Abstract: A method, system, and computer program product for obtaining a first route traversed by a target object, performing at least one prediction for a second route to be traversed by the target object based on the first route, the at least one prediction being performed with at least one of an object-specific prediction model, an object group-specific prediction model, and an object-independent prediction model, and determining, according to a decision rule, a prediction result of the second route based on the at least one prediction.

Abstract: A method and system are provided for adaptive evaluation of meta-relationships in semantic graphs. The method includes providing a semantic graph based on a knowledge base in which concepts in the form of graph nodes are linked by semantic relationships in the form of graph edges. Metadata are encoded in the edges and nodes of the semantic graph, of weightings for measuring a meta-relationship, wherein the meta-relationship applies to the concepts of the semantic graph and is independent of the semantic relationship defined by the edges of the semantic graph. A graph activation is carried out for an input context relating to one or more concepts of the semantic graph, wherein the weightings are applied to a spreading activation signal through the semantic graph to produce a measure of the meta-relationship for a sub-set of concepts of the semantic graph.

Abstract: A scalable stream synaptic supercomputer for extreme throughput neural networks is provided. The firing state of a plurality of neurons of a first neurosynaptic core is determined substantially in parallel. The firing state of the plurality of neurons is delivered to at least one additional neurosynaptic core substantially in parallel.

Abstract: A system performs an automated analysis on a set of related media content items, such as static and video display advertisements for a coordinated advertising campaign. The analysis can include, for example, recognition of products, services, brands, objects, music, speech, motion, colors and moods, in order to determine content profiles for the content items. Different sequences of the media content items are placed within the web browsing paths of individual users, and the responses to the sequences are monitored with respect to desired outcomes, such as the purchase of a product or the visiting of an advertiser's website. The content profiles, the sequences, the placements, and the responses are provided as input into a machine learning system that is trained to select sequences and placements of media content items that achieve the desired outcomes. The system can be trained in part or wholly using feedback from its own output.

Abstract: Techniques are described in which a qubit is far off-resonantly, or dispersively, coupled to a quantum mechanical oscillator. In particular, a dispersive coupling between a physical qubit and a quantum mechanical oscillator may be selected such that control of the combined qubit-oscillator system can be realized. The physical qubit may be driven with an electromagnetic pulse (e.g., a microwave pulse) and the quantum mechanical oscillator simultaneously driven with another electromagnetic pulse, the combination of which results in a change in state of the qubit-oscillator system.

Abstract: A learning computer system may include a data processing system and a hardware processor and may estimate parameters and states of a stochastic or uncertain system. The system may receive data from a user or other source. Parameters and states of the stochastic or uncertain system are estimated using the received data, numerical perturbations, and previous parameters and states of the stochastic or uncertain system. It is determined whether the generated numerical perturbations satisfy a condition. If the numerical perturbations satisfy the condition, the numerical perturbations are injected into the estimated parameters or states, the received data, the processed data, the masked or filtered data, or the processing units.

Abstract: Systems, methods, devices, and other techniques for training a trajectory planning neural network system to determine waypoints for trajectories of vehicles. A neural network training system can train the trajectory planning neural network system on the multiple training data sets. Each training data set can include: (i) a first training input that characterizes a set of waypoints that represent respective locations of a vehicle at each of a series of first time steps, (ii) a second training input that characterizes at least one of (a) environmental data that represents a current state of an environment of the vehicle or (b) navigation data that represents a planned navigation route for the vehicle, and (iii) a target output characterizing a waypoint that represents a target location of the vehicle at a second time step that follows the series of first time steps.

Abstract: A machine learning (ML) task system trains a neural network model that learns a compressed representation of acquired data and performs a ML task using the compressed representation. The neural network model is trained to generate a compressed representation that balances the objectives of achieving a target codelength and achieving a high accuracy of the output of the performed ML task. During deployment, an encoder portion and a task portion of the neural network model are separately deployed. A first system acquires data, applies the encoder portion to generate a compressed representation, performs an encoding process to generate compressed codes, and transmits the compressed codes. A second system regenerates the compressed representation from the compressed codes and applies the task model to determine the output of a ML task.

Abstract: Certain aspects of the present disclosure provide techniques for improving a user experience based on electronic records of transactions. Embodiments include training a classifier using training data comprising a set of historical transaction descriptions and a set of corresponding historical classifications that indicate whether or not each historical transaction description of the set of historical transaction descriptions is associated with a user location. Embodiments further include receiving a transaction record describing a transaction associated with a user. Embodiments further include using the classifier to determine a classification for the transaction. The classification indicates whether or not the transaction description is associated with a location of the user. Embodiments further include providing, based at least in part on the classification, a communication to the user that relates to the location of the user.

Abstract: The present subject matter discloses a system and method to enable a machine learning based analytics platform. The method may comprise generating a graphical user interface to enable one or more stakeholders to generate and manage a model for predictive analysis. The method may further comprise enabling a business user to define the business problem, and generate models to perform predictive analysis. The method may further comprise deploying the model, in a distributed environment, over a target platform. The method may further comprise monitoring the model to identify at least one error in the model and re-training the model for performing predictive analysis based on the at least one error, thereby enabling the machine learning based analytics platform.

Abstract: The technology disclosed relates to evolving a deep neural network based solution to a provided problem. In particular, it relates to providing an improved cooperative evolution technique for deep neural network structures. It includes creating blueprint structures that include a plurality of supermodule structures. The supermodule structures include a plurality of modules. The modules are neural networks. A first loop of evolution executes at the blueprint level. A second loop of evolution executes at the supermodule level. Further, multiple mini-loops of evolution execute at each of the subpopulations of the supermodules. The first loop, the second loop, and the mini-loops execute in parallel.

Abstract: Training risk determination models based on a set of labeled data transactions. A first set of labeled data transactions that have been labeled during a review process is accessed. A first risk determination model is trained using the first set of labeled data transactions. A first risk score for data transactions of a set of unlabeled data transactions is determined using the first risk determination model. Data transactions in the set of unlabeled data transactions are newly labeled based on the first risk score. The newly labeled data transactions are added to a second set of labeled data transactions that include the first set of labeled data transactions. A second risk determination model is trained using at least the second set of labeled data transactions. A second risk score is determined for subsequently received data transactions and these data transactions are rejected or approved based on the second risk score.

Abstract: A technique is described herein for processing documents in a time-efficient and accurate manner. In a training phase, the technique generates a set of initial training examples by associating entity mentions in a text corpus with corresponding entity identifiers. Each entity identifier uniquely identifies an entity in a particular ontology. The technique then removes noisy training examples from the set of initial training examples, to provide a set of filtered training examples. The technique then applies a machine-learning process to generate a linking component based, in part, on the set of filtered training examples. In an application phase, the technique uses the linking component to link input entity mentions with corresponding entity identifiers. Various application systems can leverage the capabilities of the linking component, including a search system, a document-creation system, etc.

Abstract: The technology disclosed relates to evolving deep neural network structures. A deep neural network structure includes a plurality of modules with submodules and interconnections among the modules and the submodules. In particular, the technology disclosed relates to storing candidate genomes that identify respective values for a plurality of hyperparameters of a candidate genome. The hyperparameters include global topology hyperparameters, global operational hyperparameters, local topology hyperparameters, and local operational hyperparameters. It further includes evolving the hyperparameters by training, evaluating, and procreating the candidate genomes and corresponding modules and submodules.

Abstract: Implementing a neural network can include receiving a macro instruction for implementing the neural network within a control unit of a neural network processor. The macro instruction can indicate a first data set, a second data set, a macro operation for the neural network, and a mode of operation for performing the macro operation. The macro operation can be automatically initiated using a processing unit of the neural network processor by applying the second data set to the first data set based on the mode of operation.

Abstract: A data analysis device that analyzes data having a record including an objective variable and a plurality of explanatory variables includes a node generating unit that generates a node specified by a condition of the explanatory variable on the basis of the objective variable and the explanatory variable of the record and associating the record with the node, an evaluation value generating unit that generates a proportion of the number of records whose target value is the objective variable among a plurality of records associated with the node as an evaluation value, and a parameter extracting unit that selects a node on the basis of the evaluation value and extracts and outputs the condition of the explanatory variable related to the selected node.

Abstract: Neural network architectures, with connection weights determined using Legendre Memory Unit equations, are trained while optionally keeping the determined weights fixed. Networks may use spiking or non-spiking activation functions, may be stacked or recurrently coupled with other neural network architectures, and may be implemented in software and hardware. Embodiments of the invention provide systems for pattern classification, data representation, and signal processing, that compute using orthogonal polynomial basis functions that span sliding windows of time.

Abstract: A data analytics platform may be configured to construct an inferential model for a multivariate observation vector using inferential modeling in combination with component analysis, which may enable the data analytics platform to evaluate only a subset of the variables in the observation vector and then output a predicted version of the multivariate observation vector that includes predicted values for the full set of variables that was originally included in the observation vector. In turn, the data analytics platform may use the predicted version of the multivariate observation vector output by the inferential model to determine whether an anomaly has occurred.

Abstract: Disclosed is a neuromorphic integrated circuit including, in some embodiments, a multi-layered neural network disposed in an analog multiplier array of two-quadrant multipliers. Each multiplier of the multipliers is wired to ground and draws a negligible amount of current when input signal values for input signals to transistors of the multiplier are approximately zero, weight values of the transistors of the multiplier are approximately zero, or a combination thereof. Also disclosed is a method of the neuromorphic integrated circuit including, in some embodiments, training the neural network; tracking rates of change for the weight values; determining if and how quickly certain weight values are trending toward zero; and driving those weight values toward zero, thereby encouraging sparsity in the neural network. Sparsity in the neural network combined with the multipliers wired to ground minimizes power consumption of the neuromorphic integrated circuit such that battery power is sufficient for power.

Abstract: A computer-implemented method for employing input-conditioned filters to perform natural language processing tasks using a convolutional neural network architecture includes receiving one or more inputs, generating one or more sets of filters conditioned on respective ones of the one or more inputs by implementing one or more encoders to encode the one or more inputs into one or more respective hidden vectors, and implementing one or more decoders to determine the one or more sets of filters based on the one or more hidden vectors, and performing adaptive convolution by applying the one or more sets of filters to respective ones of the one or more inputs to generate one or more representations.