Juan Mantilla
Papers
1
Total Citations
48
H-Index
1
About
Juan Mantilla is a leading researcher in computational intelligence and nonlinear system identification, with a focus on improving the efficiency of neural network models. His most-cited work, "Computational cost improvement of neural network models in black box nonlinear system identification" (2015, 48 citations), addresses a critical challenge in the field: reducing the computational burden of neural networks while maintaining their accuracy in modeling complex, nonlinear systems. Mantilla’s contributions are particularly valuable for applications in control systems, signal processing, and dynamic modeling, where real-time performance is essential. By developing novel algorithms that streamline neural network training and inference, he has enabled more practical deployment of these models in resource-constrained environments. His work has been widely recognized, with his 2015 paper serving as a foundational reference for researchers seeking to balance model complexity and computational efficiency. Mantilla’s research continues to influence the intersection of machine learning and system identification, making him a key figure in advancing black-box modeling techniques for real-world engineering challenges.
Research Focus
Key Achievements
Top Papers
- 1