Fredrik Sandin

Research

Machine learning and neuromorphic computing, with a special interest for industrial challenges requiring embedded intelligence solutions. See my scholar profile for references.

I have a PhD in Physics (2007, Swedish Graduate School of Space Technology) and I did a postdoc at IFPA in Belgium (2008-09), both focusing on numerical simulations and modelling in theoretical physics. I did the MSc diploma work in ATLAS at CERN (2001). My curiosity for brains, neuromorphic engineering and the physics of consciousness made me shift research focus. I did a second postdoc in brain-inspired machine learning (2010-11) at EISLAB, where I presently work and are involved in the AI Innovation Hub.

NCE focus issue: applications of neuromorphic engineering to wireless networks for distributed sensing.

Teaching

I am the examiner of the following courses:

• Neural Networks and Learning Machines (D7046E), link.
• Neuromorphic Computing, upcoming course in the Applied AI program.

Since 2014, I coordinate the Engineering Physics and Electrical Engineering program at LTU (Civilingenjör, 300 credits). In the past I was the examiner for E0003E Electric circuit theory, D0011E Digital design, D0017E Introduction to programming for engineers. Before 2010 I taught several courses in physics.

Supervision

Current PhD students

• Jacob Nilsson, machine learning for M2M interoperability in the Arrowhead Framework.
• Mattias Nilsson, architecture for low-power pattern recognition with DYNAP neuromorphic system.
• Karl Ekström, natural language processing for fault severity estimation, KnowIT FAST.
• Kim Albertsson (CERN), machine learning in high-energy physics.
• Rickard Brännvall (RISE), machine learning for automation of datacenters, AutoDC.
• Co-supervision of Gustav Grund Pihlgren, Saleha Javed, Carl Borngrund, Lars-Johan Sandström, and Muhammad Ahmer (SKF).

Past Postdocs

• Sergio Martin del Campo Barraza, machine learning for automation of wind turbine condition monitoring system.

Graduated PhD students

• Siddharth Dadhich, Automation of Wheel-Loaders, link (co-supervisor).
• Sergio Martin del Campo Barraza, Unsupervised feature learning applied to condition monitoring, link.
• Blerim Emruli, Ubiquitous Cognitive Computing: A Vector Symbolic Approach, link.

Other

Some code and tools. Contact me if you are interested in code used in research articles that is not listed below.

• 3FCS code, link. This code was developed and used for the quark matter calculations in the papers about neutron stars with quark matter cores and related phase diagrams, including my most cited paper in Phys. Rev. D.
• Femtolensing tool, link. Calculates the gravitational lensing signatures of low-mass (10¹⁴-10¹⁷ kg) compact interstellar objects. This code was developed when working on the preon star hypothesis, see highlights below.
• N-dimensional random projection code, link. Result of early work on representation learning for cognitive computing.
• CBVS code, link. Early work on cognitive computing.
• Dircheck, link. A useful tool for verification of large file archives.
• Python code for distributed computing over ssh, link.
• ASOUND Matlab plugin, link.
• Online collaborative writing in Latex, link. Developed before the time of Sharelatex, Overleaf etc.

Some highlights

• Gunnar Öquist Fellow award, link.
• Dark matter neutron-star core hypothesis. Paper, paper, impact.
• ISSP award for an original work in theoretical physics, link (more about Prof. 't Hooft and Prof. Zichichi).
• Preon star hypothesis. Paper, paper, observational predictions, Nature news, Phys. Rev. Focus, New Scientist.