Files

TFM_Amir_Azzam.pdf (3.37 MB)

Document type

Master thesis

Publication date

2023-07

Publication license

cc-by-nc-nd (c) Azan, 2023
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/202717

Transfer Learning For Many-Body Systems

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

Abstract

We study the ground-state properties of fully-polarized, trapped, one-dimensional fermions interacting through a Gaussian potential using a variational wavefunction represented by an antisymmetric artificial neural network. We optimize the network parameters by minimizing the energy of a four-particle system with machine learning techniques. We introduce several methods to enhance the efficiency, accuracy, and scalability of the artificial neural network approach. We use Early Stopping to terminate the training when the energy converges. We apply Transfer Learning to pre-train the network with different interactions or particle numbers to reduce the memory cost and improve the performance. We employ a re-weighting scheme to speed up the Metropolis- Hastings sampling for estimating the energy expectation value. We show that, in particular, this re-weighting scheme can speed up the training time by up to a factor of 10.

Description

Màster Oficial de Ciència i Tecnologia Quàntiques / Quantum Science and Technology, Facultat de Física, Universitat de Barcelona. Curs: 2022-2023. Tutors: A. Rios, J. Rozalén

Subject

Xarxa neuronal artificial, Estats quàntics de xarxa neuronal, Aprenentatge per transferència, Treballs de fi de màster

Subject (English)

Artificial neural network, Neural network quantum states, Transfer learning, Master's thesis

Citation

Collections

Màster Oficial - Ciència i Tecnologia Quàntiques / Quantum Science and Technology

Citation

AZZAM, Amir. Transfer Learning For Many-Body Systems. [consulted: 16 of June of 2026]. Available at: https://hdl.handle.net/2445/202717

Export metadata

JSON - METS

Share record