Vladimir Cherkassky
Papers
1
Total Citations
2
H-Index
1
About
Vladimir Cherkassky is a leading figure in machine learning and neural networks, best known for his foundational work in learning theory and statistical data modeling. His research spans the development of robust learning algorithms, including support vector machines and regularization networks, with a particular focus on bridging theoretical principles with practical applications in engineering and science. Cherkassky’s most influential contributions include pioneering the use of neural networks for solving the inverse kinematic problem in robotics, as demonstrated in his 1989 paper (2 citations), which laid early groundwork for integrating neural processing with robotic control. His broader impact is reflected in his highly cited work on the Vapnik-Chervonenkis (VC) theory, where he helped popularize and extend statistical learning concepts for real-world data analysis. With thousands of citations across his career, Cherkassky has shaped modern approaches to model selection, complexity control, and predictive modeling. He is also the author of the widely used textbook *Learning from Data*, which has educated generations of researchers. His achievements include numerous awards for teaching and research, cementing his legacy as a key architect of contemporary machine learning.
Research Focus
Key Achievements
Top Papers
- 1Solution to the inverse kinematic problem in robotics using neural network processing2 citations · 1989