Hector Carreon-Ortiz
Papers
1
Total Citations
7
H-Index
1
About
Héctor Carreón-Ortiz is a researcher specializing in computational intelligence, neural network optimization, and time series prediction. His work focuses on addressing critical challenges in deploying recurrent neural networks (RNNs) on embedded devices, particularly the high computational cost and memory demands that limit their practical application. Carreón-Ortiz’s most notable contribution is the development of a novel optimization algorithm inspired by mycorrhiza—the symbiotic fungal networks in nature—to efficiently design and train nonlinear autoregressive neural networks. His 2023 paper on this topic, which has already garnered 7 citations, demonstrates how his discrete mycorrhiza optimization algorithm can significantly enhance the architecture of RNNs for tasks like Mackey-Glass time series prediction, a benchmark problem in chaotic systems. By reducing computational overhead while maintaining predictive accuracy, his work paves the way for more efficient AI systems in resource-constrained environments. Carreón-Ortiz’s research bridges the gap between bio-inspired optimization and practical neural network deployment, offering tangible solutions for real-world applications in embedded systems and edge computing.
Research Focus
Key Achievements
Top Papers
- 1