For the Inventor, By the Inventor

Enter assignee name

San Jose, CA, United States of America

Recogni Inc.

USPTO Granted Patents = 25

% Expired Patents = 4.0

EPO Patents = 6

Trademarks = 2

Forward Citations = 10

Loading Chart...

Loading Chart...

16 inventors (with patents filed for the assignee):

Gary S Goldman (15 out of 40 patents)

Eugene M Feinberg (12 out of 26 patents)

Jian Hui Huang (9 out of 10 patents)

4. Shabarivas Abhiram (7 out of 7 patents)

5. Berend Ozceri (5 out of 6 patents)

6. Ashwin Radhakrishnan (4 out of 5 patents)

7. Pradeep R Joginipally (4 out of 5 patents)

8. Gilles J C A Backhus (3 out of 3 patents)

9. Martin Stefan Patz (3 out of 3 patents)

10. James Michael Bodwin (2 out of 4 patents)

11. Kalyana S Venkataraman (2 out of 3 patents)

12. Ramalingam K Anand (2 out of 3 patents)

13. Chung Y Lau (2 out of 3 patents)

14. Jigar K Savla (2 out of 3 patents)

15. Michael Davie (2 out of 3 patents)

Core Competencies:

AI Accelerator

Integrated Circuit

Convolutional Neural Network

Multiply Accumulate

Matrix Multiplication

Low Power Architecture

Convolution Engine

Cluster Compression

Data Processing

Neural Networks

Three-Dimensional Modeling

Deterministic Data Generation

25 patents: Sort by Forward Citations

1. 12436896 - AI accelerator integrated circuit chip with integrated cell-based fabric adapter (2025-10-07),

2. 12430547 - AI accelerator integrated circuit chip with integrated cell-based fabric adapter (2025-09-30),

3. 12293163 - Split accumulator with a shared adder (2025-05-06),

4. 12271624 - Methods and systems for processing read-modify-write requests (2025-04-08),

5. 12165041 - Low power hardware architecture for handling accumulation overflows in a convolution operation (2024-12-10),

6. 12141685 - Low power hardware architecture for a convolutional neural network (2024-11-12),

7. 12045309 - Systems and methods for performing matrix multiplication with a plurality of processing elements (2024-07-23),

8. 12039290 - Multiply accumulate (MAC) unit with split accumulator (2024-07-16),

9. 12026478 - Multiply accumulate (MAC) unit with split accumulator (2024-07-02),

10. 12008069 - Multi-mode architecture for unifying matrix multiplication, 1×1 convolution and 3×3 convolution (2024-06-11),

11. 12007937 - Multi-mode architecture for unifying matrix multiplication, 1×1 convolution and 3×3 convolution (2024-06-11),

12. 11915126 - Low power hardware architecture for a convolutional neural network (2024-02-27),

13. 11762946 - Systems for using shifter circuit and 3×3 convolver units to emulate functionality of larger sized convolver units (2023-09-19),

14. 11694069 - Methods for processing data in an efficient convolutional engine with partitioned columns of convolver units (2023-07-04),

15. 11694068 - Methods for processing horizontal stripes of data in an efficient convolutional engine (2023-07-04),

Company Overview

Recogni Inc. is a technology company based in San Jose, California, specializing in advanced artificial intelligence solutions for automotive applications. The organization focuses on developing high-performance, energy-efficient hardware and software systems designed to enhance perception and decision-making in autonomous vehicles. By leveraging cutting-edge machine learning algorithms and computer vision technologies, Recogni aims to enable safer and more efficient transportation systems, contributing to the evolution of smart mobility solutions.

Profile summary synthesized from public USPTO records and patent filings.

Company Badge

USPTO Data Jan 1 1976 - Oct 13 2026

25 Patents

#298 in San Jose, CA

#3,157 in California

#13,364 in US

#25,710 in the World

San Jose, CA, United States of America

Recogni Inc.

Forward Citations = 10

16 inventors:

Gary S Goldman (15 out of 40 patents)

Eugene M Feinberg (12 out of 26 patents)

Jian Hui Huang (9 out of 10 patents)

4. Shabarivas Abhiram (7 out of 7 patents)

5. Berend Ozceri (5 out of 6 patents)

IDiyas Innovation Intelligence. (2026). Company Patent Portfolio: Recogni Inc.. Retrieved from https://idiyas.com/company/recogni

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

Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]

Loading…