Enter inventor name

Hojin Cho

This inventor holds 150 USPTO granted patents and 1 published patent application and 121 EPO patents, primarily in Autonomous Driving Safety (CPC class G06K9-6262). Top assignees: Stradvision, Inc., Stadvision, Inc., Stradivision, Inc.. Active years: 2016-2022.

USPTO Granted Patents = 150 (Patent Applications = 1)

% Patents Active = 100.0

EPO Patents = 121 (Patent Applications = 116)

Average Co-Inventor Count = 10.3

ph-index = 14

Forward Citations = 879(Granted Patents)

Forward Citations (Not Self Cited) = 684(Dec 10, 2025)

Inventors with similar research interests:

🔬 See more inventors

Location History:

Pohang-si, KR (2019 - 2021)
Gyeongsangbuk-do, KR (2016 - 2022)

Company Filing History:

Stradvision Korea, Inc.

patents

Years Active: 2016-2022

Loading Chart...

Areas of Expertise:

Neural Network

Sensor Fusion

V2X Communication

Reinforcement Learning

Autonomous Vehicles

Blind Spot Monitoring

Lane Departure Warning

Path Planning

Emergency Vehicle Detection

Object Detection

Driving Habits Evaluation

Virtual Data Generation

150 patents (USPTO):Sort by Forward CitationsExplore Patents

1. 11461653 - Learning method and learning device for CNN using 1xK or Kx1 convolution to be used for hardware optimization, and testing method and testing device using the same (2022-10-04),

2. 11315021 - Method and device for on-device continual learning of a neural network which analyzes input data, and method and device for testing the neural network to be used for smartphones, drones, vessels, or military purpose (2022-04-26),

3. 11087175 - Learning method and learning device of recurrent neural network for autonomous driving safety check for changing driving mode between autonomous driving mode and manual driving mode, and testing method and testing device using them (2021-08-10),

4. 11074480 - Learning method and learning device for supporting reinforcement learning by using human driving data as training data to thereby perform personalized path planning (2021-07-27),

5. 11017673 - Method and device for learning generating lane departure warning (LDW) alarm by referring to information on driving situation to be used for ADAS, V2X or driver safety required to satisfy level 4 and level 5 of autonomous vehicles (2021-05-25),

6. 11010668 - Method and device for attention-driven resource allocation by using reinforcement learning and V2X communication to thereby achieve safety of autonomous driving (2021-05-18),

7. 10984262 - Learning method and testing method for monitoring blind spot of vehicle, and learning device and testing device using the same (2021-04-20),

8. 10919543 - Learning method and learning device for determining whether to switch mode of vehicle from manual driving mode to autonomous driving mode by performing trajectory-based behavior analysis on recent driving route (2021-02-16),

9. 10890916 - Location-specific algorithm selection for optimized autonomous driving (2021-01-12),

10. 10872297 - Learning method and learning device for generating training data from virtual data on virtual world by using generative adversarial network, to thereby reduce annotation cost required in training processes of neural network for autonomous driving, and a testing method and a testing device using the same (2020-12-22),

11. 10861183 - Method and device for short-term path planning of autonomous driving through information fusion by using V2X communication and image processing (2020-12-08),

12. 10843728 - Method and device for delivering steering intention of autonomous driving module or driver to steering apparatus of subject vehicle more accurately (2020-11-24),

13. 10838418 - Method for providing autonomous driving service platform to be used for supporting autonomous driving of vehicles by using competitive computing and information fusion, and server using the same (2020-11-17),

14. 10832140 - Method and device for providing information for evaluating driving habits of driver by detecting driving scenarios occurring during driving (2020-11-10),

15. 10831189 - Learning method and learning device for providing functional safety by warning driver about potential dangerous situation by using explainable AI which verifies detection processes of autonomous driving network, and testing method and testing device using the same (2020-11-10),

Title: Innovator Spotlight: Hojin Cho - Revolutionizing CNN Hardware Optimization and On-Device Continual Learning

Introduction:

In the world of innovations and patents, it is crucial to acknowledge the talented individuals who contribute immensely to advancements in technology. Today, we shine the spotlight on Hojin Cho, a visionary inventor who hails from Gyeongsangbuk-do, South Korea. With an impressive portfolio of 150 patents and groundbreaking inventions, Cho has made significant contributions in the field of artificial intelligence and machine learning.

Latest Patents:

Cho's latest patents include two pioneering inventions that have the potential to revolutionize CNN hardware optimization, as well as on-device continual learning of neural networks. The first patent focuses on a learning method and learning device for CNN, utilizing 1xK or Kx1 convolution to optimize hardware performance. This method facilitates parameter learning of a CNN by instructing the reshaping layer to concatenate features in each group, generating adjusted feature maps that effectively satisfy Key Performance Indicators (KPIs).

The second patent encompasses a method and device for on-device continual learning of neural networks. This invention enables smartphones, drones, vessels, and military applications to perform continual learning of input data. By utilizing generative adversarial networks (GANs) and online learning techniques, this method efficiently saves resources, prevents catastrophic forgetting, and ensures privacy.

Career Highlights:

Hojin Cho has cultivated an illustrious career with several notable achievements. He has been associated with prominent companies in the AI industry, including StradVision, Inc., making significant contributions to their research and development efforts. Additionally, Cho has worked with StadVision, Inc., playing an instrumental role in their technological advancements.

Collaborations:

Throughout his career, Hojin Cho has collaborated with other esteemed professionals in the field. Notably, he has worked closely with Taewoong Jang and Yongjoong Kim, who have contributed to the success of his projects. The collaborative efforts of these inventive minds have undoubtedly yielded remarkable outcomes in the realm of AI and machine learning.

Conclusion:

Hojin Cho's contributions to the field of innovations and patents are truly commendable. With an extensive portfolio of 150 patents, Cho has demonstrated his remarkable ability to push boundaries and drive advancements in CNN hardware optimization and on-device continual learning of neural networks. His inventions hold immense potential for various applications, including smartphones, drones, vessels, and military technologies. As we eagerly anticipate his future endeavors, we applaud Hojin Cho for his innovative spirit and dedication to pushing the boundaries of artificial intelligence.

This text is generated by artificial intelligence and may not be accurate.

Please report any incorrect information to [email protected]