Abstract: An automated system for recommending predictor variable values for improving predictive outcomes of a predictive model is provided. The automated system recommends appropriate predictor variable values for changeable predictor variables that improve a predictive outcome of the predictive model by (i) computing predictive outcomes for each input record during a batch ETL process and (ii) determining appropriate predictor variable values that lead to improved predictive outcomes, using the code generated extended ETL jobs updated to perform rescoring using a combination of different values of the changeable predictor variables while honoring constraints between the changeable predictor variables, or by enabling an end user to perform said rescoring by changing values of the changeable predictor variables on the fly to determine most suitable predictor variable values that lead to improved predictive outcomes.

Abstract: Hardware and neural architecture co-search may be performed by operations including obtaining a specification of a function and a plurality of hardware design parameters. The hardware design parameters include a memory capacity, a number of computational resources, a communication bandwidth, and a template configuration for performing neural architecture inference. The operations further include determining, for each neural architecture among a plurality of neural architectures, an overall latency of performance of inference of the neural architecture by an accelerator within the hardware design parameters. Each neural architecture having been trained to perform the function with an accuracy. The operations further include selecting, from among the plurality of neural architectures, a neural architecture based on the overall latency and the accuracy.

Abstract: A hardware neural network system includes an input buffer for input neurons (Nbin), an output buffer for output neurons (Nbout), and a third buffer for synaptic weights (SB) connected to a Neural Functional Unit (NFU) and a control logic (CP) for performing synapses and neurons computations. The NFU pipelines a computation into stages, the stages including weight blocks (WB), an adder tree, and a non-linearity function.

Abstract: Techniques and systems are described to model and extract knowledge from images. A digital medium environment is configured to learn and use a model to compute a descriptive summarization of an input image automatically and without user intervention. Training data is obtained to train a model using machine learning in order to generate a structured image representation that serves as the descriptive summarization of an input image. The images and associated text are processed to extract structured semantic knowledge from the text, which is then associated with the images. The structured semantic knowledge is processed along with corresponding images to train a model using machine learning such that the model describes a relationship between text features within the structured semantic knowledge. Once the model is learned, the model is usable to process input images to generate a structured image representation of the image.

Abstract: Techniques are disclosed for the generation of adversarial training data through sequence perturbation, for a deep learning network to perform event sequence analysis. A methodology implementing the techniques according to an embodiment includes applying a long short-term memory attention model to an input data sequence to generate discriminative sequence periods and attention weights associated with the discriminative sequence periods. The attention weights are generated to indicate the relative importance of data in those discriminative sequence periods. The method further includes generating perturbed data sequences based on the discriminative sequence periods and the attention weights. The generation of the perturbed data sequences employs selective filtering or conservative adversarial training, to preserve perceptual similarity between the input data sequence and the perturbed data sequences.

Abstract: A data processing system processes data sets (such as low-resolution transaction data) into high-resolution data sets by mapping generic information into attribute-based specific information that may be processed to identify frequent sets therein. When association rules are generated from such frequent sets, the complexity and/or quantity of such rules may be managed by removing redundancies from the rules, such as by filtering subsumed rules from the generated rule set that have a confidence metric value that does not exceed a first confidence metric value for a subsuming rule by more than a scaled lift threshold value that is calculated by determining a complement of the first confidence metric value, squaring the complement to obtain a squared value and multiplying the squared value by a scaling factor.

Abstract: An embodiment of the invention provides a method to determine relationships between entities where an interface receives a first data set representing observations of a first entity and observations of a second entity, and a second data set representing a relationship between the first entity and the second entity. An entity analytics engine applies a first candidate rule to the first data set to generate a first candidate relationship between the first entity and the second entity. A processor determines whether according to a criterion the first candidate relationship matches the relationship represented in the second data set. The entity analytics engine replaces the first candidate rule with a second candidate rule by when the first candidate relationship does not match the relationship represented in the second data set.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for structuring and training a recurrent neural network. This describes a technique that improves the ability to capture long term dependencies in recurrent neural networks by adding an unsupervised auxiliary loss at one or more anchor points to the original objective. This auxiliary loss forces the network to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full backpropagation through time.

Abstract: The present disclosure relates to computer systems implementing methods for online content recommendation.

Abstract: A method is provided, including: processing interactions by a plurality of users with a plurality of content items, the content items being provided over a network in response to user requests received over the network, wherein each content item is associated with one or more entities; for each user, determining a user entity set that includes entities associated with content items with which the user interacted; embedding the users and the entities in a vector space, wherein the embedding is configured to place a given user, and the entities of the given user's user entity set, in proximity to each other in the vector space; for each user, performing a proximity search in the vector space to identify a set of nearest entities to the user in the vector space; for each user, generating a user profile using the identified set of nearest entities to the user.

Abstract: The present disclosure relates to a content recommendation method, device and system. The method includes: recommending a content in a content set to a user based on an average recommendation probability; collecting feedback information on the recommended content from the user's client, wherein the feedback information includes display information and click information, the display information including displaying times and displaying timing of the recommended content on the client, and the click information including clicking times and clicking timing of the recommended content on the client; and determining a sequence of preferred contents from the contents in the content set according to the feedback information, so as to recommend a content to the user based on the sequence of preferred contents.

Abstract: A computer-implemented method optimizes a neural network. One or more processors define layers in a neural network based on neuron locations relative to incoming initial inputs and original outgoing final outputs of the neural network, where a first defined layer is closer to the incoming initial inputs than a second defined layer, and where the second defined layer is closer to the original outgoing final outputs than the first defined layer. The processor(s) define parameter criticalities for parameter weights stored in a memory used by the neural network, and associate defined layers in the neural network with different memory banks based on the parameter criticalities for the parameter weights. The processor(s) store parameter weights used by neurons in the first defined layer in the first memory bank and parameter weights used by neurons in the second defined layer in the second memory bank.

Abstract: [Problem] To provide a learning device for performing more efficient machine learning. [Solution] A learning device unit according to one embodiment comprises at least one learning device and a connection device for connecting an intermediate learning device having an internal state shared by another learning device unit to the at least one learning device.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices for object detection, tracking, and motion prediction are provided. For example, the disclosed technology can include receiving sensor data including information based on sensor outputs associated with detection of objects in an environment over one or more time intervals by one or more sensors. The operations can include generating, based on the sensor data, an input representation of the objects. The input representation can include a temporal dimension and spatial dimensions. The operations can include determining, based on the input representation and a machine-learned model, detected object classes of the objects, locations of the objects over the one or more time intervals, or predicted paths of the objects. Furthermore, the operations can include generating, based on the input representation and the machine-learned model, an output including bounding shapes corresponding to the objects.

Abstract: Explainable neural networks may be designed to be easily implementable in hardware efficiently, leading to substantial speed and space improvements. An exemplary embodiment extends upon possible hardware embodiments of XNNs, making them suitable for low power applications, smartphones, mobile computing devices, autonomous machines, server accelerators, Internet of Things (IoT) and edge computing applications amongst many other applications. The capability of XNNs to be transformed from one form to another while preserving their logical equivalence is exploited to create efficient, secure hardware implementations that are optimized for the desired application domain and predictable in their behavior.

Abstract: A policy violation detection computer-implemented method, system, and computer program product, includes extracting a policy activity from a policy, the policy activity including an actor in the policy, an object of the policy, an action of the policy, and policy scope metadata, capturing a transaction by a user including metadata of the transaction, translating the transaction by the user into an actor in the transaction, an action of the transaction, and an object of the transaction, and alerting the user of a policy violation by navigating a knowledge graph is-a hierarchy to relate the actor in the transaction to the actor in the policy, the object of the transaction to an object of the policy, and the action of the transaction to an action of the policy activity.

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 for learning parameters of a CNN using a 1×K convolution operation or a K×1 convolution operation is provided to be used for hardware optimization which satisfies KPI. The method includes steps of: a learning device (a) instructing a reshaping layer to two-dimensionally concatenate features in each group comprised of corresponding K channels of a training image or its processed feature map, to thereby generate a reshaped feature map, and instructing a subsequent convolutional layer to apply the 1×K or the K×1 convolution operation to the reshaped feature map, to thereby generate an adjusted feature map; and (b) instructing an output layer to refer to features on the adjusted feature map or its processed feature map, and instructing a loss layer to calculate losses by referring to an output from the output layer and its corresponding GT.

Abstract: Handshake protocol layer features are extracted from training data associated with encrypted network traffic of a plurality of classified devices. Record protocol layer features are extracted from the training data. One or more models are trained based on the extracted handshake protocol layer features and the extracted record protocol layer features. The one or more models are applied to an observed encrypted network traffic stream associated with a device to determine a predicted device classification of the device.

Abstract: The present invention discloses a neural network training method for a memristor memory for memristor errors, which is mainly used for solving the problem of decrease in inference accuracy of a neural network based on the memristor memory due to a process error and a dynamic error. The method comprises the following steps: performing modeling on a conductance value of a memristor under the influence of the process error and the dynamic error, and performing conversion to obtain a distribution of corresponding neural network weights; constructing a prior distribution of the weights by using the weight distribution obtained after modeling, and performing Bayesian neural network training based on variational inference to obtain a variational posterior distribution of the weights; and converting a mean value of the variational posterior of the weights into a target conductance value of the memristor memory.