arXiv subjects

Santiago Cortes

Publications and source records attributed to Santiago Cortes.

8 recordsLinked to original sources

arXiv2022

Masterful: A Training Platform for Computer Vision Models

Masterful is a software platform to train deep learning computer vision models. Data and model architecture are inputs to the platform, and the output is a trained model. The platform's primary goal is to maximize a trained model's accuracy, which it achieves through its regularization and semi-supervised learning implementations. The platform's secondary goal is to minimize the amount of manual experimentation typically required to tune training hyperparameters, which it achieves via multiple metalearning algorithms which are custom built to control the platform's regularization and semi-supervised learning implementations. The platform's tertiary goal is to minimize the computing resources required to train a model, which it achieves via another set of metalearning algorithms which are purpose built to control Tensorflow's optimization implementations. The platform builds on top of Tensorflow's data management, architecture, automatic differentiation, and optimization implementations.

cs.CV↗

arXiv2020

COVID-19 Emotion Monitoring as a Tool to Increase Preparedness for Disease Outbreaks in Developing Regions

The COVID-19 pandemic brought many challenges, from hospital-occupation management to lock-down mental-health repercussions such as anxiety or depression. In this work, we present a solution for the later problem by developing a Twitter emotion-monitor system based on a state-of-the-art natural-language processing model. The system monitors six different emotions on accounts in cities, as well as politicians and health-authorities Twitter accounts. With an anonymous use of the emotion monitor, health authorities and private health-insurance companies can develop strategies to tackle problems such as suicide and clinical depression. The model chosen for such a task is a Bidirectional-Encoder Representations from Transformers (BERT) pre-trained on a Spanish corpus (BETO). The model performed well on a validation dataset. The system is deployed online as part of a web application for simulation and data analysis of COVID-19, in Colombia, available at https://epidemiologia-matematica.org.

cs.CL↗

arXiv2020

Unsupervised learning for economic risk evaluation in the context of Covid-19 pandemic

Justifying draconian measures during the Covid-19 pandemic was difficult not only because of the restriction of individual rights, but also because of its economic impact. The objective of this work is to present a machine learning approach to identify regions that should implement similar health policies. For that end, we successfully developed a system that gives a notion of economic impact given the prediction of new incidental cases through unsupervised learning and time series forecasting. This system was built taking into account computational restrictions and low maintenance requirements in order to improve the system's resilience. Finally this system was deployed as part of a web application for simulation and data analysis of COVID-19, in Colombia, available at (https://covid19.dis.eafit.edu.co).

cs.LG↗

arXiv2018

Inertial Odometry on Handheld Smartphones

Building a complete inertial navigation system using the limited quality data provided by current smartphones has been regarded challenging, if not impossible. This paper shows that by careful crafting and accounting for the weak information in the sensor samples, smartphones are capable of pure inertial navigation. We present a probabilistic approach for orientation and use-case free inertial odometry, which is based on double-integrating rotated accelerations. The strength of the model is in learning additive and multiplicative IMU biases online. We are able to track the phone position, velocity, and pose in real-time and in a computationally lightweight fashion by solving the inference with an extended Kalman filter. The information fusion is completed with zero-velocity updates (if the phone remains stationary), altitude correction from barometric pressure readings (if available), and pseudo-updates constraining the momentary speed. We demonstrate our approach using an iPad and iPhone in several indoor dead-reckoning applications and in a measurement tool setup.

cs.CV↗

arXiv2018

PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation

This paper presents a novel method for visual-inertial odometry. The method is based on an information fusion framework employing low-cost IMU sensors and the monocular camera in a standard smartphone. We formulate a sequential inference scheme, where the IMU drives the dynamical model and the camera frames are used in coupling trailing sequences of augmented poses. The novelty in the model is in taking into account all the cross-terms in the updates, thus propagating the inter-connected uncertainties throughout the model. Stronger coupling between the inertial and visual data sources leads to robustness against occlusion and feature-poor environments. We demonstrate results on data collected with an iPhone and provide comparisons against the Tango device and using the EuRoC data set.

cs.CV↗

arXiv2016

Chiral Symmetry restoration from the hadronic regime

We discuss recent advances on QCD chiral symmetry restoration at finite temperature, within the theoretical framework of Effective Theories. $U(3)$ Ward Identities are derived between pseudoscalar susceptibilities and quark condensates, allowing to explain the behaviour of lattice meson screening masses. Unitarized interactions and the generated $f_0(500)$ thermal state are showed to play an essential role in the description of the transition through the scalar susceptibility

hep-ph↗

arXiv2016

Large-$N$ pion scattering at finite temperature: the $f_0(500)$ and chiral restoration

We consider the $O(N+1)/O(N)$ Non-Linear Sigma Model for large $N$ as an effective theory for low-energy QCD at finite temperature $T$, in the chiral limit. At $T=0$ this formulation provides a good description of scattering data in the scalar channel and generates dynamically the $f_0(500)$ pole, the pole position lying within experimental determinations. Previous $T=0$ results with this model are updated using newer analysis of pion scattering data. We calculate the pion scattering amplitude at finite $T$ and show that it satisfies exactly thermal unitarity, which had been assumed but not formally proven in previous works. We discuss the main differences with the $T=0$ result and we show that one can define a proper renormalization scheme with $T=0$ counterterms such that the renormalized amplitude can be chosen to depend only on a few parameters. Next, we analyze the behaviour of the $f_0(500)$ pole at finite $T$, which is consistent with chiral symmetry restoration when the scalar susceptibility is saturated by the $f_0(500)$ state, in a second-order transition scenario and in accordance with lattice and theoretical analysis.

hep-ph↗

arXiv2016

Large-$N$ Pion Scattering, Finite-Temperature Effects and the Relationship of the $f_{0}(500)$ with Chiral Symmetry Restoration

In this work, we review how the mass and the width of the $f_{0}(500)$ pole behave in a regime where temperature is below the critical chiral transition value. This is attained by considering a large-$N$ $O(N + 1)/O(N)$ invariant Non-Linear Sigma Model (NLSM) such that we can study the dynamical generation of a $f_{0}(500)$ resonance. Introducing thermal effects via the imaginary time formalism allows us to study the behavior of the pole and relate it to chiral restoration.

hep-ph↗