Abstract: A computer-implemented method for reducing computation cost associated with a machine learning task performed by a computer system by implementing continuous control of attention for a deep learning network includes initializing a control-value function, an observation-value function and a sequence of states associated with a current episode. If a current epoch associated with the current episode is odd, an observation-action is selected, the observation-action is executed to observe a partial image, and the observation-value function is updated based on the partial image and the control-value function. If the current epoch is even, a control-action is selected, the control-action is executed to obtain a reward corresponding to the control-action, and the control-value function is updated based on the reward and the observation-value function.

Abstract: Systems and methods disclosed herein relate to autonomous agents. A first autonomous agent receives, from a first sensor, a first set of event data indicating events relating to a subject. The first autonomous agent provides the first set of event data to a data aggregator. The first autonomous agent receives, from the data aggregator, correlated event data including events sensed by the first autonomous agent and a second autonomous agent. The first autonomous agent applies machine learning model to the correlated event data to predict a first pattern of activity and determines, based on the first pattern of activity, that a first action is to be performed, causing the first actuator module to perform the first action.

Abstract: A machine learning model inference routing system in a machine learning service is described herein. The machine learning model inference routing system includes load balancer(s), network traffic router(s), an endpoint registry, and a feedback processing system that collectively allow the machine learning model inference routing system to adjust the routing of inferences based on machine learning model accuracy, demand, and/or the like. In addition, the arrangement of components in the machine learning model inference routing system enables the machine learning service to perform shadow testing, support ensemble machine learning models, and/or improve existing machine learning models using feedback data.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: An approach is provided in which an information handing system determines a hidden cycle of hidden evidence based on one of multiple signals in a frequency-based representation of source evidence. The information handling system extrapolates the hidden evidence to create a forecast data set and, in turn, utilizes the forecast data set to process a request.

Abstract: Systems and methods that use a neural network architecture for extracting interpretable relationships among predictive input variables. This leads to neural network models that are interpretable and explainable. More importantly, these systems and methods lead to discovering new interpretable variables that are functions of predictive input variables, which in turn can be extracted as new features and utilized in other types of interpretable models, like scorecards (fraud score, etc.), but with higher predictive power than conventional systems and methods.

Abstract: A user expertise classifying method, system, and computer program product, include analyzing an input by a user based on at least one of vocabulary, orthography, and grammar of the user input, processing user background data obtained from a database, and calculating an expertise score of the user based on the analyzed user input and the processed background data.

Abstract: Techniques for auto-scaling hosted machine learning models for production inference are described. A machine learning model can be deployed in a hosted environment such that the infrastructure supporting the machine learning model scales dynamically with demand so that performance is not impacted. The model can be auto-scaled using reactive techniques or predictive techniques.

Abstract: Techniques are provided for unification of classifier models across device platforms of varying form factors and/or sensor calibrations. A methodology implementing the techniques according to an embodiment includes extracting classification features from data provided by sensors associated with a first device platform. The method also includes applying a feature mapping function to the extracted features. The feature mapping function is configured to transform the features such that the are suitable for use by a classifier model that is trained on data provided by sensors associated with a second device platform. The method further includes executing the classifier model on the transformed features to generate classifications, for example recognized activities associated with use of the first device. The feature mapping function is based on application of a statistical distribution distance minimization between a sampling of data provided by sensors of the first device and sensors of the second device.

Abstract: A method and system for augmenting a training dataset for a generative adversarial network (GAN). The training dataset includes labelled data samples and unlabelled data samples. The method includes: receiving generated samples generated using a first neural network of the GAN and the unlabelled samples of training dataset; determining a decision value for a sample from a decision function, wherein the sample is a generated sample of the generated samples or an unlabelled sample of the unlabelled samples of the training dataset; comparing the decision value to a threshold; in response to determining that the decision value exceeds the threshold: predicting a label for a sample; assigning the label to the sample; and augmenting the training dataset to include the sample with the assigned label as a labelled sample.

Abstract: Methods for genetic generation of tools for use in a convolutional neural network are provided. Randomly generated starting points and sets of positive and negative tasks are distributed to multiple processors. Each processor iterates an instruction queue over its received tasks based on existing analysis tools, generating a test score for each iteration. A set of instructions is saved as a new tool if its generated test score determines a successful test. A convolutional neural network is executed over complex test cases based on a tool set that includes the new tools. Output results of the convolutional neural network are analyzed and a new tool set is created by removing tools that are not utilized in generating the output results. Systems and machine-readable media are also provided.

Abstract: The amount of time required to train a neural network may be decreased by modifying the neural network to allow for greater parallelization of computations. The computations for cells of the neural network may be modified so that the matrix-vector multiplications of the cell do not depend on a previous cell and thus allowing the matrix-vector computations to be performed outside of the cells. Because the matrix-vector multiplications can be performed outside of the cells, they can be performed in parallel to decrease the computation time required for processing a sequence of training vectors with the neural network. The trained neural network may be applied to a wide variety of applications, such as performing speech recognition, determining a sentiment of text, determining a subject matter of text, answering a question in text, or translating text to another language.

Abstract: A computer in a distributed computing system is disclosed. The computer includes: a graphics processing unit (GPU) memory; a central processing unit (CPU) memory comprising a Key-Value Store (KVS) module; an execution engine module configured to run a deep learning (DL) program to create a plurality of operator graph layers in the graphics processing unit memory; a client library module configured to create a GPU-CPU synchronization (GCS) module for each of the plurality of operator graph layers; a coordination service module configured to compute network cost of a first and a second communication scheme and select, based on the network cost, one of the first and second communication scheme for transmitting data associated with one of the plurality of operator graph layers from a corresponding GCS module.

Abstract: A method for machine learning based database management is provided. The method may include training a machine learning model to detect an anomaly that is present and/or developing in a database system. The anomaly in the database system may be detected by at least processing, with a trained machine learning model, one or more performance metrics for the database system. In response to detecting the presence of the anomaly at the database system, one or more remedial actions may be determined for correcting and/or preventing the anomaly at the database system. The one or more remedial actions may further be sent to a database management system associated with the database system. Related systems and articles of manufacture are also provided.

Abstract: Disclosed herein are neural networks for generating target classifications for an object from a set of input sequences. Each input sequence includes a respective input at each of multiple time steps, and each input sequence corresponds to a different sensing subsystem of multiple sensing subsystems. For each time step in the multiple time steps and for each input sequence in the set of input sequences, a respective feature representation is generated for the input sequence by processing the respective input from the input sequence at the time step using a respective encoder recurrent neural network (RNN) subsystem for the sensing subsystem that corresponds to the input sequence. For each time step in at least a subset of the multiple time steps, the respective feature representations are processed using a classification neural network subsystem to select a respective target classification for the object at the time step.

Abstract: A context-aware attention-based neural network is provided for answering an input question given a set of purportedly supporting statements for the input question. The neural network includes a processing element. The processing element is configured to calculate a question representation for the input question, based on word annotations and word-level attentions calculated for the input question. The processing element is further configured to calculate a sentence representation for each of the purportedly supporting statements, based on word annotations and word-level attentions calculated for each of the purportedly supporting statements. The processing element is also configured to calculate a context representation for the set of purportedly supporting statements with respect to the sentence representation for each of the purportedly supporting statements.

Abstract: A method includes generating, by a processor of a computing device, a first plurality of models (including a first number of models) based on a genetic algorithm and corresponding to a first epoch of the genetic algorithm. The method includes determining whether to modify an epoch size for the genetic algorithm during a second epoch of the genetic algorithm based on a convergence metric associated with at least one epoch that is prior to the second epoch. The second epoch is subsequent to the first epoch. The method further includes, based on determining to modify the epoch size, generating a second plurality of models (including a second number of models that is different than the first number) based on the genetic algorithm and corresponding to the second epoch. Each model of the first plurality of models and the second plurality of models includes data representative of neural networks.

Abstract: Systems, methods, and articles of manufacture to perform an operation comprising deriving, based on a corpus of electronic text, a machine learning data model that associates words with corresponding usage contexts over a window of time, according to a diffusion process, wherein the machine learning data model comprises a plurality of skip-gram models, wherein each skip-gram model comprises a word embedding vector and a context embedding vector for a respective time step associated with the respective skip-gram model, generating a smoothed model by applying a variational inference operation over the machine learning data model, and identifying, based on the smoothed model and the corpus of electronic text, a change in a semantic use of a word over at least a portion of the window of time.

Abstract: A system for multitemporal data analysis is provided, comprising a directed computation graph service module configured to receive input data from a plurality of sources, analyze the input data to determine a best course of action for analyzing the input data, and split the input data for queueing to a general transformer service module or a decomposable service module based at least in part by analysis of the input data; a general transformer service module configured to receive data from the directed computation graph service module, and perform analysis on the received data; and a general transformer service module configured to receive data from directed computational graph module, and perform analysis on the received data.

Abstract: Provided are device and method for determining a Convolutional Neural Network (CNN) model. The device for determining the CNN model includes: a first determination unit configured to determine complexity of a database including multiple samples; a second determination unit configured to determine a classification capability of a CNN model applicable to the database based on the complexity of the database; a third determination unit configured to acquire classification capability of each candidate CNN model; and a matching unit configured to determine the CNN model applicable to the database based on the classification capability of each candidate CNN model. With the device and method for determining the CNN module, a design process of CNN model can be simplified.