Naima Chouikhi

Papers

Total Citations

H-Index

About

Naima Chouikhi is a leading researcher in the field of computational intelligence, with a primary focus on recurrent neural networks (RNNs) and their applications in robotics and control systems. Her most cited work, "Learning to Walk Using a Recurrent Neural Network with Time Delay" (2013), has garnered 15 citations and represents a significant contribution to the development of biologically inspired locomotion in autonomous systems. In this study, Chouikhi demonstrated how time-delayed RNNs can effectively model complex motor patterns, enabling robots to learn stable walking gaits through adaptive feedback mechanisms. This work bridges the gap between neural network theory and practical robotics, offering a robust framework for real-time learning in dynamic environments. Chouikhi's research has implications for rehabilitation robotics, prosthetics, and human-robot interaction, where adaptive movement control is critical. Her contributions are recognized for advancing the understanding of how temporal dependencies in neural networks can be harnessed for motor learning, making her a notable figure in the intersection of artificial intelligence and robotics.