Anna Montesanto
Papers
1
Total Citations
9
H-Index
1
About
Anna Montesanto’s research lies at the intersection of neural computation and robotics, where she has pioneered the application of unsupervised learning models to autonomous systems. Her most-cited work, “Self-Organizing Maps versus Growing Neural Gas in a Robotic Application” (2003), provides a seminal comparative analysis of two foundational neural architectures—Kohonen’s Self-Organizing Maps and the Growing Neural Gas algorithm—within a real-world robotic context. This study, which has garnered 9 citations, systematically evaluates their performance in tasks such as sensorimotor mapping and adaptive control, establishing a critical framework for selecting topology-preserving networks in dynamic environments. Montesanto’s contributions are particularly notable for bridging theoretical neural network principles with practical robotic implementation, offering engineers clear guidance on algorithm trade-offs. Her work has influenced subsequent research in adaptive robotics and neural plasticity models, and she is recognized for advancing the understanding of how self-organizing systems can enable robots to learn from unstructured sensory data. Through her focused, application-driven approach, Montesanto continues to shape the design of more flexible and resilient autonomous agents.
Research Focus
Key Achievements
Top Papers
- 1Self-Organizing Maps versus Growing Neural Gas in a Robotic Application9 citations · 2003