skip to content

Assistant Professor in Data Intensive Science in DAMTP and the IoA, working on AI for scientific discovery.

Research: Google Scholar

Group page: astroautomata.com



[quanta magazine]

 

Publications

Rediscovering orbital mechanics with machine learning
P Lemos, N Jeffrey, M Cranmer, S Ho, P Battaglia
(2022)
LEARNED COARSE MODELS FOR EFFICIENT TURBULENCE SIMULATION
K Stachenfeld, DB Fielding, D Kochkov, M Cranmer, T Pfaff, J Godwin, C Cui, S Ho, P Battaglia, A Sanchez-Gonzalez
– Iclr 2022 10th International Conference on Learning Representations
(2022)
A Bayesian neural network predicts the dissolution of compact planetary systems.
M Cranmer, D Tamayo, H Rein, P Battaglia, S Hadden, PJ Armitage, S Ho, DN Spergel
– Proceedings of the National Academy of Sciences
(2021)
118,
e2026053118
A Deep-learning Approach for Live Anomaly Detection of Extragalactic Transients
VA Villar, M Cranmer, E Berger, G Contardo, S Ho, G Hosseinzadeh, JY-Y Lin
– The Astrophysical Journal Supplement Series
(2021)
255,
24
Unsupervised Resource Allocation with Graph Neural Networks
M Cranmer, P Melchior, B Nord
(2021)
Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network
A Oladosu, T Xu, P Ekfeldt, BA Kelly, M Cranmer, S Ho, AM Price-Whelan, G Contardo
(2021)
A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
VA Villar, M Cranmer, E Berger, G Contardo, S Ho, G Hosseinzadeh, JY-Y Lin
(2021)
A Bayesian neural network predicts the dissolution of compact planetary systems
M Cranmer, D Tamayo, H Rein, P Battaglia, S Hadden, PJ Armitage, S Ho, DN Spergel
(2021)
Unsupervised Resource Allocation with Graph Neural Networks
M Cranmer, P Melchior, B Nord
– Proceedings of Machine Learning Research
(2021)
148,
272
Discovering Symbolic Models from Deep Learning with Inductive Biases
M Cranmer, A Sanchez-Gonzalez, P Battaglia, R Xu, K Cranmer, D Spergel, S Ho
(2020)
  • <
  • 8 of 10
  • >

Research Group

Relativity and Gravitation

Room

B2.17