G.G. Lendaris
Papers
1
Total Citations
47
H-Index
1
About
G.G. Lendaris is a pioneering figure in computational intelligence, with a career spanning neural networks, adaptive systems, and optimization theory. His most-cited work, "Linear Hopfield networks and constrained optimization" (1999, 47 citations), introduced a groundbreaking method for solving linear equations by augmenting Hopfield networks with feedforward layers to compute the Moore-Penrose generalized inverse. This contribution bridged neural computation and linear algebra, offering a powerful tool for constrained optimization problems. Beyond this, Lendaris has made significant contributions to reinforcement learning, system identification, and adaptive control, often integrating neural network architectures with dynamic programming. His research has influenced fields from robotics to signal processing, with his papers collectively garnering hundreds of citations. A professor emeritus at Portland State University, Lendaris is also recognized for his work on fuzzy logic and intelligent control systems, and he has been a key figure in advancing the practical application of neural networks in engineering. His legacy lies in his ability to fuse theoretical rigor with real-world problem-solving, inspiring students and researchers to explore the intersection of machine learning and optimization.
Research Focus
Key Achievements
Top Papers
- 1Linear Hopfield networks and constrained optimization47 citations · 1999