no code implementations • 20 Mar 2024 • Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska
The lack of transparency of Deep Neural Networks continues to be a limitation that severely undermines their reliability and usage in high-stakes applications.
no code implementations • 14 Mar 2024 • Imanol Echeverria, Maialen Murua, Roberto Santana
Recent advancements in the flexible job-shop scheduling problem (FJSSP) are primarily based on deep reinforcement learning (DRL) due to its ability to generate high-quality, real-time solutions.
no code implementations • 24 Oct 2023 • Imanol Echeverria, Maialen Murua, Roberto Santana
In scheduling problems common in the industry and various real-world scenarios, responding in real-time to disruptive events is essential.
no code implementations • 5 Mar 2023 • Roberto Santana, Ivan Hidalgo-Cenalmor, Unai Garciarena, Alexander Mendiburu, Jose Antonio Lozano
We assess the impact of these functions on semi-supervised problems with a varying amount of labeled instances.
no code implementations • 15 Feb 2023 • Andrea Bonfanti, Roberto Santana, Marco Ellero, Babak Gholami
Physics-Informed Neural Networks (PINNs) are Neural Network architectures trained to emulate solutions of differential equations without the necessity of solution data.
1 code implementation • 5 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.
no code implementations • 16 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.
no code implementations • 26 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.
no code implementations • 28 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.
1 code implementation • 14 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.
no code implementations • 23 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.
no code implementations • 22 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.
no code implementations • 11 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.
no code implementations • 1 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.
no code implementations • 21 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.
no code implementations • 1 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.
no code implementations • 13 Jan 2018 • Unai Garciarena, Alexander Mendiburu, Roberto Santana
We evaluate the method to introduce imputation methods as part of TPOT.
1 code implementation • 11 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.
no code implementations • 4 Jun 2017 • Unai Garciarena, Roberto Santana, Alexander Mendiburu
Missing data has a ubiquitous presence in real-life applications of machine learning techniques.
1 code implementation • 18 Feb 2017 • Roberto Santana
We show that our method is able to reproduce the same behavior as human-designed algebraic operators.
no code implementations • 17 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.
no code implementations • 10 Dec 2015 • Roberto Santana, Alexander Mendiburu, Jose A. Lozano
NM-landscapes have been recently introduced as a class of tunable rugged models.
no code implementations • 18 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.
no code implementations • 2 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.