logo

For the Inventor, By the Inventor

Gyeongsangbuk-do, South Korea

Insu Kim

USPTO Granted Patents = 82

 

Average Co-Inventor Count = 13.0

ph-index = 9

Forward Citations = 430(Granted Patents)

Forward Citations (Not Self Cited) = 399(Dec 10, 2025)


Inventors with similar research interests:


Location History:

  • Gyeongsangbok-do, KR (2019)
  • Pohang-si, KR (2019 - 2020)
  • Gyeongsangbuk-do, KR (2019 - 2022)

Company Filing History:

goldMedal81 out of 162 
 
Stradvision, Inc.
 patents
silverMedal1 out of 1 
 
Stradivision, Inc.
 patent

Years Active: 2019-2022

Loading Chart...
Loading Chart...
Areas of Expertise:
Convolutional Neural Networks
Autonomous Vehicles
Object Detection
Deep Learning Optimization
Image Analysis
Continual Learning
Lane Departure Warning
Reinforcement Learning
Surveillance Systems
Hyperparameter Optimization
Pedestrian Detection
Multi-Camera Systems
82 patents (USPTO):Explore 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. 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),
4. 10984262 - Learning method and testing method for monitoring blind spot of vehicle, and learning device and testing device using the same (2021-04-20),
5. 10783438 - 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 (2020-09-22),
6. 10699192 - Method for optimizing hyperparameters of auto-labeling device which auto-labels training images for use in deep learning network to analyze images with high precision, and optimizing device using the same (2020-06-30),
7. 10692002 - Learning method and learning device of pedestrian detector for robust surveillance based on image analysis by using GAN and testing method and testing device using the same (2020-06-23),
8. 10635941 - Method and device for on-device continual learning of neural network which analyzes input data by optimized sampling of training images, and method and device for testing the neural network for smartphones, drones, vessels, or military purpose (2020-04-28),
9. 10621476 - Learning method and learning device for object detector based on reconfigurable network for optimizing customers' requirements such as key performance index using target object estimating network and target object merging network, and testing method and testing device using the same (2020-04-14),
10. 10592799 - Determining FL value by using weighted quantization loss values to thereby quantize CNN parameters and feature values to be used for optimizing hardware applicable to mobile devices or compact networks with high precision (2020-03-17),
11. 10579924 - Learning method, learning device with multi-feeding layers and testing method, testing device using the same (2020-03-03),
12. 10579907 - Method for automatically evaluating labeling reliability of training images for use in deep learning network to analyze images, and reliability-evaluating device using the same (2020-03-03),
13. 10565863 - Method and device for providing advanced pedestrian assistance system to protect pedestrian preoccupied with smartphone (2020-02-18),
14. 10565476 - Method and computing device for generating image data set for learning to be used for detection of obstruction in autonomous driving circumstances and learning method and learning device using the same (2020-02-18),
15. 10553118 - 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 (2020-02-04),

Title: Insu Kim: Innovating Hardware Optimization in CNN Learning and Testing

Introduction:

Meet Insu Kim, a remarkable inventor and researcher hailing from Gyeongsangbuk-do, KR. With a remarkable track record of 82 patents, Kim has made significant contributions to the field of hardware optimization in convolutional neural networks (CNN). This article will delve into his latest patents, career highlights, and noteworthy collaborations.

Latest Patents:

Insu Kim's recent patents showcase his expertise in hardware optimization and on-device continual learning of neural networks. One of his groundbreaking inventions includes a learning method and device for CNN, utilizing 1xK or Kx1 convolution to be used for hardware optimization. This method allows for the learning parameters of a CNN to be optimized for hardware, resulting in improved performance while satisfying key performance indicators (KPIs).

Another notable invention by Kim involves a method and device for on-device continual learning of a neural network. This method permits the analysis of input data and ensures continual learning for smartphones, drones, vessels, or military purposes. By employing generative adversarial networks (GANs) and online learning techniques, this patent assists in saving resources, preventing catastrophic forgetting, and maintaining data privacy.

Career Highlights:

Insu Kim's career has been marked by an exceptional drive for innovation and research. He has held positions in reputed companies such as StradVision, Inc., where he has undoubtedly made remarkable contributions to the field. His extensive experience and expertise in hardware optimization have earned him recognition within the industry.

Collaborations:

Throughout his journey, Insu Kim has had the pleasure of collaborating with numerous talented individuals. Notably, he has worked alongside Kye-Hyeon Kim and Yongjoong Kim, who have made significant contributions within the field. These collaborations have paved the way for groundbreaking inventions and advancements in hardware optimization, benefiting industries such as automotive, surveillance, and military.

Conclusion:

Insu Kim's contributions to hardware optimization in convolutional neural networks have undeniably made a profound impact on the field of artificial intelligence. His patents showcase his ingenuity, particularly in CNN learning and testing methods that prioritize hardware optimization while also considering crucial aspects like on-device continual learning. As technology continues to evolve, we can expect Insu Kim to thrive and continue shaping the future of AI applications.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…