Cherkassky
Papers
1
Total Citations
64
H-Index
1
About
Vladimir Cherkassky has made pioneering contributions at the intersection of neural networks, machine learning, and robotics. His early work on the inverse kinematic problem in robotics introduced a novel neural network approach using the Hopfield-Tank analog computation scheme, where neuron states represent joint velocities and connection weights are derived from the manipulator's Jacobian. This foundational 1989 paper, with 64 citations, demonstrated how neural processing could solve complex robotic control problems. Cherkassky's research spans learning theory, model complexity control, and statistical learning, with a particular focus on developing practical methodologies for empirical modeling. He is widely recognized for his work on Vapnik-Chervonenkis (VC) theory and its applications, as well as for his influential textbook "Learning from Data: Concepts, Theory, and Methods," which has become a standard reference in the field. His contributions have shaped modern understanding of bias-variance tradeoffs, regularization, and the fundamental principles of learning from data, cementing his reputation as a leading figure in computational intelligence and statistical learning theory.
Research Focus
Key Achievements
Top Papers
- 1