A complete theoretical understanding about why neural networks techniques are so successful when applied to physical systems and especially on determining phase transitions is still missing.
A possible starting point for a theoretical treatment suggests that deep learning is a form of coarse graining. On the other hand, in theoretical physics the notion of coarse graining is characterized by the renormalization group flow. We discuss the possibility of an underlying fundamental relation between certain machine learning methods and the renormalization group flow in theoretical physics. To do so we will be introducing the restricted Boltzmann machines and their training methods on lattice spin models.

While the neural networks have no direct knowledge about the Hamiltonian and the interactions of the physical models, we show that they identify spontaneously the critical regime of the lattice spin models. We discuss this behavior in the context of Renormalization Group Flow and thermodynamics.

Dimitris is working in the field of theoretical (high energy) physics. He is Columbus fellow assistant professor in the Physics department of National Sun Yat-sen University and center scientist of the National Center for Theoretical Sciences in Taiwan. His main research interests include the study of Strongly Coupled Systems, the Gauge/Gravity duality, Gravity, Quantum Field Theory and Chaos.

In the past, he has been affiliated with the IAS Durham University UK, the National Center for Theoretical Sciences (Tsinghua University), TW; the University of Oxford UK; the National Technical and the university of Athens; the Witwatersrand University SA. His PhD was on topics of gauge/gravity duality at Durham University, UK 

 
About the EuroCC-2 project

EuroCC 2 will work to identify and address the skills gaps in the European High Performance Computing (HPC) ecosystem and coordinate cooperation across Europe to ensure a consistent skills base.

The role of EuroCC 2 is to establish and run a network of more than 30 NCCs across the EuroHPC Participating States. The NCCs act as single points of access in each country between stakeholders and national and EuroHPC systems. They operate on a regional and national level to liaise with local communities, in particular SMEs, map HPC competencies and facilitate access to European HPC resources for users from the private and public sector.

EuroCC 2 delivers training, interacts with industry, develops competence mapping and communication materials and activities, and supports the adoption of HPC services in other related fields, such as quantum computing, artificial intelligence (AI), high performance data analytics (HPDA) to expand the HPC user base.

This project has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101101903. The JU receives support from the European Union’s programme Digital Europe and Germany, Bulgaria, Austria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, Greece, Hungary, Ireland, Italy, Lithuania, Latvia, Poland, Portugal, Romania, Slovenia, Spain, Sweden, France, Netherlands, Belgium, Luxembourg , Slovakia, Norway, Switzerland, Turkey, the Republic of North Macedonia, Iceland, Montenegro and Serbia.