Sparkcognition, Inc.

Keith D Moore

Sari Andoni

Junhwan Choi

Elmira M Bonab

Syed Mohammad Amir Husain

Tyler S McDonnell

Syed Mohammad Ali

Erik Skiles

Jimmie Goode

Joshua Bronson

Yiyun Lan

Gavin Sellers

Marissa Wiseman

Daniel P Meador

Eric O Korman

James R Eskew

A method includes receiving, by a processor, an input data set. The input data set includes a plurality of features. The method includes determining, by the processor, one or more characteristics of the input data set. The method includes, based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process. The automated model generation process is configured to generate a plurality of models using a weighted randomization process. The one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features. The method further includes executing, by the processor, the automated model generation process to output a mode, the model including data representative of a neural network.

Automated model building search space reduction

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.

Execution of a genetic algorithm having variable epoch size with selective execution of a training algorithm

A method includes receiving input that identifies one or more data sources and determining, based on the input, a machine learning problem type of a plurality of machine learning problem types supported by an automated model building (AMB) engine. The method also includes generating an input data set of the AMB engine based on application of one or more rules to the one or more data sources. The method further includes, based on the input data set and the machine learning problem type, initiating execution of the AMB engine to generate a neural network configured to model at least a portion of the input data set.

Pre-processing for data-driven model creation

A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.

Ensembling of neural network models

A method includes generating, by a processor of a computing device, an output set of models corresponding to a first epoch of a genetic algorithm and based on an input set of models of the first epoch. The input set and the output set includes data representative of a neural network. The method includes determining a particular model of the output set based on a fitness function. A first topological parameter of a first model of the input set is modified to generate the particular model of the output set. The method includes modifying a probability that the first topological parameter is to be changed by a genetic operation during a second epoch of the genetic algorithm that is subsequent to the first epoch. The method includes generating a second output set of models corresponding to the second epoch and based on the output set and the modified probability.

Execution of a genetic algorithm with variable evolutionary weights of topological parameters for neural network generation and training

A method includes determining a trainable model to provide to a trainer, the trainable model determined based on modification of one or more models of a plurality of models. The plurality of models is generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method also includes providing the trainable model to the trainer. The method further includes adding a trained model, output by the trainer based on the trainable model, as input to a second epoch of the genetic algorithm, the second epoch subsequent to the first epoch.

Cooperative execution of a genetic algorithm with an efficient training algorithm for data-driven model creation

A method includes performing, by a computing device, a clustering operation to group documents of a document corpus into clusters in a feature vector space. The document corpus includes one or more labeled documents and one or more unlabeled documents. Each of the one or more labeled documents is assigned to a corresponding class in classification data associated with the document corpus, and each of the one or more unlabeled document is not assigned to any class in the classification data. The method also includes generating, by the computing device, a prompt requesting classification of a particular document of the document corpus, where the particular document is selected based on a distance between the particular document and a labeled document of the one or more labeled documents.

Generation of document classifiers

A method includes receiving, via a graphical user interface including a plurality of document elements and a plurality of class elements, user input associating a first document element of the plurality of document elements with a first class element of the plurality of class elements. Each document element represents a corresponding document of a plurality of documents, and each class element represents a corresponding class of a plurality of classes. The method also includes generating a document classifier using supervised training data, where the supervised training data indicates, based on the user input, that a first document represented by the first document element is assigned to a first class associated with the first class element.

A method includes receiving an input data set, each entry including multiple features. The method includes receiving a user input identifying a target feature of the multiple features and a target value of the target feature. The method includes determining, one or more correlated features of the multiple features. The method includes providing the input data set to multiple neural networks (including multiple VAEs) to train the multiple neural networks. The method includes generating a simulated data set based on the input data set, each entry including at least the target feature and the one or more correlated features. Values of the one or more correlated features are randomized or pseudorandomized and the target feature is fixed at the target value. The method includes providing the simulated data set to the multiple neural networks to generate output data and displaying a GUI based on the output data.

Model building for simulation of one or more target features

A method includes, based on a fitness function, selecting a subset of models from a plurality of models. The plurality of models is generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method also includes performing at least one genetic operation of the genetic algorithm with respect to at least one model of the subset to generate a trainable model and sending the trainable model to an optimization trainer. The method includes adding a trained model received from the optimization trainer as input to a second epoch of the genetic algorithm that is subsequent to the first epoch.

Growing community of inventors

Cedar Park, TX, United States of America

Keith D Moore