Myles Kumaresan
Papers
1
Total Citations
2
H-Index
1
About
Myles Kumaresan is a pioneering figure in computational neuroscience and neural network modeling, best known for his foundational work on motor sequence learning. His most cited paper, "Generalisation and Extension of Motor Programs for a Sequential Recurrent Network" (1993), introduced a novel framework for how recurrent neural networks can encode, generalize, and extend motor programs—a concept that has influenced subsequent research in motor control and artificial intelligence. Though his citation count is modest, with this work garnering 2 citations, its conceptual significance lies in bridging cognitive psychology and neural computation, offering early insights into how sequential behaviors are learned and adapted. Kumaresan’s contributions are particularly notable for their focus on the generalization capabilities of recurrent architectures, a theme that has become central in modern deep learning. His work remains a touchstone for researchers exploring the intersection of sequence learning, motor control, and neural plasticity, demonstrating how even low-cited papers can seed enduring ideas in a rapidly evolving field.
Research Focus
Key Achievements
Top Papers
- 1