Abstract: Techniques are shown for generating image frames from a media presentation. In one embodiment a computer implemented method is provided. The method includes identifying, by a processing device, image frames from a media presentation comprising a plurality of image frames. Candidate thumbnails are selected from the identified image frames. A probability is determined that a selected candidate thumbnail with a success ranking higher than other selected thumbnails is an optimum candidate thumbnail for representing the media presentation in view of a relationship between the success ranking of the selected candidate thumbnail and the success rankings of the other selected candidate thumbnails. Thereupon, data for displaying the selected candidate thumbnail to a user as a representative of the media presentation is provided by the processing device.

Abstract: In one embodiment, a system to accelerate batch-normalized convolutional neural network (CNN) models is disclosed. The system extracts a plurality of first groups of layers from a first CNN model, each group of the first groups having a first convolutional layer and a first batch-norm layer. For each group of the plurality of first groups, the system calculates a first scale vector and a first shift vector based on the first batch-norm layer, and generates a second convolutional layer representing the corresponding group of the plurality of first groups based on the first convolutional layer and the first scale and the first shift vectors. The system generates an accelerated CNN model based on the second convolutional layer corresponding to the plurality of the first groups, such that the accelerated CNN model is utilized subsequently to classify an object perceived by an autonomous driving vehicle (ADV).

Abstract: Architectures for multicore neuromorphic systems are provided. In various embodiments, a neural network description is read. The neural network description describes a plurality of logical cores. A plurality of precedence relationships are determined among the plurality of logical cores. Based on the plurality of precedence relationships, a schedule is generated that assigns the plurality of logical cores to a plurality of physical cores at a plurality of time slices. Based on the schedule, the plurality of logical cores of the neural network description are executed on the plurality of physical cores.

Abstract: Systems and methods for creating and/or using an artificial intelligence memory system that models human memory are provided. The AI memory system creates and/or uses a user centric memory graph. The user centric memory graph implicitly links memory elements of a user utilizing relationships created in space, time, and cognitive dimensions similar to how the human brain stores and recalls different memory elements. The user centric memory graph is used by searching and/or constraining the user centric memory graph based on a determined user context and/or a user query.

Abstract: Disclosed herein are system, method, and computer program product embodiments for encoding symbolic data into a subsymbolic format while preserving the semantic arrangement of the symbolic data. In an embodiment, to encode the symbolic data, a subsymbolic encoder system may convert a symbolic graph into a tuple representation having tuple elements corresponding to the nodes of the symbolic graph. The subsymbolic encoder system may retrieve a dictionary identification for each tuple element and calculate a subsymbolic value for each tuple element using an exponential component. The subsymbolic encoder system may standardize the length of the subsymbolic values and/or add a weighted relationship indicator to the subsymbolic values. The subsymbolic encoder system may transmit the subsymbolic values to a subsymbolic intelligence system.

Abstract: A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.

Abstract: A non-transitory computer-readable recording medium stores therein a program for causing a computer to execute a process for, in repeatedly training a given training model, repeatedly training the training model a given number of times by using a numerical value of a floating-point number, the numerical value being a parameter of the training model or training data of the training model, or any combination thereof; and, after the training by using the numerical value of the floating-point number, repeatedly training the training model by using a numerical value of a fixed-point number corresponding to a numerical value of the floating-point number obtained by the training.

Abstract: A synchrophasor measurement-based disturbance identification method is described considering different penetration levels of renewable energy. A differential Teager-Kaiser energy operator (dTKEO)-based algorithm is first utilized to improve multiple-disturbances detection accuracy. Then, feature extractions via the integrated additive angular margin (AAM) loss and the long short-term memory (LSTM) network is described. This enables one to deal with intra-class similarity and inter-class variance of disturbances when high penetration renewable energy occurs. With the extracted features, a multi-stage weighted summing (MSWS) loss-based criterion is described for adaptive data window determination and fast disturbance pre-classification. Finally, the re-identification model based on feature similarity is established to identify unknown disturbances, a challenge for existing machine learning algorithms.

Abstract: The present disclosure discloses method and system for extracting relevant entities from a text corpus. The method comprises receiving, by the entity extraction computing device, a text corpus and an entity, determining at least one feature for each block of text from the text corpus, where the at least one feature corresponds to predefined one or more feature heads, calculating a score for each block of text from the text corpus based on training of the entity extraction system, determining a template from one or more templates based on the score, where the one or more templates are generated based on the training of the entity extraction system, and extracting at least one relevant entity from the text corpus, with respect to the entity, based on the template. The method and system disclosed in the present disclosure may be used to extract relevant entities across various domains by training the system.

Abstract: Computer-implemented, machine-learning systems and methods relate to a combination of neural networks. The systems and methods train the respective member networks both (i) to be diverse and yet (ii) according to a common, overall objective. Each member network is trained or retrained jointly with all the other member networks, including member networks that may not have been present in the ensemble when a member is first trained.

Abstract: A system and method for solving linear complementarity problems for rigid body simulation is disclosed. The method includes determining one or more contact constraints affecting an original object having an original mass. The method includes splitting the original object by a total number of the contact constraints into a plurality of sub-bodies. The method includes assigning a contact constraint to a corresponding sub-body. The method further includes solving contact constraints in isolation for each sub-body. The method also includes enforcing positions and orientations of each sub-body are identical.

Abstract: A computer system receives multiple datapoints of a geomechanical property of a hydrocarbon reservoir modeled by a three-dimensional (3D) grid. Each datapoint corresponds to a respective grid cell of the 3D grid. Each grid cell of the 3D grid is represented by 3D coordinates. For each grid cell of the 3D grid, the computer system generates a data component of the geomechanical property based on the 3D coordinates of the grid cell. The computer system adds the data component to a datapoint corresponding to the grid cell to provide an augmented set of datapoints. The computer system transforms the augmented set of datapoints into a Gaussian distribution using Gaussian approximation. The computer system simulates the geomechanical property of the hydrocarbon reservoir based on the Gaussian distribution using sequential Gaussian simulation.

Abstract: The disclosure generally describes methods, software, and systems, including a method for machine learning anomaly detection for a set of assets. Assets are analyzed using anomaly-detection analysis and a set of anomaly-detection rules. Each asset is associated with correlated records comprising characteristics of the particular asset and characteristic of non-asset-specific signals. Each anomaly-detection rule is associated with conditions determined to be indicative of a potential anomaly. At least a subset of the assets are provided for presentation in a user interface. Each asset is identified as being in a potential anomalous or non-anomalous state based on the anomaly-detection analysis. Input is received from a user identifying at least one asset as anomalous as a non-anomalous asset. Based on the received input, at least one anomaly-detection rule is modified that was applied to identify the asset as anomalous. The modified rule is stored for future analyses.

Abstract: A structural design method of a product is provided. The method includes obtaining a preliminary design of a subsurface mesh structure by filling a body model of the product with spherical cells at preset positions of the body model and performing an finite element analysis and optimization; and optimizing, through a design method for optimizing functions, filling features of the spherical cells based on a simulation analysis so that the structure of the product satisfies a preset target.

Abstract: A method and a device that performs the method for measuring the flatness of a metal product traveling on a path, the method includes measuring a first longitudinal tension measurement value (T1) with a measuring roller, determining a model of stress over the thickness of the metal product as a function of plastic or elastoplastic deformation of the product, calculating a correction factor for the longitudinal deformation according to the stress model, calculating a corrective value (T1?, T2?) for the first longitudinal tension measurement value (T1) at at least one evaluation point (M1, M2) as a function of the longitudinal deformation correction factor (Z1), and calculating a corrected flatness measurement value (PC) at at least one of the evaluation points.

Abstract: A set of vectors may be obtained. The vectors may be multi-dimensional vectors that are associated with and describe tokens from a first set of tokens from a corpus of sources. The description may be based in part on the relationship of the token to at least a portion of the remainder of the corpus. A set of sentiment scores may be obtained. The sentiment scores in the set of sentiment scores may describe a sentiment associated with a corresponding token that is described by a vector from the set of vectors. The set of vectors and the set of sentiment scores may be input into a pattern-recognizer pathway in a first neural network. A probability value of a potential future event may then be generated by the first neural network. The probability value may be based on the set of vectors and the set of sentiment scores.

Abstract: Techniques for monitoring and optimizing Monte Carlo simulations within a provider network are described. A metric representing a similarity between a first data distribution associated with a Monte Carlo simulation template and a second data distribution associated with a data source is generated and evaluated against a condition based on a threshold. A new Monte Carlo simulation template is generated based on the Monte Carlo simulation template. A Monte Carlo simulation is run based on the new Monte Carlo simulation template using a plurality of virtual machines (VMs).

Abstract: A machine learning module receives inputs comprising attributes of a storage controller, where the attributes affect performance parameters for performing stages and destages in the storage controller. In response to an event, the machine learning module generates, via forward propagation, an output value that indicates whether to fill holes in a track of a cache by staging data to the cache prior to destage of the track. A margin of error is calculated based on comparing the generated output value to an expected output value, where the expected output value is generated from an indication of whether it is correct to fill holes in a track of the cache by staging data to the cache prior to destage of the track. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation to reduce the margin of error.

Abstract: Systems, apparatus and methods described herein are configured to receive a user command line instruction, of a first type, for transmission to a device and convert the user command line instruction to a device specific command line instruction. In some embodiments, the systems, apparatus and methods described herein are further configured to transmit the device specific command line instruction to the device, and convert a device specific response received from the device to a response of the first type.

Abstract: A method is provided for correcting a curvature or deformity in a patient's spine based on the digitized locations of implanted screws. The method is implemented by a control unit through a GUI to digitize screw locations, accept one or more correction outputs, and generate one or more rod solution outputs shaped to fit at locations distinct from the implanted screw locations.