David Friedlander
Papers
1
Total Citations
3
H-Index
1
About
David Friedlander’s research lies at the intersection of robotics, cognitive science, and machine learning, with a particular focus on how autonomous systems can learn and categorize objects from their environments. His most cited work, “Induction of Prototypes in a Robotic Setting Using Local Search MDL” (2004), introduces a novel application of Minimum Description Length (MDL) principles to enable robots to form conceptual prototypes through local search. This approach not only advances robotic perception but also offers a computational model for understanding concept learning in biological systems. By grounding abstract learning frameworks in physical robotic interactions, Friedlander bridges theoretical machine learning with practical autonomy. Though his citation count is modest, his work is notable for its interdisciplinary ambition, connecting information theory, developmental psychology, and robotics. Friedlander’s contributions are particularly valuable for researchers exploring how machines can move beyond simple sensorimotor tasks toward higher-level cognitive functions like categorization and abstraction—a foundational step for more sophisticated human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1Induction of Prototypes in a Robotic Setting Using Local Search MDL3 citations · 2004