Dr Mehmet Suzen MInstP

google scholar
Erdős number = 5

Equivalence in Deep Neural Networks via Conjugate Matrix Ensembles
arXiv:2006.13687 | deep_dyson_networks.ipynb
cascading Periodic Spectral Ergodicity (cPSE):
A complexity measure for connectionist machine learning
Manuscript arXiv:1911.07831
Available in Bristol Package v0.2.6 as a single function.
Development stage Python notebook on nbview
Featured as Applying Occam’s razor to Deep Learning
Generalised learning in time-series: reconstructive cross-validation (rCV)
Manuscript arXiv:1910.09394
Python notebook on nbview : Prototype implementation with Ornstein-Uhlenbeck processes
Presentation February 2020
Compressive transition path sampling: How to simulate rare event for longer time scales?
Manuscript: arXiv:1804.09781
Spectral ergodicity could explain deep learning.
Manuscript: arXiv:1704.08303
Software:
- Python Package Bristol Parallel Random Matrix Tools
Talks :
- Spectral ergodicity for explainable deep learning:A simulation approach
- Spectral Ergodicity in Deep Learning Architectures
Effective ergodicity in single-spin-flip dynamics
Phys. Rev. E 90, 032141 (2014) DOI: 10.1103/PhysRevE.90.032141
Mehmet Suezen

Induced Charge Computation, Ph.D. Dissertation, FIAS, Goethe University, Frankfurt/Main
Academic descendant of Carl Friedrich Gauss: math genealogy
Chaotic behaviour of geodesics, MSc Thesis in Theoretical Physics, Cyprus

Mentor Data Scientists and engineers: Machine learning and data mining projects.
Warwick/London/Cologne: 2015-16, 2018-2019, 2020
Mentor postdoc colleagues on compressed sensing algorithms.
Barcelona (ICFO), 2009-2010.
Onboard and provide initial guidance for postdoc colleagues on
induced charge computation algorithms and
ensemble equivalence in single molecule stretching.
Frankfurt am Main (FIAS) 2006-2009.
Supervise Computer Science undergraduate projects.
Network anomaly detection.
Cyprus, 2005.