Taehee Kim
Papers
2
Total Citations
14
H-Index
2
About
Taehee Kim is a pioneering researcher in neural network structural learning and intelligent robotic sensing. His most notable contribution is the development of the **Augmentation by Training with Residuals (ATR)** algorithm, a fully automatic feedforward neural network learning method that eliminates the need for users to guess initial weight values or the number of hidden-layer neurons. By taking an incremental approach, ATR autonomously determines network architecture and weights, representing a significant advance in making neural networks more accessible and efficient. This foundational work, published in 1995, has garnered **11 citations** and remains influential in the field of structural learning. Kim also explored tactile sensing for robotics, authoring a 1996 study on **PVDF tactile dynamic sensing** in behavior-based assembly robots, which contributed to the integration of sensory feedback in autonomous systems. His research bridges theoretical algorithm design with practical robotic applications, offering tools that simplify complex neural network training while enhancing robot-environment interaction. Kim’s work continues to inspire researchers seeking automated, user-friendly approaches to machine learning and intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2