Sas Institute Inc.

Jorge Manuel Gomes Da Silva

Ilknur Kaynar Kabul

Ralph Walter Abbey

Mohammadreza Nazari

Patrick Hall

Jared Langford Dean

Susan Edwards Haller

Amirhassan Fallah Dizche

Joshua David Griffin

Afshin Oroojlooyjadid

Davood Hajinezhad

Steven E Krueger

Lawrence Edmund Lewis

Xu Chen

Varunraj Valsaraj

Jonathan Lee Walker

Xindian Long

Xin Jiang Hunt

Saba Emrani

Arin Chaudhuri

Kedar Shriram Prabhudesai

Xunlei Wu

Xingqi Du

Jinxin Yi

Brett Alan Wujek

Hamza Mustafa Ghadyali

Bahar Biller

Alexander Richard Phelps

Ye Liu

Wei Xiao

Prathaban Mookiah

Weichen Wang

Ruiwen Zhang

Hamoon Azizsoltani

Namita Dilip Lokare

Robert Winston Blanchard

Yan Xu

Deovrat Vijay Kakde

Seyedalireza Yektamaram

Hardi Desai

Yan Gao

Hansi Jiang

Seung Hyun Kong

Maria Jahja

Warren Sarle

Yu-Min Lin

Gregory Naisat

Kushawah Yogender Singh

Kiran Devidas Bhole

Girish Vinayak Kolapkar

Aishwarya Sharma

Amod Anil Ankulkar

A system, method, and computer-program product includes commencing a parent computer process based on receiving a request to perform an analytical operation on one or more datasets, commencing at least one child computer process that is launched by the parent computer process when the parent computer process initiates an execution of the analytical operation on the one or more datasets, transmitting, by the at least one child computer process, a request to the parent computer process to retrieve the one or more datasets, writing, by the parent computer process, the one or more datasets to a cross-process queue based on the parent computer process receiving the requests, reading, by the at least one child computer process, the one or more datasets from the cross-process queue, and executing, using an analytical application executing on the least one child computer process, the analytical operation based on the one or more datasets.

Systems and methods for executing an analytical operation across a plurality of computer processes

A computing device determines an optimal number of threads for a computer task. Execution of a computing task is controlled in a computing environment based on each task configuration included in a plurality of task configurations to determine an execution runtime value for each task configuration. An optimal number of threads value is determined for each set of task configurations having common values for a task parameter value, a dataset indicator, and a hardware indicator. The optimal number of threads value is an extremum value of an execution parameter value as a function of a number of threads value. A dataset parameter value is determined for a dataset. A hardware parameter value is determined as a characteristic of each distinct executing computing device in the computing environment. The optimal number of threads value for each set of task configurations is stored in a performance dataset in association with the common values.

Optimal number of threads determination system

A computing device trains a machine state predictive model. A generative adversarial network with an autoencoder is trained using a first plurality of observation vectors. Each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable. The state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state. The first plurality of observation vectors successively defines sequential machine states to manufacture a product. A second plurality of observation vectors is generated using the trained generative adversarial network with the autoencoder. A machine state machine learning model is trained to predict a subsequent machine state using the first plurality of observation vectors and the generated second plurality of observation vectors. A description of the machine state machine learning model is output.

Automated control of a manufacturing process

(A) Conditional vectors are defined. (B) Latent observation vectors are generated using a predefined noise distribution function. (C) A forward propagation of a generator model is executed with the conditional vectors and the latent observation vectors as input to generate an output vector. (D) A forward propagation of a decoder model of a trained autoencoder model is executed with the generated output vector as input to generate a plurality of decoded vectors. (E) Transformed observation vectors are selected from transformed data based on the defined plurality of conditional vectors. (F) A forward propagation of a discriminator model is executed with the transformed observation vectors, the conditional vectors, and the decoded vectors as input to predict whether each transformed observation vector and each decoded vector is real or fake. (G) The discriminator and generator models are updated and (A) through (G) are repeated until training is complete.

Tabular data generation for machine learning model training system

A computing device generates synthetic tabular data. Until a convergence parameter value indicates that training of an attention generator model is complete, conditional vectors are defined; latent vectors are generated using a predefined noise distribution function; a forward propagation of an attention generator model that includes an attention model integrated with a conditional generator model is executed to generate output vectors; transformed observation vectors are selected; a forward propagation of a discriminator model is executed with the transformed observation vectors, the conditional vectors, and the output vectors to predict whether each transformed observation vector and each output vector is real or fake; a discriminator model loss value is computed based on the predictions; the discriminator model is updated using the discriminator model loss value; an attention generator model loss value is computed based on the predictions; and the attention generator model is updated using the attention generator model loss value.

Tabular data generation with attention for machine learning model training system

A computing system responsive to obtaining original image data, detects a set of data point(s), in the original image data, that indicates an object. The system determines, based on the set of data point(s), a set of pixels associated with the object in the original image data. The system generates an alternative visual identifier for the object that provides a unique identifier for the set of pixels absent in the original image data. The system generates, autonomously from intervention by any user of the computing system, pixel information to conceal feature(s) of the object. The system obtains modified image data comprising the alternative visual identifier. The modified image data further comprises the feature(s) of the object in the original image data visually concealed in the modified image data according to the pixel information. The system outputs an image representation of a trajectory of the object through the modified image data.

Real-time concealed object tracking

A computing system obtains image data representing images. Each of the images is captured at different time points of a physical environment. The physical environment comprises a first object and a second object. The computing system executes a control system to augment the physical environment. The control system detects a group forming in the images. The control system tracks an aspect of a movement, of a given object, in the group. The control system simulates the physical environment and the movement, of the given object, in the group in a simulated environment. The control system evaluates simulated actions in the simulated environment for a predefined objective for the physical environment. The predefined objective is related to an interaction between objects in the group. The control system generates based on evaluated simulated actions and autonomously from involvement by any user of the control system, an indication to augment the physical environment.

Real-time spatial and group monitoring and optimization

Data is classified using semi-supervised data. Sparse coefficients are computed using a decomposition of a Laplacian matrix. (B) Updated parameter values are computed for a dimensionality reduction method using the sparse coefficients, the Laplacian matrix, and a plurality of observation vectors. The updated parameter values include a robust estimator of a decomposition matrix determined from the decomposition of the Laplacian matrix. (B) is repeated until a convergence parameter value indicates the updated parameter values for the dimensionality reduction method have converged. A classification matrix is defined using the sparse coefficients and the robust estimator of the decomposition of the Laplacian matrix. The target variable value is determined for each observation vector based on the classification matrix. The target variable value is output for each observation vector of the plurality of unclassified observation vectors and is defined to represent a label for a respective unclassified observation vector.

Distributable event prediction and machine learning recognition system

A computing system trains a reinforcement learning model comprising multiple different attention model components. The reinforcement learning model trains on training data of a first environment (e.g., a first traffic intersection). The reinforcement learning model trains by training a state attention computer model on the training data that weighs each of respective inputs of a respective state. The reinforcement learning model trains by training an action attention computer model that determines a probability of switching from a first action to a second action of the first set of the multiple candidate actions (e.g., changing traffic colors of traffic lights). Alternatively, or additionally, a computing system generates an indication of a selected outcome according to the reinforcement learning model and sends a selection output to the second environment (e.g., a second traffic intersection with more lanes than the first traffic intersection) to implement the selected action in the second environment.

Universal attention-based reinforcement learning model for control systems

A computing system receives historical data. The historical data comprises physical actions taken in an experiment in a physical environment. The experiment comprises user-defined stages. The historical data comprises a recorded outcome, according to user-defined performance indicator(s) related to the user-defined stages, for each physical action taken in the experiment. The system generates, by a discrete event simulator, a computing representation of a simulated environment of the physical environment. The simulated environment comprises processing stages. The system obtains simulation data. The simulation data comprises simulated actions taken by the discrete event simulator. The simulation data comprises a predicted outcome, according to user-defined performance indicator(s) related to the processing stages, for each simulated action taken by the discrete event simulator. The system validates accuracy of the discrete event simulator at predicting the recorded outcome in the experiment. The system trains a computing agent according to a sequential decision-making algorithm.

Discrete event simulation with sequential decision making

Data is classified using semi-supervised data. A decomposition is performed to define a first decomposition matrix that includes first eigenvectors of a weight matrix, a second decomposition matrix that includes second eigenvectors of a transpose of the weight matrix, and a diagonal matrix that includes eigenvalues of the first eigenvectors. Eigenvectors are selected from the first eigenvectors to define a reduced decomposition matrix. A linear transformation matrix is computed as a function of the first decomposition matrix, the reduced decomposition matrix, the diagonal matrix, and a penalty matrix. When a rank of the linear transformation matrix is less than a number of rows of the penalty matrix, a classification matrix is computed by updating a gradient of a cost function. When the rank of the linear transformation matrix is equal to the number of rows of the penalty matrix, the classification matrix is computed using a dual formulation.

Data is classified using semi-supervised data. A weight matrix is computed using a kernel function applied to observation vectors. A decomposition of the computed weight matrix is performed. A predefined number of eigenvectors is selected from the decomposed weight matrix to define a decomposition matrix. (A) A gradient value is computed as a function of the defined decomposition matrix, sparse coefficients, and a label vector. (B) A value of each coefficient of the sparse coefficients is updated based on the gradient value. (A) and (B) are repeated until a convergence parameter value indicates the sparse coefficients have converged. A classification matrix is defined using the converged sparse coefficients. The target variable value is determined and output for each observation vector based on the defined classification matrix to update the label vector and defined to represent the label for a respective unclassified observation vector.

Growing community of inventors

Durham, NC, United States of America

Jorge Manuel Gomes Da Silva