logo

For the Inventor, By the Inventor

The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Patent No.:

US 12737435 B1

PDFFull Text
Date of Patent:
Sep. 15, 2026

Filed:

Oct. 25, 2021

Deep neural networks via prototype factorization

Applicant:

Robert Bosch Gmbh, Stuttgart, DE;

Inventors:

Panpan Xu, Santa Clara, CA (US);

Liu Ren, Saratoga, CA (US);

Zeng Dai, Santa Clara, CA (US);

Junhan Zhao, Melrose, MA (US);

Assignee:

Robert Bosch GmbH, , DE;

Attorney:

Dickinson Wright PLLC

Primary Examiner:

Kakali Chaki

Assistant Examiner:

Josep undefined Han

Int. Cl.
CPC ...
G06N 3/045 (2023.01); G06F 18/20 (2023.01); G06F 18/2113 (2023.01); G06F 18/214 (2023.01); G06F 18/241 (2023.01); G06F 18/2413 (2023.01); G06N 3/0464 (2023.01); G06N 3/08 (2023.01); G06N 3/082 (2023.01); G06N 3/084 (2023.01); G06N 3/09 (2023.01); G06N 20/00 (2019.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06F 18/24133 (2023.01); G06F 18/2113 (2023.01); G06F 18/2148 (2023.01); G06F 18/285 (2023.01); G06N 3/082 (2013.01);
Abstract

A method may include receiving a set of images, analyzing the images, selecting an internal layer, extracting neuron activations, factorizing the neuron activations via a matrix factorization algorithm to select prototypes and generate weights for each of the selected prototypes, replacing the neuron activations of the internal layer with the selected prototypes and the weights for the selected prototypes, receiving a second set of images, classifying the second set of images using the prototypes and weights, displaying the second set of images, selected prototypes, and weights, displaying predicted results and ground truth for the second set of images, providing error images based on the predicted results and ground truth; identifying error prototypes of the selected prototypes associated with the error images; ranking error weights of the error prototypes, and outputting a new image class based on the error prototypes being one of a top ranked error weights.

Find Patent Forward Citations

Xu, Panpan. (2026). Deep neural networks via prototype factorization (U.S. Patent No. 12737435). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12737435

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…