Publications

Google Scholar profile

Peer-reviewed articles

  1. C. Gerbelot, A. Karagulyan, S. Karp, K. Ravichandran, M. Stern, N. Srebro, “Applying statistical learning theory to deep learning“, J. Stat. Mech-Theory E. 10, 104003 (2024).
  2. L. E. Altman, M. Stern, A. J. Liu and D. J. Durian, “Experimental demonstration of coupled learning in elastic networks“, Phys. Rev. Applied 22, 012053 (2024).
  3. S. Dillavou, B. D. Beyer, M. Stern, M. Z. Miskin, A. J. Liu and D. J. Durian, “Machine learning without a processor: Emergent learning in a nonlinear analog network“, Proc. Natl. Acad. Sci. USA 121, 28 (2024).
  4. M. Stern, S. Dillavou, D. Jayaraman, D. J. Durian and A. J. Liu, “Training self-learning circuits for power-efficient solutions“, APL Mach. Learn. 2 016114 (2024).
  5. M. Stern, A. J. Liu and V. Balasubramanian, “Physical effects of learning“, Phys. Rev. E 109, 024311 (2024).
  6. Barat et. al., “Soft matter roadmap“, J. Phys. Materials 7, 012501 (2023).
  7. M. Stern, A. Murugan, “Learning without neurons in physical systems“, Annu. Rev. Condens. Matter Phys. 14, 417-441 (2023).
  8. C. Arinze, M. Stern, S. R. Nagel, A. Murugan, “Learning to self-fold at a bifurcation“, Phys. Rev. E 107, 025001 (2023).
  9. S. Dillavou, M. Stern, A. J. Liu and D. J. Durian, “Demonstration of decentralized, physics-driven learning“, Phys. Rev. Applied 18, 014040 (2022). -Editors’ Suggestion-
  10. M. Stern, S. Dillavou, M. Z. Miskin, D. J. Durian and A. J. Liu, “Physical learning beyond the quasistatic limit“, Phys. Rev. Research 4, L022037 (2022).
  11. J. F. Wycoff, S. Dillavou, M. Stern, A. J. Liu and D. J. Durian, “Desynchronous learning in a physics-driven learning network“, J. Chem. Phys. 156, 144903 (2022).
  12. M. Stern, D. Hexner, J. W. Rocks and A. J. Liu, “Supervised learning in physical networks: From machine learning to learning machines“, Phys. Rev. X 11, 021045 (2021).
  13. M. Stern, M.B. Pinson and A. Murugan, “Continual learning of multiple memories in mechanical networks“, Phys. Rev. X 10, 031044 (2020).
  14. M. Stern, C. Arinze, L. Perez, S. E. Palmer and A. Murugan, “Supervised learning through physical changes in a mechanical system“, Proc. Natl. Acad. Sci. USA 117, 26 (2020).
  15. M. Stern, V. Jayaram and A. Murugan, “Shaping the topology of folding pathways in mechanical systems“, Nat. Commun. 9, (1) 4303 (2018).
  16. M. Stern, M.B. Pinson and A. Murugan, “The complexity of folding self-folding origami“, Phys. Rev. X 7, 041070 (2017).
  17. M.B. Pinson*, M. Stern*, A.C. Ferrero, T. A. Witten, E. Chen and A. Murugan, “Self-folding origami at any energy scale“,  Nat. Commun. 8, 15477 (2017).
  18. M. H. K. Schaarsberg, I. R. Peters, M. Stern, K. Dodge, W. W. Zhang and H. M. Jaeger, “From splashing to bouncing: The influence of viscosity on the impact of suspension droplets on a solid surface“, Phys. Rev. E 93, 062609 (2016).

Conference papers

  1. M. Stern, S. Dillavou, M. Z. Miskin, D. J. Durian and A. J. Liu, “Contrastive power-efficient physical learning in resistor networks“, Workshop on Machine Learning with New Compute Paradigms (NeurIPS 2023), New Orelans, Louisiana, Unites States.
  2. S. Dillavou, B. Beyer, M. Stern, M. Z. Miskin, A. J. Liu and D. J. Durian, “Nonlinear classification without a processor“, Workshop on Machine Learning with New Compute Paradigms (NeurIPS 2023), New Orelans, Louisiana, Unites States.
  3. S. Dillavou, B. Beyer, M. Stern, M. Z. Miskin, A. J. Liu and D. J. Durian, “Circuits that train themselves: decentralized, physics-driven learning“, AI and Optical Data Sciences IV (SPIE 2023), San Francisco, California, United States.
  4. M. Stern, S. Dillavou, M. Z. Miskin, D. J. Durian and A. J. Liu, “Out of equilibrium learning dynamics in physical allosteric resistor networks“, Fourth Workshop on Machine Learning and the Physical Sciences (NeurIPS 2021), Vancouver, Canada.
  5. M. Stern, C. de Mulatier, P. Fleig and V. Balasubramanian, “Curious exploration in complex environments based on Hopfield networks“, Towards Curious Robots: Modern Approaches for Intrinsically Motivated Intelligent Behavior (ICRA 2021), Xi’an, China.
  6. M. Stern, D. Hexner, J. W. Rocks and A. J. Liu, “Flow networks as learning machines“, Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020), Vancouver, Canada.

Preprints

  1. M. Stern, M. Guzman, F. Martins, A. J. Liu and V. Balasubramanian, “Physical networks become what they learn“, arXiv:2406.09689.

Patents

  1. S. Dillavou, D. J. Durian, A. J. Liu, M. Stern, M. Z. Miskin, “Coupled networks for physics-based machine learning“, US20220383205A1 (Dec. 2022).

Recorded talks

 

Learning without neurons in physical systems – Soft, Living, Active and Adaptive Matter Seminar , February 12th, 2024

 

From machine learning to learning machines – Science on the rocks (IAC and ScienceAbroad), July 18th, 2020

 

Ph.D. defense – November 4th, 2019

 

Media coverage

 

Controlling AI’s Growing Energy Needs – Communications of the ACM (November 2024)

Training neural networks using physical equations of motion – PNAS Commentary (July 2024)

 

A First, physical system learns nonlinear tasks without a traditional computer processor – Penn Today (July 2024)

 

How to Make the Universe Think for Us – Quanta Magazine (May 2022)

 

Simple electrical circuit learns on its own-with no help from a computer – Science (March 2022)

A panel of resistors

 

Programming Matter to do a Computer’s Job – APS News (May 2021)

Researchers at the University of Pennsylvania have developed an electrical circuit that learned to identify different kinds of iris flowers.

 

Why Self-folding Objects Get Stuck – Futurity (January 2018)