Adarsh K. Jeewajee

Papers

1

Total Citations

22

H-Index

1

About

Adarsh K. Jeewajee is a researcher whose work sits at the intersection of machine learning, spatial cognition, and structured computation. His most notable contribution, the 2019 paper "Graph Element Networks: adaptive, structured computation and memory" (22 citations), introduces a novel framework that adapts graph neural networks (GNNs) to model continuous spatial processes without requiring a predefined graph structure. Drawing inspiration from finite element analysis, Jeewajee’s approach assigns GNN nodes to spatial locations, enabling dynamic, memory-augmented computation that can reason about physical and abstract spaces. This work has been influential in advancing the use of neural networks for tasks involving spatial reasoning, such as robotics and physics simulation, where traditional grid-based methods fall short. By bridging graph-based learning with continuous domains, Jeewajee has opened new avenues for adaptive, structured AI systems. His research is particularly relevant for students and researchers exploring how neural networks can model real-world environments with flexibility and efficiency.

Research Focus

Key Achievements

1
H-Index
1
Papers
22
Total Citations
22
Avg Citations/Paper
🏆 Most Cited Paper
Graph Element Networks: adaptive, structured computation and memory
22 citations · 2019
📈 Most Prolific Year: 2019 (1 Papers)
🤝 Key Collaborators: 5

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 3 days ago