Evaluación de nuevas arquitecturas de IA para la estimación de la incertidumbre

Vista sencilla de ítem
dc.contributor.authorPautsch, Erik
dc.contributor.authorLi, John
dc.contributor.authorRizzi, Silvio
dc.contributor.authorThiruvathukal, George K.
dc.contributor.authorPantoja, Maria
dc.contributor.orcidPautsch, Erik [0000-0003-0028-5598]spa
dc.contributor.orcidLi, John [0000-0002-3730-3713]spa
dc.contributor.orcidRizzi, Silvio [0000-0002-3804-2471]spa
dc.contributor.orcidThiruvathukal, George K. [0000-0002-0452-5571]spa
dc.contributor.orcidPantoja, Maria [0000-0002-1942-9769]spa
dc.date.accessioned2025-02-13T21:03:20Z
dc.date.available2025-02-13T21:03:20Z
dc.date.issued2024-06-18
dc.description.abstractEl Aprendizaje Profundo (AP) ha hecho avanzar la visión por ordenador, ofreciendo un rendimiento impresionante en tareas visuales complejas. Sin embargo, persiste la necesidad de estimaciones precisas de la incertidumbre, en particular para las entradas fuera de distribución (OOD, en su acrónimo en inglés). Nuestra investigación evalúa la incertidumbre en Redes Neuronales Convolucionales (CNN, en inglés) y transformadores de visión (ViT, en inglés) utilizando los conjuntos de datos MNIST e ImageNet-1K. Utilizando plataformas de Alto Rendimiento (HPC, en inglés), incluidos el superordenador tradicional Polaris y aceleradores de IA como Cerebras CS-2 y SambaNova DataScale, evaluamos los méritos computacionales y los cuellos de botella de cada plataforma. En este artículo se describen las consideraciones clave para utilizar la HPC en la estimación de la incertidumbre en el AP, y se ofrecen ideas que guían la integración de algoritmos y hardware para aplicaciones de AP robustas, especialmente en visión por ordenador.spa
dc.description.abstractenglishDeep Learning (DL) has advanced computer vision, delivering impressive performance on intricate visual tasks. Yet, the need for accurate uncertainty estimations, particularly for out-of-distribution (OOD) inputs, persists. Our research evaluates uncertainty in Convolutional Neural Networks (CNN) and Vision Transformers (ViT) using the MNIST and ImageNet-1K datasets. Using High-Performance (HPC) platforms, including the traditional Polaris supercomputer and AI accelerators like Cerebras CS-2 and SambaNova DataScale, we assessed the computational merits and bottlenecks of each platform. This paper delineates key considerations for using HPC in uncertainty estimations in DL, offering insights that guide the integration of algorithms and hardware for robust DL applications, especially in computer vision.eng
dc.format.mimetypeapplication/pdfspa
dc.identifier.doihttps://doi.org/10.29375/25392115.5274
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga UNABspa
dc.identifier.issn1657-2831spa
dc.identifier.issn2539-2115
dc.identifier.repourlrepourl:https://repository.unab.edu.cospa
dc.identifier.urihttp://hdl.handle.net/20.500.12749/28291
dc.language.isospaspa
dc.publisherUniversidad Autónoma de Bucaramanga UNABspa
dc.relationhttps://revistas.unab.edu.co/index.php/rcc/article/view/5274/4084spa
dc.relation.referencesAmini, A., Schwarting, W., & Rus, D. (2020, December 6). Deep evidential regression. In H. Larochelle, M. Ranzato, R. T. Hadsell, M. F. Balcan, & H. Lin (Eds.), NIPS'20: 34th International Conference on Neural Information Processing Systems, Vancouver BC, Canada, December 6-12, (pp. 14927-14937, Article 1251). Red Hook, NY, USA: Curran Associates Inc. doi:10.5555/3495724.3496975
dc.relation.referencesANL. (2021, August 26). Polaris. (Argonne National Laboratory) Retrieved July 2023, from ANL website: https://www.alcf.anl.gov/polaris
dc.relation.referencesBojarski, M., Yeres, P., Choromanska, A., Choromanski, K., Firner, B., Jackel, L., & Muller, U. (2017, April 25). Explaining how a deep neural network trained with end-to-end learning steers a car. arXiv:1704.07911v1 [cs.CV], 1-8. doi:10.48550/arXiv.1704.07911
dc.relation.referencesCordonnier, J.-B., Loukas, A., & Jaggi, M. (2020). On the relationship between selfattention and convolutional layers. Eighth International Conference on Learning Representations - ICLR 2020, April 26-30. Addis Ababa. Retrieved from https://infoscience.epfl.ch/entities/publication/48815b9c-e947-4c4d-84fa-7ebf1f6df4dd/conferencedetails
dc.relation.referencesDeng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Li, F.-F. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, 20-25 June (pp. 248-255). Miami, FL, USA: IEEE. doi:10.1109/CVPR.2009.5206848
dc.relation.referencesEmani, M., Vishwanath, V., Adams, C., Papka, M. E., Stevens, R., Florescu, L., . . . Sujeeth, A. (2021, March 26). Accelerating scientific applications with sambanova reconfigurable dataflow architecture. Computing in Science & Engineering, 23(2), 114–119. doi:10.1109/MCSE.2021.3057203
dc.relation.referencesGal, Y., & Ghahramani, Z. (2016, June). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In M. F. Balcan, & K. Q. Weinberger (Ed.), Proceedings of The 33rd International Conference on Machine Learning. 48, pp. 1050-1059. New York, New York, USA (20–22 Jun 2016): PMLR. Retrieved from https://proceedings.mlr.press/v48/gal16.html
dc.relation.referencesGeifman, Y., & El-Yaniv, R. (2017, December 4). Selective classification for deep neural networks. In U. von Luxburg, I. M. Guyon, S. Bengio, H. M. Wallach, & R. Fergus (Eds.), NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA, December 4 - 9, 2017 (pp. 4885-4894). Red Hook, NY, USA: Curran Associates Inc. doi:10.5555/3295222.3295241
dc.relation.referencesGuo, C., Pleiss, G., Sun, Y., & Weinber, K. Q. (2017). On calibration of modern neural networks. In D. Precup, & Y. W. Teh (Ed.), Proceedings of the 34th International Conference on Machine Learning. 70, pp. 1321-1330. PMLR. Retrieved from https://proceedings.mlr.press/v70/guo17a.html
dc.relation.referencesHendrycks, D., Liu, X., Wallace, E., Dziedzic, A., Krishnan, R., & Song, D. (2020, July). Pretrained transformers improve out-of-distribution robustness. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault (Eds.), Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 2744–2751). Online: Association for Computational Linguistics. doi:10.18653/v1/2020.acl-main.244
dc.relation.referencesLecun, Y., Jackel, L. D., Bottou, L., Cortes, C., Denker, J. S., Drucker, H., . . . Vapnik, V. (1995). Learning algorithms for classification: A comparison on handwritten digit recognition. In J. H. Oh, C. Kwon, & S. Cho (Eds.), Learning algorithms for classification: A comparison on handwritten digit recognition (pp. 261-276). World Scientific. Retrieved from https://nyuscholars.nyu.edu/en/publications/learning-algorithms-for-classification-a-comparison-on-handwritte
dc.relation.referencesLie, S. (2022). Cerebras architecture deep dive: First look inside the hw/sw co-design for deep learning. In 2022 IEEE Hot Chips 34 Symposium (HCS), 21-23 August (pp. 1–34). Cupertino, CA, USA: IEEE. doi:10.1109/HCS55958.2022.9895479
dc.relation.referencesLiu, Y., & Guo, H. (2020, July 13). Peer loss functions: Learning from noisy labels without knowing noise rates. In H. C. Daumé, & A. Singh (Eds.), ICML'20: International Conference on Machine LearningJuly 13 - 18 (Vols. 119, Article 578, pp. 6226–6236). JMLR.org.
dc.relation.referencesMacDonald, S., Foley, H., Yap, M., Johnston, R. L., Steven, K., Koufariotis, L. T., . . . Trzaskowski, M. (2023, May 6). Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology. Scientific Reports, 13, 7395. doi:10.1038/s41598-023-31126-5
dc.relation.referencesOvadia, Y., Fertig, E., Ren, J., Nado, Z., Sculley, D., Nowozin, S., . . . Snoek, J. (2019). Can you trust your model's uncertainty? evaluating predictive uncertainty under dataset shift. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, & R. Garnett (Eds.), Advances in Neural Information Processing Systems (Vol. 32). Red Hook, NY, USA: Curran Associates Inc. Retrieved from https://proceedings.neurips.cc/paper_files/paper/2019/file/8558cb408c1d76621371888657d2eb1d-Paper.pdf
dc.relation.referencesRen, A. Z., Dixit, A., Bodrova, A., Singh, S., Tu, S., Brown, N., . . . Majumdar, A. (2023, September 4). Robots that ask for help: Uncertainty alignment for large language model planners. arXiv:2307.01928v2 [cs.RO], 1-24. doi:10.48550/arXiv.2307.01928
dc.relation.referencesTamkin, A., Nguyen, D., Deshpande, S., Mu, J., & Goodman, N. (2022). Active learning helps pretrained models learn the intended task. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Advances in Neural Information Processing Systems (Vol. 35, pp. 28140-28153). Curran Associates Inc. Retrieved from
dc.relation.urihttps://revistas.unab.edu.co/index.php/rcc/issue/view/303spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.sourceVol. 25 Núm. 2 (2024): Revista Colombiana de Computación (Julio-Diciembre); 23-34spa
dc.subjectIncertidumbrespa
dc.subjectAprendizaje Profundospa
dc.subjectAprendizaje por conjuntosspa
dc.subjectAprendizaje evidencialspa
dc.subjectInteligencia Artificialspa
dc.subject.keywordsUncertaintyeng
dc.subject.keywordsDeep Learningeng
dc.subject.keywordsEnsembleseng
dc.subject.keywordsEvidential Learningeng
dc.subject.keywordsArtificial intelligenceeng
dc.titleEvaluación de nuevas arquitecturas de IA para la estimación de la incertidumbrespa
dc.title.translatedEvaluation of Novel AI Architectures for Uncertainty Estimationeng
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.driverinfo:eu-repo/semantics/article
dc.type.hasversioninfo:eu-repo/semantics/publishedVersion
dc.type.localArtículospa
dc.type.redcolhttp://purl.org/redcol/resource_type/ART

Archivos

Bloque original

Mostrando 1 - 1 de 1
Miniatura
Nombre:
Articulo 3.pdf
Tamaño:
799.26 KB
Formato:
Adobe Portable Document Format
Descripción:
Artículo
Descargar

Bloque de licencias

Mostrando 1 - 1 de 1
Miniatura
Nombre:
license.txt
Tamaño:
347 B
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Revista Colombiana de Computación