Search Results for author: Pavlos Protopapas

Found 48 papers, 21 papers with code

Gravitational Duals from Equations of State

no code implementations21 Mar 2024 Yago Bea, Raul Jimenez, David Mateos, Shuheng Liu, Pavlos Protopapas, Pedro Tarancón-Álvarez, Pablo Tejerina-Pérez

Under this map, the equation of state of the field theory is encoded in the black hole solutions of the gravitational theory.

Generating Images of the M87* Black Hole Using GANs

1 code implementation2 Dec 2023 Arya Mohan, Pavlos Protopapas, Keerthi Kunnumkai, Cecilia Garraffo, Lindy Blackburn, Koushik Chatterjee, Sheperd S. Doeleman, Razieh Emami, Christian M. Fromm, Yosuke Mizuno, Angelo Ricarte

To validate the effectiveness of our approach, we employ a convolutional neural network to predict the BH spin using both the GRMHD images and the images generated by our proposed model.

Data Augmentation Image Generation

One-Shot Transfer Learning for Nonlinear ODEs

no code implementations25 Nov 2023 Wanzhou Lei, Pavlos Protopapas, Joy Parikh

We introduce a generalizable approach that combines perturbation method and one-shot transfer learning to solve nonlinear ODEs with a single polynomial term, using Physics-Informed Neural Networks (PINNs).

Transfer Learning

Improving astroBERT using Semantic Textual Similarity

no code implementations29 Nov 2022 Felix Grezes, Thomas Allen, Sergi Blanco-Cuaresma, Alberto Accomazzi, Michael J. Kurtz, Golnaz Shapurian, Edwin Henneken, Carolyn S. Grant, Donna M. Thompson, Timothy W. Hostetler, Matthew R. Templeton, Kelly E. Lockhart, Shinyi Chen, Jennifer Koch, Taylor Jacovich, Pavlos Protopapas

The NASA Astrophysics Data System (ADS) is an essential tool for researchers that allows them to explore the astronomy and astrophysics scientific literature, but it has yet to exploit recent advances in natural language processing.

Astronomy Language Modelling +1

Transfer Learning with Physics-Informed Neural Networks for Efficient Simulation of Branched Flows

1 code implementation1 Nov 2022 Raphaël Pellegrin, Blake Bullwinkel, Marios Mattheakis, Pavlos Protopapas

Physics-Informed Neural Networks (PINNs) offer a promising approach to solving differential equations and, more generally, to applying deep learning to problems in the physical sciences.

Transfer Learning

DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks

1 code implementation15 Sep 2022 Blake Bullwinkel, Dylan Randle, Pavlos Protopapas, David Sondak

Solutions to differential equations are of significant scientific and engineering relevance.

RcTorch: a PyTorch Reservoir Computing Package with Automated Hyper-Parameter Optimization

1 code implementation12 Jul 2022 Hayden Joy, Marios Mattheakis, Pavlos Protopapas

However, RC adoption has lagged other neural network models because of the model's sensitivity to its hyper-parameters (HPs).

Evaluating Error Bound for Physics-Informed Neural Networks on Linear Dynamical Systems

no code implementations3 Jul 2022 Shuheng Liu, Xiyue Huang, Pavlos Protopapas

This paper shows that one can mathematically derive explicit error bounds for physics-informed neural networks trained on a class of linear systems of differential equations.

Improving Astronomical Time-series Classification via Data Augmentation with Generative Adversarial Networks

no code implementations13 May 2022 Germán García-Jara, Pavlos Protopapas, Pablo A. Estévez

Due to the latest advances in technology, telescopes with significant sky coverage will produce millions of astronomical alerts per night that must be classified both rapidly and automatically.

Data Augmentation Time Series +2

Physics-Informed Neural Networks for Quantum Eigenvalue Problems

no code implementations24 Feb 2022 Henry Jin, Marios Mattheakis, Pavlos Protopapas

We expand on the method of using unsupervised neural networks for discovering eigenfunctions and eigenvalues for differential eigenvalue problems.

Building astroBERT, a language model for Astronomy & Astrophysics

no code implementations1 Dec 2021 Felix Grezes, Sergi Blanco-Cuaresma, Alberto Accomazzi, Michael J. Kurtz, Golnaz Shapurian, Edwin Henneken, Carolyn S. Grant, Donna M. Thompson, Roman Chyla, Stephen McDonald, Timothy W. Hostetler, Matthew R. Templeton, Kelly E. Lockhart, Nemanja Martinovic, Shinyi Chen, Chris Tanner, Pavlos Protopapas

The existing search tools for exploring the NASA Astrophysics Data System (ADS) can be quite rich and empowering (e. g., similar and trending operators), but researchers are not yet allowed to fully leverage semantic search.

Astronomy Language Modelling +3

Uncertainty Quantification in Neural Differential Equations

no code implementations NeurIPS Workshop DLDE 2021 Olga Graf, Pablo Flores, Pavlos Protopapas, Karim Pichara

Uncertainty quantification (UQ) helps to make trustworthy predictions based on collected observations and uncertain domain knowledge.

Uncertainty Quantification

One-Shot Transfer Learning of Physics-Informed Neural Networks

1 code implementation21 Oct 2021 Shaan Desai, Marios Mattheakis, Hayden Joy, Pavlos Protopapas, Stephen Roberts

In this study, we present a general framework for transfer learning PINNs that results in one-shot inference for linear systems of both ordinary and partial differential equations.

Transfer Learning

Unsupervised Reservoir Computing for Solving Ordinary Differential Equations

1 code implementation25 Aug 2021 Marios Mattheakis, Hayden Joy, Pavlos Protopapas

A closed-form formula for the optimal output weights is derived to solve first order linear equations in a backpropagation-free learning process.

Bayesian Optimization

Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems

1 code implementation16 Jul 2021 Shaan Desai, Marios Mattheakis, David Sondak, Pavlos Protopapas, Stephen Roberts

In this study, we address the challenge of learning from such non-autonomous systems by embedding the port-Hamiltonian formalism into neural networks, a versatile framework that can capture energy dissipation and time-dependent control forces.

Encoding Involutory Invariances in Neural Networks

no code implementations7 Jun 2021 Anwesh Bhattacharya, Marios Mattheakis, Pavlos Protopapas

In certain situations, neural networks are trained upon data that obey underlying symmetries.

A New Artificial Neuron Proposal with Trainable Simultaneous Local and Global Activation Function

no code implementations15 Jan 2021 Tiago A. E. Ferreira, Marios Mattheakis, Pavlos Protopapas

The proposed neuron was tested for problems where the target was a purely global function, or purely local function, or a composition of two global and local functions.

Semi-supervised Neural Networks solve an inverse problem for modeling Covid-19 spread

1 code implementation10 Oct 2020 Alessandro Paticchio, Tommaso Scarlatti, Marios Mattheakis, Pavlos Protopapas, Marco Brambilla

Studying the dynamics of COVID-19 is of paramount importance to understanding the efficiency of restrictive measures and develop strategies to defend against upcoming contagion waves.

Unsupervised Neural Networks for Quantum Eigenvalue Problems

no code implementations10 Oct 2020 Henry Jin, Marios Mattheakis, Pavlos Protopapas

Eigenvalue problems are critical to several fields of science and engineering.

MPCC: Matching Priors and Conditionals for Clustering

1 code implementation ECCV 2020 Nicolás Astorga, Pablo Huijse, Pavlos Protopapas, Pablo Estévez

Our experiments show that adding a learnable prior and augmenting the number of encoder updates improve the quality of the generated samples, obtaining an inception score of 9. 49 $\pm$ 0. 15 and improving the Fr\'echet inception distance over the state of the art by a 46. 9% in CIFAR10.

Clustering Decoder

Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks

1 code implementation21 Jul 2020 Dylan Randle, Pavlos Protopapas, David Sondak

This work develops a novel method for solving differential equations with unsupervised neural networks that applies Generative Adversarial Networks (GANs) to \emph{learn the loss function} for optimizing the neural network.

Gender Classification and Bias Mitigation in Facial Images

1 code implementation13 Jul 2020 Wenying Wu, Pavlos Protopapas, Zheng Yang, Panagiotis Michalatos

We worked to increase classification accuracy and mitigate algorithmic biases on our baseline model trained on the augmented benchmark database.

Classification Gender Classification +1

Solving Differential Equations Using Neural Network Solution Bundles

no code implementations17 Jun 2020 Cedric Flamant, Pavlos Protopapas, David Sondak

The time evolution of dynamical systems is frequently described by ordinary differential equations (ODEs), which must be solved for given initial conditions.

Bayesian Inference

Application of Machine Learning to Predict the Risk of Alzheimer's Disease: An Accurate and Practical Solution for Early Diagnostics

no code implementations2 Jun 2020 Courtney Cochrane, David Castineira, Nisreen Shiban, Pavlos Protopapas

This paper proposes a machine learning predictive model for AD development without medical imaging and with fewer clinical visits and tests, in hopes of earlier and cheaper diagnoses.

BIG-bench Machine Learning feature selection

Scalable End-to-end Recurrent Neural Network for Variable star classification

1 code implementation3 Feb 2020 Ignacio Becker, Karim Pichara, Márcio Catelan, Pavlos Protopapas, Carlos Aguirre, Fatemeh Nikzat

Our method uses minimal data preprocessing, can be updated with a low computational cost for new observations and light curves, and can scale up to massive datasets.

Classification Classification Of Variable Stars +1

Streaming Classification of Variable Stars

1 code implementation4 Dec 2019 Lukas Zorich, Karim Pichara, Pavlos Protopapas

Naively re-training from scratch is not an option in streaming settings, mainly because of the expensive pre-processing routines required to obtain a vector representation of light curves (features) each time we include new observations.

BIG-bench Machine Learning Classification +2

An Information Theory Approach on Deciding Spectroscopic Follow Ups

1 code implementation6 Nov 2019 Javiera Astudillo, Pavlos Protopapas, Karim Pichara, Pablo Huijse

We propose a methodology in a probabilistic setting that determines a-priory which objects are worth taking spectrum to obtain better insights, where we focus 'insight' as the type of the object (classification).

General Classification Time Series +1

Matching Embeddings for Domain Adaptation

no code implementations25 Sep 2019 Manuel Pérez-Carrasco, Guillermo Cabrera-Vives, Pavlos Protopapas, Nicolás Astorga, Marouan Belhaj

In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled target domain.

Domain Adaptation Semi-supervised Domain Adaptation

Improving Image Classification Robustness through Selective CNN-Filters Fine-Tuning

no code implementations8 Apr 2019 Alessandro Bianchi, Moreno Raimondo Vendra, Pavlos Protopapas, Marco Brambilla

To solve this issue, we propose a transfer learning approach optimized to keep into account that in each layer of a CNN some filters are more susceptible to image distortion than others.

Classification General Classification +2

Efficient Optimization of Echo State Networks for Time Series Datasets

2 code implementations12 Mar 2019 Jacob Reinier Maat, Nikos Gianniotis, Pavlos Protopapas

Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains.

Astronomy Bayesian Optimization +2

Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models

no code implementations7 Dec 2018 Marouan Belhaj, Pavlos Protopapas, Weiwei Pan

Thanks to the combination of a semi-supervised ELBO and parameters sharing across domains, we are able to simultaneously: (i) align all supervised examples of the same class into the same latent Gaussian Mixture component, independently from their domain; (ii) predict the class of unsupervised examples from different domains and use them to better model the occurring shifts.

General Classification Transfer Learning

T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling

2 code implementations20 Nov 2018 Giorgia Ramponi, Pavlos Protopapas, Marco Brambilla, Ryan Janssen

Results show that classifiers trained on T-CGAN-generated data perform the same as classifiers trained on real data, even with very short time series and small training sets.

Data Augmentation Generative Adversarial Network +2

Robust period estimation using mutual information for multi-band light curves in the synoptic survey era

2 code implementations11 Sep 2017 Pablo Huijse, Pablo A. Estevez, Francisco Forster, Scott F. Daniel, Andrew J. Connolly, Pavlos Protopapas, Rodrigo Carrasco, Jose C. Principe

Robust and efficient methods that can aggregate data from multidimensional sparsely-sampled time series are needed.

Instrumentation and Methods for Astrophysics Information Theory Information Theory

Clustering Based Feature Learning on Variable Stars

1 code implementation29 Feb 2016 Cristóbal Mackenzie, Karim Pichara, Pavlos Protopapas

Representatives of these patterns, called exemplars, are then used to transform lightcurves of a labeled set into a new representation that can then be used to train an automatic classifier.

Classification Of Variable Stars Clustering +2

Fast and optimal nonparametric sequential design for astronomical observations

no code implementations11 Jan 2015 Justin J. Yang, Xufei Wang, Pavlos Protopapas, Luke Bornn

The spectral energy distribution (SED) is a relatively easy way for astronomers to distinguish between different astronomical objects such as galaxies, black holes, and stellar objects.

Astronomy Experimental Design

Supervised detection of anomalous light-curves in massive astronomical catalogs

no code implementations18 Apr 2014 Isadora Nun, Karim Pichara, Pavlos Protopapas, Dae-Won Kim

With the aim of taking full advantage of all the information we have about known objects, our method is based on a supervised algorithm.

An improved quasar detection method in EROS-2 and MACHO LMC datasets

no code implementations1 Apr 2013 Karim Pichara, Pavlos Protopapas, Dae-Won Kim, Jean-Baptiste Marquette, Patrick Tisserand

We present a new classification method for quasar identification in the EROS-2 and MACHO datasets based on a boosted version of Random Forest classifier.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.