data (e.g. for use by a control system). The methods described herein make use of multi-agent sensor-action fusion. The methods are multi-agent in that a set of machine learning agents are trained in order to control the sensors to focus on the most important features and regions. The embodiments implement sensor-action fusion in that sensor fusion is performed in order to obtain a combined view of the environment and this combined view is utilised to determine the most appropriate actions.

Abstract: This application relates to classifying information using a fully-connected layer of a convolutional neural network. A method for classifying information using a fully-connected layer of a convolutional neural network includes calculating a first partial output for a first block of elements by performing a dot product operation using a first row of elements of the first block of elements and a first weight block, where the first row of elements of the first block of elements corresponds to a first batch of elements. The method further includes generating a first output element using the first partial output for the first block of elements and at least one other partial output corresponding to the first batch of elements.

Abstract: This application relates to performing fully-connected inferences using a convolutional neural network. A method includes receiving a two-dimensional input matrix that includes a plurality of elements. The method further includes identifying a two-dimensional weight matrix corresponding to the two-dimensional input matrix, where the two-dimensional weight matrix includes a plurality of weight values. The method further includes transposing a first column of the two-dimensional weight matrix and storing the transposed first column of the two-dimensional weight matrix in a first register having a first length corresponding to the transposed first column. The method further includes generating a first output element by performing a first dot product operation using a first row of the two-dimensional input matrix and the transposed first column. Finally, the method includes storing the first output element in a first row of a two-dimensional output matrix.

Abstract: A method and a system are provided for training a machine-learning (ML) system to function as a chatbot. According to one embodiment, a method for training and ML system includes providing to the machine-learning system: in a first iteration, a first input-output pair that includes a first input and a first output; and, in a second iteration, a second input-output pair that includes a second input and a second output, where the second input includes the first input-output pair and the second output is different from the first output, so that a context for the second input-output pair is stored in the memory of the ML system.

Abstract: Methods and systems for generating a multi-model ensemble of global climate simulation data from a plurality of global climate simulation models (GCMs), to be used in training a neural network (NN)-based climate forecasting model, are disclosed. The methods and systems perform steps of computing a GCM validation measure for each GCM; selecting a validated subset of the GCMs, by comparing each computed GCM validation measure to a validation threshold determined based on observational historical climate data; computing a forecast skill score for each validated GCM, based on a first forecast function; selecting a validated and skillful subset of GCMs; generating one or more candidate ensembles by combining simulation data from at least two validated and skillful GCMs; computing an ensemble forecast skill score for each candidate ensemble, based on a second forecast function; and selecting a best-scored candidate ensemble.

Abstract: The present invention relates to a parameter training method for a convolutional neural network, CNN, for classifying data, the method comprising the implementation by data processing means (11c) of servers (1a, 1b, 1c) of steps of: (a1) Obtaining parameters of a set of at least one first CNN; (a2) For a first CNN of said set: Training, based on a database of already-classified public training data, parameters of a final representation block (B) of a second CNN corresponding to the first selected CNN to which said representation block (B) has been added; Retraining, based on a database of already-classified confidential training data of a secondary server (1a, 1b), parameters of the second CNN; Transmitting to the main server (1c) parameters of a third CNN corresponding to the second CNN without a final representation block (B); (a3) Replacing a first CNN of said set of first CNNs with the third CNN; (a4) Aggregating said set of at least one first CNN into a fourth CNN.

Abstract: A system for using hash keys to preserve privacy across multiple tasks is disclosed. The system may provide training batch(es) of input observations each having a customer request and stored task to an encoder, and assign a hash key(s) to each of the stored tasks. The system may provide a new batch of input observations with a new customer request and new task to the encoder. The encoder may generate a new hash key assigned to the new customer request and determine whether any existing hash key corresponds with the new hash key. If so, the system may associate the new batch of input observations with the corresponding hash key and update the corresponding hash key such that it is also configured to provide access to the new batch of input observations. If not, the system may generate a new stored task and assign the new hash key to it.

Abstract: Methods and systems are provided for generating a multi-label classification system. The multi-label classification system can use a multi-label classification neural network system to identify one or more labels for an image. The multi-label classification system can explicitly take into account the relationship between classes in identifying labels. A relevance sub-network of the multi-label classification neural network system can capture relevance information between the classes. Such a relevance sub-network can decouple independence between classes to focus learning on relevance between the classes.

Abstract: Systems and methods are provided for implementing hardware optimization for a hardware accelerator. The hardware accelerator emulates a neural network. Training of the neural network integrates a regularized pruning technique to systematically reduce a number of weights. A crossbar array included in hardware accelerator can be programmed to calculate node values of the pruned neural network to selectively reduce the number of weight column lines in the crossbar array. During deployment, the hardware accelerator can be programmed to power off periphery circuit elements that correspond to a pruned weight column line to optimize the hardware accelerator for power. Alternatively, before deployment, the hardware accelerator can be optimized for area by including a finite number of weight column line. Then, regularized pruning of the neural network selectively reduces the number of weights for consistency with the finite number of weight columns lines in the hardware accelerator.

Abstract: Provided is a neural network device including at least one processor configured to implement an arithmetic circuit configured to generate third data including a plurality of pixels based on a neural network configured to perform an arithmetic operation on first data and second data, and a compressor configured to generate compressed data by compressing the third data, wherein the compressor is further configured to generate, as the compressed data, bitmap data comprising location information about a non-zero pixel having a non-zero data value among the plurality of pixels based on a quad-tree structure.

Abstract: A machine learning system, including at least one temporal filter. An input variable, encompassing a chronological sequence of images, is processed with the aid of the machine learning system, using the filter. The machine learning system is configured to use the filter on a sequence of pixels, which are all situated at identical coordinates of the images, or at identical coordinates of intermediate results. Filter coefficients of the filter are quantized. A method, a computer program, and a device for creating the machine learning system are also described.

Abstract: A system includes first, second and third input data sets. The first input data set includes demographic information characterizing a patient. The second and third input data sets characterize a healthcare treatment history of the patient. A neural network includes first, second and third neural subnetworks. The first neural subnetwork is configured to process the first input data set to produce a first output data set. The second neural subnetwork is configured to process the second input data set to produce a second output data set. The third neural subnetwork is configured to process the third input data set to produce a third output data set. An autoencoder layer has an input layer comprising the first, second and third output data sets and is configured to process the first, second and third output data sets to produce a secondary output data set.

Abstract: A circuit for multiplying a number N of first operands each by a corresponding second operand, and for adding the products of the multiplications, with N?2; the circuit comprising: N input conductors; N programmable conductance circuits connected each between one of the input conductors and at least one output conductor; each programmable conductance circuit being arranged to be programmable at a value depending in a known manner from one of the first operands; each input conductor being arranged to receive from an input circuit an input train of voltage spikes having a spike rate that derives in a known manner from one of the second operands; and at least one output circuit arranged to generate an output train of voltage spikes having a spike rate that derives in a known manner from a sum over time of the spikes received on the at least one output conductor.

Abstract: This application relates to computing circuitry (200), in particular for analogue computing circuitry suitable for neuromorphic computing. The circuitry (200) has a plurality of memory cells (201), each memory cell having an input electrode (201) for receiving a cell input signal and an output (203P, 203N) for outputting a cell output signal (IP, IN), with first and second paths connecting the input electrode to the output. The cell output signal thus depends on a differential current between the first and second paths due to the cell input signal. Each memory cell also comprises at least one programmable-resistance memory element (204) in each of the first and second paths and is controllable, by selective programming of the programmable-resistance memory elements, to store a data digit that can take any of at least three different values.

Abstract: In one embodiment, a method of training dynamic models for autonomous driving vehicles includes the operations of receiving a first set of training data from a training data source, the first set of training data representing driving statistics for a first set of features; training a dynamic model based on the first set of training data for the first set of features; determining a second set of features as a subset of the first set of features based on evaluating the dynamic model, each of the second set of features representing a feature whose performance score is below a predetermined threshold. The method further includes the following operations for each of the second set of features: retrieving a second set of training data associated with the corresponding feature of the second set of features, and retraining the dynamic model using the second set of training data.

Abstract: Fusion of neural networks is performed by obtaining a first neural network and a second neural network. The first and the second neural networks are the result of a parent neural network subjected to different training. A similarity score is calculated of a first component of the first neural network and a corresponding second component of the second neural network. An interpolation weight is determined for the first and the second components by using the similarity score. A neural network parameter of the first component is updated based on the interpolation weight and a corresponding neural network parameter of the second component to obtain a fused neural network.

Abstract: Described herein are embodiments for a deep level-wise extreme multi-label learning and classification (XMLC) framework to facilitate the semantic indexing of literatures. In one or more embodiments, the Deep Level-wise XMLC framework comprises two sequential modules, a deep level-wise multi-label learning module and a hierarchical pointer generation module. In one or more embodiments, the first module decomposes terms of domain ontology into multiple levels and builds a special convolutional neural network for each level with category-dependent dynamic max-pooling and macro F-measure based weights tuning. In one or more embodiments, the second module merges the level-wise outputs into a final summarized semantic indexing. The effectiveness of Deep Level-wise XMLC framework embodiments is demonstrated by comparing it with several state-of-the-art methods of automatic labeling on various datasets.

Abstract: A model training method and apparatus is disclosed, where the model training method acquires a recognition result of a teacher model and a recognition result of a student model for an input sequence and trains the student model such that the recognition result of the teacher model and the recognition result of the student model are not distinguished from each other.

Abstract: A neural network system includes a processor and a memory. The processor is configured to perform learning including multiple learning iterations on multiple layers, to determine at least one layer in which the learning is interrupted among the multiple layers. The determination of the at least one layer in which the learning is interrupted is based on a result of comparing for each of the multiple layers a distribution of first weight values resulting from a first learning iteration with a distribution of second weight values resulting from a second learning iteration. The processor is also configured to perform a third learning iteration in layers except the at least one layer for which interruption of the learning has been determined.

Abstract: Systems, methods, and computer-readable media are described for performing weakly supervised semantic segmentation of input images that utilizes self-guidance on attention maps during training to cause a guided attention inference network (GAIN) to focus attention on an object in an input image in a holistic manner rather than only on the most discriminative parts of the image. The self-guidance is provided jointly by a classification loss function and an attention mining loss function. Extra supervision can also be provided by using a select number pixel-level labeled input images to enhance the semantic segmentation capabilities of the GAIN.

Abstract: Techniques are disclosed for training a machine learning model to perform actions within an environment. In one example, an input device receives a declarative statement. A computation engine selects, based on the declarative statement, a template that includes a template action performable within the environment. The computation engine generates, based on the template, synthetic training episodes. The computation engine further generates experiential training episodes, each experiential training episode collected by a machine learning model from past actions performed by the machine learning model. Each synthetic training episode and experiential training episode comprises an action and a reward. A machine learning system trains, with the synthetic training episodes and the experiential training episodes, the machine learning model to perform the actions within the environment.

Abstract: Systems and methods for generating an interference prediction for a target well are disclosed herein. A computing system generates a plurality of interference metrics for a plurality of interference events. For each well, the computing system generates a graph based representation of the well and its neighboring wells. The computing system generates a predictive model using a graph-based model by generating a training data set and learning, by the graph-based model, an interference value for each interference event based on the training data set. The computing system receives, from a client device, a request to generate an interference prediction for a target well. The computing system generates, via the predictive model, an interference metric based on the one or more metrics associated with the target well.

Abstract: A method includes collecting a first dataset of input-output data for a first building, training a deep learning model using the first dataset, initializing parameters of a target model for a second building using parameters of the deep learning model, collecting a second dataset of input-output data for a second building, training the target model for the second building using the initialized parameters of the target model and the second dataset, and controlling building equipment using the target model. Controlling the building equipment affects a variable state or condition of the building.

Abstract: A computer system and method for machine inductive learning on a graph is provided. In the inductive learning computational approach, an iterative approach is used for sampling a set of seed nodes and then considering their k-degree (hop) neighbors for aggregation and propagation. The approach is adapted to enhance privacy of edge weights by adding noise during a forward pass and a backward pass step of an inductive learning computational approach. Accordingly, it becomes more technically difficult for a malicious user to attempt to reverse engineer the edge weight information. Applicants were able to experimentally validate that acceptable privacy costs could be achieved in various embodiments described herein.

Abstract: A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

Abstract: A computing device for training an artificial neural network model includes: a model analyzer configured to receive a first artificial neural network model and split the first artificial neural network model into a plurality of layers; a training logic configured to calculate first sensitivity data varying as the first artificial neural network model is pruned, calculate a target sensitivity corresponding to a target pruning rate based on the first sensitivity data, calculate second sensitivity data varying as each of the plurality of layers is pruned, and output, based on the second sensitivity data, an optimal pruning rate of each of the plurality of layers, the optimal pruning rate corresponding to the target pruning rate; and a model updater configured to prune the first artificial neural network model based on the optimal pruning rate to obtain a second artificial neural network model, and output the second artificial neural network model.

Abstract: A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

Abstract: A method includes providing a computer system, the computer system including at least a processor and a memory, the memory including at least an operating system, executing a process in the memory, the process including providing a recurrent circuit model, and converting the recurrent circuit model into a recurrent neural network that can be fit with gradient descent.

Abstract: According to an aspect of an embodiment, operations may include selecting, from a training dataset, a first data point as a seed data point. The operations may further include generating a population of data points by application of a genetic model on the seed data point. The population of data points may include the seed data point and a plurality of transformed data points of the seed data point. The operations may further include determining a best-fit data point in the generated population of data points based on application of a fitness function on the generated population of data points. The operations may further include executing a training operation on the DNN based on the determined best-fit data point. The operations may further include obtaining a trained DNN for the first data point based on the training operation on the DNN based on the determined best-fit data point.

Abstract: A system for an artificial intelligence alimentary professional support network for vibrant constitutional guidance includes at least a server. The system includes a diagnostic engine designed and configured to receive a biological extraction from a user and generate a diagnostic output based on the biological extraction. The system includes an advisor module designed and configured to receive a request for an advisory input, generate an advisory output using the request for an advisory input and the diagnostic output, and transmit the advisory output. The system includes an alimentary input module designed and configured to receive the advisory output, select an informed advisor alimentary professional client device as a function of the request for an advisory input, and transmit the at least an advisory output to the informed advisor alimentary professional client device.

Abstract: A system is disclosed. The system has a weighted comparison module, comprising computer-executable code stored in non-volatile memory, a processor, and a user device. The weighted comparison module, processor, and user device are configured to receive data of at least one decision-making goal parameter via the user device, determine a plurality of decision-making factors, determine a weight for each of the plurality of decision-making factors, continuously receive data affecting decision-making, determine at least one relationship between an increase or a decrease of a value of the at least one decision-making goal parameter and the plurality of decision-making factors based on iteratively modifying the weights for each of the plurality of decision-making factors and analyzing the continuously-received data, and optimize the value of the at least one decision-making goal parameter by iteratively modifying the weights for each of the plurality of decision-making factors based on the at least one relationship.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for generating a recommendation for a composite computer application program from unstructured text. Unstructured text specifying functional requirements for a composite computer application program is received. The unstructured text is processed to generate topic metadata. The topics represent actions to be performed by the composite computer application program. Based on the generated topic metadata, a micro service is determined for performing each action. A recommendation for a sequence of microservices pertinent to the specified functional requirements is also determined, wherein each microservice is deployed in a separate container. Rules for synchronizing operations between the individual containers are specified. A recommendation for a deployable composite computer application program comprising the collection of individual containers and the specified rules is generated.

Abstract: An apparatus links an entity in a first knowledge-graph with a word in a text. The apparatus, based on a number of first-edges coupled to each of first-nodes serving as a transition-source and a number of second-edges coupled to each of second-nodes serving as a transition-destination in the first knowledge-graph, identifies a third-edge to be deleted from edges coupled to a third-node among the second-nodes which has a preset input-order indicating a number of edges that transition to the third-node, and generates a second knowledge-graph by deleting the third-edge from the first knowledge-graph. The apparatus couples first and second nodes which have been coupled to each other by the third-edge in the first knowledge-graph, via a fourth-node to which the first and second nodes are coupled by edges in the second knowledge-graph, and provides the word in the text and the entity linked with the word to a user.

Abstract: One embodiment provides a method, including: mining a plurality of deep-learning models from a plurality of input sources; extracting information from each of the deep-learning models, by parsing at least one of (i) code corresponding to the deep-learning model and (ii) text corresponding to the deep-learning model; identifying, for each of the deep-learning models, operators that perform operations within the deep-learning model; producing, for each of the deep-learning models and from (i) the extracted information and (ii) the identified operators, an ontology comprising terms and features of the deep-learning model, wherein the producing comprises populating a pre-defined ontology format with features of each deep-learning model; and generating a deep-learning model catalog comprising the plurality of deep-learning models, wherein the catalog comprises, for each of the deep-learning models, the ontology corresponding to the deep-learning model.

Abstract: A computer-implemented method of handling super large quantities of incompatible types of data sets and records in a common environment is provided in which the method applies real-time analytics and multi-view information objects to these data sets and records according to a predetermined analytics model. The method dynamically tracks the combined results of the real-time analytics across multiple contexts and problem domains and, in parallel, updates the analytics model continuously and accurately.

Abstract: Embodiments of the invention are directed to intelligently and dynamically controlling both changes made within EUC applications and the control rules associated with such changes. A similarity index is calculated/assigned for each data entry field (i.e., cell/intersection) and the controls implemented when a changes to data in the entry fields occurs is based on the similarity index. In other embodiments, a change to data entry fields dynamically prompts analysis of the change based on historical approval and/or denial patterns specific to the EUC application, the data entry field(s) and/or the user of the application. In response to the analysis the control rules may be dynamically updated, and applied to the current change. In other embodiments, inputs, such as reviewer's comments, are the basis for determining a need to update existing controls or add new controls associated with data entry field(s) and the conditions associated therewith are determined and applied.

Abstract: A computer-implemented method can receive a new plan deviation alert having a deviation level that quantifies a mismatch between expected supply chain parameters specified by a supply chain plan and observed supply chain parameters. Responsive to the new plan deviation alert, the method can perform a rule-based search to find a plurality of potential remediation solutions to correct the mismatch. The method can simulate implementation of the potential remediation solutions and evaluate expended resources associated with them. Based on the evaluated expended resources, the method can generate a ranked list of candidate remediation solutions and display the ranked list of candidate remediation solutions in a user interface. The method can receive a selected remediation solution from the ranked list of candidate remediation solutions for initiation. Machine learning can be used on an expert user's selection to adapt to the expert's preferences and provide more relevant remediation solutions.

Abstract: A rule presentation method by a computer, includes specifying a plurality of rules that specify one of examples according to the number of positive examples and the number of negative examples for one or more combinations of attributes, based on training data; acquiring first data that has a combination of attributes different from the combination of attributes included in the training data and is not associated with a label that designates the positive example or the negative example; selecting a rule related to the combination of attributes from among the plurality of specified rules; generating second data in which a label different from examples specified by the selected rule is associated with the first data; specifying the number of samples of the first data in which the label of the positive example or the negative example specified by the selected rule changes; and determining an order of rules.

Abstract: A unified access layer (UAL) and scalable query engine receive queries from various interfaces and executes the queries with respect to non-heterogeneous data management and analytic computing platforms that are sources of record for data they store. Query performance is monitored and used to generate a query performance model. The query performance model may be used to generate alternatives for queries of users or groups of users or to generate policies for achieving a target performance. Performance may be improved by monitoring queries and retrieving catalog data for databases referenced and generating a recommendation model according to them. Duplicative or overlapping sources may be identified based on the monitoring and transformations to improve accuracy and security may be suggested. A recommendation model may be generated based on analysis of queries received through the UAL. Transformations may be performed according to the recommendation model in order to improve performance.

Abstract: Complex computer system architectures are described for analyzing data elements of a knowledge graph, and predicting new surprising or unforeseen facts from relational learning applied to the knowledge graph. This discovery process takes advantage of the knowledge graph structure to improve the computing capabilities of a device executing a discovery calculation by applying both training and inference analysis techniques on the knowledge graph within an embedding space, and generating a scoring strategy for predicting surprising facts that may be discoverable from the knowledge graph.

Abstract: Provided in various embodiments are a model training method and apparatus, an electronic device and a computer readable storage medium, belonging to the technical field of computers. In those embodiments, at least one sample subset can be obtained according to a sample set configured to train models. For each of the sample subsets, a plurality of machine learning models can be trained corresponding to the sample subset according to the sample subset, and predicted values of the plurality of machine learning models can be obtained for the sample subset. A fusion sample set can then be determined according to the predicted values of the machine learning models for each of the sample subsets, and a target machine learning model can be trained according to the fusion sample set.