Menachem Stern
Papers
2
Total Citations
31
H-Index
2
About
Menachem Stern is pioneering the next frontier of machine learning by moving beyond traditional digital processors. His core research lies at the intersection of physics, nonlinear dynamics, and artificial intelligence, where he designs physical learning systems—specifically, "learning metamaterials" and analog networks that can learn without a central processor. Stern’s major contribution is the demonstration of emergent learning in nonlinear electronic networks, showing that physical systems can be trained to perform tasks through local, contrastive learning rules rather than power-hungry backpropagation. His most cited work, "Machine learning without a processor: Emergent learning in a nonlinear analog network" (2024, 29 citations), and its predecessor (2023) lay the groundwork for fast, fault-tolerant, and energy-efficient hardware for AI. By proving that a nonlinear electronic metamaterial can learn autonomously, Stern challenges the conventional separation between computation and physical substrate, opening the door to embedded, adaptive intelligence in materials. His work is a critical step toward neuromorphic computing and self-learning physical systems, with profound implications for low-power edge AI and autonomous devices.
Research Focus
Key Achievements
Top Papers
- 1
- 2