Search Results for author: Roberto Santana

Found 19 papers, 2 papers with code

When and How to Fool Explainable Models (and Humans) with Adversarial Examples

no code implementations5 Jul 2021 Jon Vadillo, Roberto Santana, Jose A. Lozano

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations.

Redefining Neural Architecture Search of Heterogeneous Multi-Network Models by Characterizing Variation Operators and Model Components

no code implementations16 Jun 2021 Unai Garciarena, Roberto Santana, Alexander Mendiburu

In this paper, we investigate the effect of different variation operators in a complex domain, that of multi-network heterogeneous neural models.

Neural Architecture Search

On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future

no code implementations26 May 2021 Unai Garciarena, Nuno Lourenço, Penousal Machado, Roberto Santana, Alexander Mendiburu

Neuroevolutionary algorithms, automatic searches of neural network structures by means of evolutionary techniques, are computationally costly procedures.

Analysis of Dominant Classes in Universal Adversarial Perturbations

no code implementations28 Dec 2020 Jon Vadillo, Roberto Santana, Jose A. Lozano

The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion.

Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions

no code implementations14 Apr 2020 Jon Vadillo, Roberto Santana, Jose A. Lozano

Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet malicious perturbations to natural inputs.

Adversarial Attack

On the human evaluation of audio adversarial examples

no code implementations23 Jan 2020 Jon Vadillo, Roberto Santana

In this paper we investigate to which extent the distortion metrics proposed in the literature for audio adversarial examples, and which are commonly applied to evaluate the effectiveness of methods for generating these attacks, are a reliable measure of the human perception of the perturbations.

Universal adversarial examples in speech command classification

no code implementations22 Nov 2019 Jon Vadillo, Roberto Santana

Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human.

Classification General Classification

Evolving Gaussian Process kernels from elementary mathematical expressions

no code implementations11 Oct 2019 Ibai Roman, Roberto Santana, Alexander Mendiburu, Jose A. Lozano

Gaussian Process is a state-of-the-art technique for regression and classification that heavily relies on a kernel function.

Time Series

Sentiment analysis with genetically evolved Gaussian kernels

no code implementations1 Apr 2019 Ibai Roman, Alexander Mendiburu, Roberto Santana, Jose A. Lozano

Our results show that the algorithm can outperform Gaussian Processes with traditional kernels for some of the sentiment analysis tasks considered.

Gaussian Processes Sentiment Analysis

Towards automatic construction of multi-network models for heterogeneous multi-task learning

no code implementations21 Mar 2019 Unai Garciarena, Alexander Mendiburu, Roberto Santana

Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks.

Atari Games Multi-Task Learning

Expanding variational autoencoders for learning and exploiting latent representations in search distributions

no code implementations1 Jul 2018 Unai Garciarena, Roberto Santana, Alexander Mendiburu

In the past, evolutionary algorithms (EAs) that use probabilistic modeling of the best solutions incorporated latent or hidden vari- ables to the models as a more accurate way to represent the search distributions.

Gray-box optimization and factorized distribution algorithms: where two worlds collide

1 code implementation11 Jul 2017 Roberto Santana

To illustrate this claim, we present a contrasted analysis of formalisms, questions, and results produced in FDAs and gray-box optimization.

Reproducing and learning new algebraic operations on word embeddings using genetic programming

1 code implementation18 Feb 2017 Roberto Santana

We show that our method is able to reproduce the same behavior as human-designed algebraic operators.

Word Embeddings

Evolutionary Approaches to Optimization Problems in Chimera Topologies

no code implementations17 Aug 2016 Roberto Santana, Zheng Zhu, Helmut G. Katzgraber

In this paper we investigate for the first time the use of Evolutionary Algorithms (EAs) on Ising spin glass instances defined on the Chimera topology.

MOEA/D-GM: Using probabilistic graphical models in MOEA/D for solving combinatorial optimization problems

no code implementations18 Nov 2015 Murilo Zangari de Souza, Roberto Santana, Aurora Trinidad Ramirez Pozo, Alexander Mendiburu

Evolutionary algorithms based on modeling the statistical dependencies (interactions) between the variables have been proposed to solve a wide range of complex problems.

Combinatorial Optimization

A probabilistic evolutionary optimization approach to compute quasiparticle braids

no code implementations2 Oct 2014 Roberto Santana, Ross B. McDonald, Helmut G. Katzgraber

Topological quantum computing is an alternative framework for avoiding the quantum decoherence problem in quantum computation.

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