dc.contributorGiraldo Gallo, José Jairo
dc.contributorSeoane Bartolomé, Beatriz
dc.creatorNavas Gómez, Alfonso de Jesús
dc.date.accessioned2023-02-15T15:50:31Z
dc.date.available2023-02-15T15:50:31Z
dc.date.created2023-02-15T15:50:31Z
dc.date.issued2022-11-15
dc.identifierhttps://repositorio.unal.edu.co/handle/unal/83483
dc.identifierUniversidad Nacional de Colombia
dc.identifierRepositorio Institucional Universidad Nacional de Colombia
dc.identifierhttps://repositorio.unal.edu.co/
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)
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.
dc.languageeng
dc.publisherUniversidad Nacional de Colombia
dc.publisherBogotá - Ciencias - Maestría en Ciencias - Física
dc.publisherFacultad de Ciencias
dc.publisherBogotá, Colombia
dc.publisherUniversidad Nacional de Colombia - Sede Bogotá
dc.relationD. H. Ackley, G. E. Hinton, and T. J. Sejnowski. A learning algorithm for boltzmann machines. Cognitive science, 9(1):147–169, 1985.
dc.relationD. J. Amit and V. Martin-Mayor. Field theory, the renormalization group, and critical phenomena: graphs to computers. World Scientific Publishing Company, 2005.
dc.relationA. Bakk and J. S. Høye. One-dimensional ising model applied to protein folding. Physica A: Statistical Mechanics and its Applications, 323:504–518, 2003.
dc.relationH. Ballesteros and V. Martín-Mayor. Test for random number generators: Schwinger-Dyson equations for the ising model. Physical Review E, 58(5):6787, 1998.
dc.relationS. 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.
dc.relationN. Béreux, A. Decelle, C. Furtlehner, and B. Seoane. Learning a restricted Boltzmann machine using biased Monte Carlo sampling. arXiv preprint arXiv:2206.01310, 2022.
dc.relationC. M. Bishop. Pattern Recognition and Machine Learning. Springer, New York, 2006.
dc.relationB. 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.
dc.relationL. Brocchieri and S. Karlin. Protein length in eukaryotic and prokaryotic proteomes. Nucleic acids research, 33(10):3390–3400, 2005.
dc.relationG. 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.
dc.relationA. Decelle. TorchRBM. https://github.com/AurelienDecelle/TorchRBM, 2021. Accessed: 20-07-2022.
dc.relationA. Decelle and C. Furtlehner. Restricted Boltzmann machine: Recent advances and mean-field theory. Chinese Physics B, 30(4):040202, 2021.
dc.relationA. Decelle, C. Furtlehner, and B. Seoane. Equilibrium and non-equilibrium regimes in the learning of restricted boltzmann machines. arXiv preprint arXiv:2105.13889, 2021.
dc.relationA. Fischer and C. Igel. An introduction to restricted boltzmann machines. In Iberoamerican congress on pattern recognition, pages 14–36. Springer, 2012.
dc.relationM. 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.
dc.relationW. K. Hastings. Monte carlo sampling methods using markov chains and their applications. Biometrika, 57(1):97–109, 1953.
dc.relationT. 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.
dc.relationG. E. Hinton. Training products of experts by minimizing contrastive divergence. Neural computation, 14(8):1771–1800, 2002.
dc.relationG. E. Hinton. A practical guide to training restricted Boltzmann machines. In Neural networks: Tricks of the trade, pages 599–619. Springer, 2012.
dc.relationG. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507, 2006.
dc.relationR. 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.
dc.relationN. Le Roux and Y. Bengio. Representational power of restricted Boltzmann machines and deep belief networks. Neural computation, 20(6):1631–1649, 2008.
dc.relationY. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
dc.relationP. 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.
dc.relationR. G. Melko, G. Carleo, J. Carrasquilla, and J. I. Cirac. Restricted boltzmann machines in quantum physics. Nature Physics, 15(9):887–892, 2019.
dc.relationN. 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.
dc.relationG. Montúfar. Restricted Boltzmann machines: Introduction and review. In Information Geometry and Its Applications IV, pages 75–115. Springer, 2016.
dc.relationF. 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.
dc.relationD. Sherrington and S. Kirkpatrick. Solvable model of a spin-glass. Physical review letters, 35(26):1792, 1975.
dc.relationD. 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.
dc.relationP. 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.
dc.relationT. 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.
dc.relationJ. Tubiana, S. Cocco, and R. Monasson. Learning protein constitutive motifs from sequence data. Elife, 8:e39397, 2019.
dc.relationG. Van Rossum and F. L. Drake Jr. Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam, 1995.
dc.relationU. Wolff. Collective Monte Carlo updating for spin systems. Physical Review Letters, 62(4):361, 1989.
dc.relationB. 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.
dc.rightsAtribución-NoComercial-SinDerivadas 4.0 Internacional
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rightsinfo:eu-repo/semantics/openAccess
dc.titleExploring in and out-of-equilibrium learning regimes of restricted Boltzmann machines
dc.typeTrabajo de grado - Maestría


Este ítem pertenece a la siguiente institución