Search Results for author: Fernando Perez-Cruz

Found 34 papers, 16 papers with code

Synthetic location trajectory generation using categorical diffusion models

1 code implementation19 Feb 2024 Simon Dirmeier, Ye Hong, Fernando Perez-Cruz

Diffusion probabilistic models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data, for instance, for computer vision, audio, natural language processing, or biomolecule generation.

Benchmarking Decision Making +1

Revealing behavioral impact on mobility prediction networks through causal interventions

no code implementations20 Nov 2023 Ye Hong, Yanan Xin, Simon Dirmeier, Fernando Perez-Cruz, Martin Raubal

Deep neural networks are increasingly utilized in mobility prediction tasks, yet their intricate internal workings pose challenges for interpretability, especially in comprehending how various aspects of mobility behavior affect predictions.

Causal Inference

Uncertainty quantification and out-of-distribution detection using surjective normalizing flows

1 code implementation1 Nov 2023 Simon Dirmeier, Ye Hong, Yanan Xin, Fernando Perez-Cruz

Reliable quantification of epistemic and aleatoric uncertainty is of crucial importance in applications where models are trained in one environment but applied to multiple different environments, often seen in real-world applications for example, in climate science or mobility analysis.

Out-of-Distribution Detection Uncertainty Quantification

Diffusion models for probabilistic programming

1 code implementation1 Nov 2023 Simon Dirmeier, Fernando Perez-Cruz

We propose Diffusion Model Variational Inference (DMVI), a novel method for automated approximate inference in probabilistic programming languages (PPLs).

Probabilistic Programming Variational Inference

Simulation-based inference using surjective sequential neural likelihood estimation

1 code implementation2 Aug 2023 Simon Dirmeier, Carlo Albert, Fernando Perez-Cruz

We present Surjective Sequential Neural Likelihood (SSNL) estimation, a novel method for simulation-based inference in models where the evaluation of the likelihood function is not tractable and only a simulator that can generate synthetic data is available.

Bayesian Inference Variational Inference

Adaptive Annealed Importance Sampling with Constant Rate Progress

1 code implementation27 Jun 2023 Shirin Goshtasbpour, Victor Cohen, Fernando Perez-Cruz

This algorithm relies on a sequence of interpolating distributions bridging the target to an initial tractable distribution such as the well-known geometric mean path of unnormalized distributions which is assumed to be suboptimal in general.

PassGPT: Password Modeling and (Guided) Generation with Large Language Models

1 code implementation2 Jun 2023 Javier Rando, Fernando Perez-Cruz, Briland Hitaj

Large language models (LLMs) successfully model natural language from vast amounts of text without the need for explicit supervision.

Forecasting Particle Accelerator Interruptions Using Logistic LASSO Regression

no code implementations15 Mar 2023 Sichen Li, Jochem Snuverink, Fernando Perez-Cruz, Andreas Adelmann

Unforeseen particle accelerator interruptions, also known as interlocks, lead to abrupt operational changes despite being necessary safety measures.

Binary Classification regression

Vision Paper: Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysis

no code implementations18 Oct 2022 Yanan Xin, Natasa Tagasovska, Fernando Perez-Cruz, Martin Raubal

Particularly, the transportation sector would benefit from the progress in AI and advance the development of intelligent transportation systems.

Causal Inference

Optimization of Annealed Importance Sampling Hyperparameters

1 code implementation27 Sep 2022 Shirin Goshtasbpour, Fernando Perez-Cruz

Annealed Importance Sampling (AIS) is a popular algorithm used to estimates the intractable marginal likelihood of deep generative models.

Facilitated machine learning for image-based fruit quality assessment

1 code implementation10 Jul 2022 Manuel Knott, Fernando Perez-Cruz, Thijs Defraeye

Image-based machine learning models can be used to make the sorting and grading of agricultural products more efficient.

BIG-bench Machine Learning Classification +2

OADAT: Experimental and Synthetic Clinical Optoacoustic Data for Standardized Image Processing

1 code implementation17 Jun 2022 Firat Ozdemir, Berkan Lafci, Xosé Luís Deán-Ben, Daniel Razansky, Fernando Perez-Cruz

However, no standardized datasets generated with different types of experimental set-up and associated processing methods are available to facilitate advances in broader applications of OA in clinical settings.

Image Reconstruction Image-to-Image Translation +1

What You See is What You Classify: Black Box Attributions

1 code implementation23 May 2022 Steven Stalder, Nathanaël Perraudin, Radhakrishna Achanta, Fernando Perez-Cruz, Michele Volpi

These attributions are provided in the form of masks that only show the classifier-relevant parts of an image, masking out the rest.

Learning Summary Statistics for Bayesian Inference with Autoencoders

1 code implementation28 Jan 2022 Carlo Albert, Simone Ulzega, Firat Ozdemir, Fernando Perez-Cruz, Antonietta Mira

For stochastic models with intractable likelihood functions, approximate Bayesian computation offers a way of approximating the true posterior through repeated comparisons of observations with simulated model outputs in terms of a small set of summary statistics.

Bayesian Inference

FedComm: Federated Learning as a Medium for Covert Communication

no code implementations21 Jan 2022 Dorjan Hitaj, Giulio Pagnotta, Briland Hitaj, Fernando Perez-Cruz, Luigi V. Mancini

Proposed as a solution to mitigate the privacy implications related to the adoption of deep learning, Federated Learning (FL) enables large numbers of participants to successfully train deep neural networks without having to reveal the actual private training data.

Federated Learning

Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network

1 code implementation27 Sep 2021 Michael Stalder, Firat Ozdemir, Artur Safin, Jonas Sukys, Damien Bouffard, Fernando Perez-Cruz

Nowadays physical models are developed to estimate lake dynamics; however, computations needed for accurate estimation of lake surface temperature can get prohibitively expensive.

A data acquisition setup for data driven acoustic design

no code implementations24 Sep 2021 Romana Rust, Achilleas Xydis, Kurt Heutschi, Nathanaël Perraudin, Gonzalo Casas, Chaoyu Du, Jürgen Strauss, Kurt Eggenschwiler, Fernando Perez-Cruz, Fabio Gramazio, Matthias Kohler

In this paper, we present the automated data acquisition setup, the data processing and the computational generation of diffusive surface structures.

A Novel Approach for Classification and Forecasting of Time Series in Particle Accelerators

no code implementations1 Feb 2021 Sichen Li, Mélissa Zacharias, Jochem Snuverink, Jaime Coello de Portugal, Fernando Perez-Cruz, Davide Reggiani, Andreas Adelmann

The beam interruptions (interlocks) of particle accelerators, despite being necessary safety measures, lead to abrupt operational changes and a substantial loss of beam time.

Binary Classification Classification +5

Improved BiGAN training with marginal likelihood equalization

1 code implementation4 Nov 2019 Pablo Sánchez-Martín, Pablo M. Olmos, Fernando Perez-Cruz

We propose a novel training procedure for improving the performance of generative adversarial networks (GANs), especially to bidirectional GANs.

Probabilistic Time of Arrival Localization

no code implementations15 Oct 2019 Fernando Perez-Cruz, Pablo M. Olmos, Michael Minyi Zhang, Howard Huang

In this paper, we take a new approach for time of arrival geo-localization.

Infinite Factorial Finite State Machine for Blind Multiuser Channel Estimation

no code implementations18 Oct 2018 Francisco J. R. Ruiz, Isabel Valera, Lennart Svensson, Fernando Perez-Cruz

New communication standards need to deal with machine-to-machine communications, in which users may start or stop transmitting at any time in an asynchronous manner.

Sparse Three-parameter Restricted Indian Buffet Process for Understanding International Trade

no code implementations29 Jun 2018 Melanie F. Pradier, Viktor Stojkoski, Zoran Utkovski, Ljupco Kocarev, Fernando Perez-Cruz

This paper presents a Bayesian nonparametric latent feature model specially suitable for exploratory analysis of high-dimensional count data.

WHAT ARE GANS USEFUL FOR?

no code implementations ICLR 2018 Pablo M. Olmos, Briland Hitaj, Paolo Gasti, Giuseppe Ateniese, Fernando Perez-Cruz

In this paper, we noticed that even though GANs might not be able to generate samples from the underlying distribution (or we cannot tell at least), they are capturing some structure of the data in that high dimensional space.

Density Estimation

PassGAN: A Deep Learning Approach for Password Guessing

3 code implementations1 Sep 2017 Briland Hitaj, Paolo Gasti, Giuseppe Ateniese, Fernando Perez-Cruz

State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes.

BIG-bench Machine Learning Generative Adversarial Network

Accelerated Parallel Non-conjugate Sampling for Bayesian Non-parametric Models

no code implementations19 May 2017 Michael Minyi Zhang, Sinead A. Williamson, Fernando Perez-Cruz

First, we introduce an accelerated feature proposal mechanism that we show is a valid MCMC algorithm for posterior inference.

Bayesian Inference valid

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning

1 code implementation24 Feb 2017 Briland Hitaj, Giuseppe Ateniese, Fernando Perez-Cruz

Unfortunately, we show that any privacy-preserving collaborative deep learning is susceptible to a powerful attack that we devise in this paper.

Federated Learning Generative Adversarial Network +1

Infinite Factorial Dynamical Model

1 code implementation NeurIPS 2015 Isabel Valera, Francisco Ruiz, Lennart Svensson, Fernando Perez-Cruz

We propose the infinite factorial dynamic model (iFDM), a general Bayesian nonparametric model for source separation.

Deep Learning for Multi-label Classification

no code implementations17 Dec 2014 Jesse Read, Fernando Perez-Cruz

In multi-label classification, the main focus has been to develop ways of learning the underlying dependencies between labels, and to take advantage of this at classification time.

Classification General Classification +1

Bayesian Nonparametric Crowdsourcing

no code implementations18 Jul 2014 Pablo G. Moreno, Yee Whye Teh, Fernando Perez-Cruz, Antonio Artés-Rodríguez

Crowdsourcing has been proven to be an effective and efficient tool to annotate large datasets.

Active Learning

Bayesian nonparametric comorbidity analysis of psychiatric disorders

no code implementations29 Jan 2014 Francisco J. R. Ruiz, Isabel Valera, Carlos Blanco, Fernando Perez-Cruz

To this end, we use the large amount of information collected in the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC) database and propose to model these data using a nonparametric latent model based on the Indian Buffet Process (IBP).

Variational Inference

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