Title: Systems and methods for customizing kernel machines with deep neural networks

Abstract

A method including receiving an input data set. The input data set can include one of a feature domain set or a kernel matrix. The method also can include constructing dense embeddings using: (i) Nyström approximations on the input data set when the input data set comprises the kernel matrix, and (ii) clustered Nyström approximations on the input data set when the input data set comprises the feature domain set. The method additionally can include performing representation learning on each of the dense embeddings using a multi-layer fully-connected network for each of the dense embeddings to generate latent representations corresponding to each of the dense embeddings. The method further can include applying a fusion layer to the latent representations corresponding to the dense embeddings to generate a combined representation. The method additionally can include performing classification on the combined representation. Other embodiments of related systems and methods are also disclosed.

Inventors:

Song, Huan; Thiagarajan, Jayaraman; Spanias, Andreas

Issue Date:

2023-02-21

Research Org.:

Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States); Arizona State Univ., Tempe, AZ (United States)

Sponsoring Org.:

USDOE; National Science Foundation (NSF)

OSTI Identifier:

1987153

Patent Number(s):

11586905

Application Number:

16/152,841

Assignee:

Arizona Board of Regents on Behalf of Arizona State University (Scottsdale, AZ); Lawrence Livermore National Security, LLC (Livermore, CA)

Patent Classifications (CPCs):

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

Show more

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

G06F17/16 - Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

G06N20/10 - using kernel methods, e.g. support vector machines [SVM]
G06N20/20 - Ensemble learning
G06N3/08 - Learning methods
G06N3/082 - {modifying the architecture, e.g. adding or deleting nodes or connections, pruning}
G06N3/084 - {Back-propagation}

Show less

DOE Contract Number:  

1540040; AC52-07NA27344

Resource Type:

Patent

Resource Relation:

Patent File Date: 10/05/2018

Country of Publication:

United States

Language:

English