Exploring in and out-of-equilibrium learning regimes of restricted Boltzmann machines

dc.contributor.advisorGiraldo Gallo, José Jairo
dc.contributor.advisorSeoane Bartolomé, Beatriz
dc.contributor.authorNavas Gómez, Alfonso de Jesús
dc.date.accessioned2023-02-15T15:50:31Z
dc.date.available2023-02-15T15:50:31Z
dc.date.issued2022-11-15
dc.descriptionilustracionesspa
dc.description.abstractAunque los métodos de inteligencia artificial basados en aprendizaje automatizado son considerados como una de las tecnologías disruptivas de nuestros tiempos, el entendimiento de estas herramientas yace muy por detrás de su éxito práctico. La física estadística de sistemas desordenados goza de una larga historia estudiando problemas de inferencia y aprendizaje usando sus propias herramientas. Siguiendo con esta tradición, en este trabajo final de maestría se estudió cómo el protocolo de aprendizaje afecta a los patrones extraídos por una Máquina Restringida de Boltzmann. En particular, se entrenaron máquinas dentro y fuera del equilibrio con muestras del modelo de Ising en 1 y 2 dimensiones para luego, usando un nuevo método de inferencia, extraer la matriz de acoplamientos del modelo efectivo aprendido en cada caso. Este experimento permitió dilucidar algunas consecuencias de los regímenes de entrenamiento dentro y fuera de equilibrio. Adicionalmente, se exploró el potencial del uso de las Máquinas Restringidas de Boltzmann para la extracción automática de patrones para muestras similares a las del modelo de Ising, siendo este el primer paso para abordar problemas más complejos. (Texto tomado de la fuente)spa
dc.description.abstractAlthough machine learning based artificial intelligence is considered as one of the most disruptive technologies of our age, the understanding of many of these methods lies behind their practical success. Statistical physics of disordered systems has a long history studying inference problems and learning processes with its own tools, shedding light on the underlying mechanisms of many machine learning models. Following this tradition, in this master's thesis we studied how the training protocol affects the model and the features extracted by an unsupervised machine learning method called Restricted Boltzmann Machine. In particular, we trained machines in and out-of-equilibrium learning regimes with Ising Model samples and then, using a novel pattern extraction protocol developed in this work, we inferred the coupling matrix of the effective Ising model learned in each case. Such experiment allowed us to elucidate some consequences of equilibrium and non-equilibrium training regimes. Additionally, we explored the potential use of restricted Boltzmann machine as an inference tool for Ising model-like sample data, being the first step towards to tackle more complex problems.eng
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ciencias - Físicaspa
dc.format.extent39 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/83483
dc.language.isoengspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.facultyFacultad de Cienciasspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Ciencias - Maestría en Ciencias - Físicaspa
dc.relation.referencesD. H. Ackley, G. E. Hinton, and T. J. Sejnowski. A learning algorithm for boltzmann machines. Cognitive science, 9(1):147–169, 1985.spa
dc.relation.referencesD. J. Amit and V. Martin-Mayor. Field theory, the renormalization group, and critical phenomena: graphs to computers. World Scientific Publishing Company, 2005.spa
dc.relation.referencesA. Bakk and J. S. Høye. One-dimensional ising model applied to protein folding. Physica A: Statistical Mechanics and its Applications, 323:504–518, 2003.spa
dc.relation.referencesH. Ballesteros and V. Martín-Mayor. Test for random number generators: Schwinger-Dyson equations for the ising model. Physical Review E, 58(5):6787, 1998.spa
dc.relation.referencesS. Behnel, R. Bradshaw, C. Citro, L. Dalcin, D. S. Seljebotn, and K. Smith. Cython: The best of both worlds. Computing in Science & Engineering, 13(2):31–39, 2011.spa
dc.relation.referencesN. Béreux, A. Decelle, C. Furtlehner, and B. Seoane. Learning a restricted Boltzmann machine using biased Monte Carlo sampling. arXiv preprint arXiv:2206.01310, 2022.spa
dc.relation.referencesC. M. Bishop. Pattern Recognition and Machine Learning. Springer, New York, 2006.spa
dc.relation.referencesB. Bravi, J. Tubiana, S. Cocco, R. Monasson, T. Mora, and A. M. Walczak. Rbm-mhc: A semi-supervised machine-learning method for sample-specific prediction of antigen presentation by hla-i alleles. Cell systems, 12(2):195–202, 2021.spa
dc.relation.referencesL. Brocchieri and S. Karlin. Protein length in eukaryotic and prokaryotic proteomes. Nucleic acids research, 33(10):3390–3400, 2005.spa
dc.relation.referencesG. Cossu, L. Del Debbio, T. Giani, A. Khamseh, and M. Wilson. Machine learning determination of dynamical parameters: The ising model case. Physical Review B, 100(6):064304, 2019.spa
dc.relation.referencesA. Decelle. TorchRBM. https://github.com/AurelienDecelle/TorchRBM, 2021. Accessed: 20-07-2022.spa
dc.relation.referencesA. Decelle and C. Furtlehner. Restricted Boltzmann machine: Recent advances and mean-field theory. Chinese Physics B, 30(4):040202, 2021.spa
dc.relation.referencesA. Decelle, C. Furtlehner, and B. Seoane. Equilibrium and non-equilibrium regimes in the learning of restricted boltzmann machines. arXiv preprint arXiv:2105.13889, 2021.spa
dc.relation.referencesA. Fischer and C. Igel. An introduction to restricted boltzmann machines. In Iberoamerican congress on pattern recognition, pages 14–36. Springer, 2012.spa
dc.relation.referencesM. Harsh, J. Tubiana, S. Cocco, and R. Monasson. ‘place-cell’ emergence and learning of invariant data with restricted boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space. Journal of Physics A: Mathematical and Theoretical, 53(17):174002, 2020.spa
dc.relation.referencesW. K. Hastings. Monte carlo sampling methods using markov chains and their applications. Biometrika, 57(1):97–109, 1953.spa
dc.relation.referencesT. L. Hill. Generalization of the one-dimensional Ising model applicable to helix transitions in nucleic acids and proteins. The Journal of Chemical Physics, 30(2):383–387, 1959.spa
dc.relation.referencesG. E. Hinton. Training products of experts by minimizing contrastive divergence. Neural computation, 14(8):1771–1800, 2002.spa
dc.relation.referencesG. E. Hinton. A practical guide to training restricted Boltzmann machines. In Neural networks: Tricks of the trade, pages 599–619. Springer, 2012.spa
dc.relation.referencesG. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507, 2006.spa
dc.relation.referencesR. D. Hjelm, V. D. Calhoun, R. Salakhutdinov, E. A. Allen, T. Adali, and S. M. Plis. Restricted boltzmann machines for neuroimaging: an application in identifying intrinsic networks. NeuroImage, 96:245–260, 2014.spa
dc.relation.referencesN. Le Roux and Y. Bengio. Representational power of restricted Boltzmann machines and deep belief networks. Neural computation, 20(6):1631–1649, 2008.spa
dc.relation.referencesY. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.spa
dc.relation.referencesP. Mehta, M. Bukov, C.-H. Wang, A. G. Day, C. Richardson, C. K. Fisher, and D. J. Schwab. A high-bias, low-variance introduction to machine learning for physicists. Physics reports, 810:1–124, 2019.spa
dc.relation.referencesR. G. Melko, G. Carleo, J. Carrasquilla, and J. I. Cirac. Restricted boltzmann machines in quantum physics. Nature Physics, 15(9):887–892, 2019.spa
dc.relation.referencesN. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller, and E. Teller. Equation of state calculations by fast computing machines. The journal of chemical physics, 21(6):1087–1092, 1953.spa
dc.relation.referencesG. Montúfar. Restricted Boltzmann machines: Introduction and review. In Information Geometry and Its Applications IV, pages 75–115. Springer, 2016.spa
dc.relation.referencesF. Ricci-Tersenghi. The Bethe approximation for solving the inverse Ising problem: a comparison with other inference methods. Journal of Statistical Mechanics: Theory and Experiment, 2012(08):P08015, 2012.spa
dc.relation.referencesD. Sherrington and S. Kirkpatrick. Solvable model of a spin-glass. Physical review letters, 35(26):1792, 1975.spa
dc.relation.referencesD. Silver, T. Hubert, J. Schrittwieser, I. Antonoglou, M. Lai, A. Guez, M. Lanctot, L. Sifre, D. Kumaran, T. Graepel, et al. A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science, 362(6419):1140–1144, 2018.spa
dc.relation.referencesP. Smolensky. Information processing in dynamical systems: Foundations of harmony theory. In D. E. Rumelhart and J. L. McLelland, editors, Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations, chapter 6, pages 194–281. MIT Press, Cambridge, 1986.spa
dc.relation.referencesT. Tieleman. Training restricted boltzmann machines using approximations to the likelihood gradient. In Proceedings of the 25th international conference on Machine learning, pages 1064–1071, 2008.spa
dc.relation.referencesJ. Tubiana, S. Cocco, and R. Monasson. Learning protein constitutive motifs from sequence data. Elife, 8:e39397, 2019.spa
dc.relation.referencesG. Van Rossum and F. L. Drake Jr. Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam, 1995.spa
dc.relation.referencesU. Wolff. Collective Monte Carlo updating for spin systems. Physical Review Letters, 62(4):361, 1989.spa
dc.relation.referencesB. Yelmen, A. Decelle, L. Ongaro, D. Marnetto, C. Tallec, F. Montinaro, C. Furtlehner, L. Pagani, and F. Jay. Creating artificial human genomes using generative neural networks. PLoS genetics, 17(2):e1009303, 2021.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/spa
dc.subject.lembComplejidad computacionalspa
dc.subject.lembComputational complexityeng
dc.subject.lembSistemas expertosspa
dc.subject.proposalInteligencia artificialspa
dc.subject.proposalAprendizaje automatizadospa
dc.subject.proposalFísica estadística de sistemas desordenadosspa
dc.subject.proposalMáquinas de Boltzmann restringidasspa
dc.subject.proposalMétodos de Monte-Carlospa
dc.subject.proposalArtificial intelligenceeng
dc.subject.proposalStatistical physics of disordered systemseng
dc.subject.proposalRestricted Boltzmann machineseng
dc.subject.proposalMonte-Carlo methodseng
dc.subject.proposalMachine learningeng
dc.titleExploring in and out-of-equilibrium learning regimes of restricted Boltzmann machineseng
dc.title.translatedExplorando los regímenes de aprendizaje dentro y fuera del equilibrio de las máquinas de Boltzmann restringidas
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1032483566.2022.pdf
Tamaño:
891.28 KB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ciencias - Física

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: