
When and How to Fool Explainable Models (and Humans) with Adversarial Examples
Reliable deployment of machine learning models such as neural networks c...
read it

Redefining Neural Architecture Search of Heterogeneous MultiNetwork Models by Characterizing Variation Operators and Model Components
With neural architecture search methods gaining ground on manually desig...
read it

On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future
Neuroevolutionary algorithms, automatic searches of neural network struc...
read it

Analysis of Dominant Classes in Universal Adversarial Perturbations
The reasons why Deep Neural Networks are susceptible to being fooled by ...
read it

Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions
Despite the remarkable performance and generalization levels of deep lea...
read it

On the human evaluation of audio adversarial examples
Humanmachine interaction is increasingly dependent on speech communicat...
read it

Universal adversarial examples in speech command classification
Adversarial examples are inputs intentionally perturbed with the aim of ...
read it

Towards automatic construction of multinetwork models for heterogeneous multitask learning
Multitask learning, as it is understood nowadays, consists of using one...
read it

On the performance of multiobjective estimation of distribution algorithms for combinatorial problems
Fitness landscape analysis investigates features with a high influence o...
read it

Towards a more efficient representation of imputation operators in TPOT
Automated Machine Learning encompasses a set of metaalgorithms intended...
read it

Graybox optimization and factorized distribution algorithms: where two worlds collide
The concept of graybox optimization, in juxtaposition to blackbox opti...
read it

Evolving imputation strategies for missing data in classification problems with TPOT
Missing data has a ubiquitous presence in reallife applications of mach...
read it

Reproducing and learning new algebraic operations on word embeddings using genetic programming
Wordvector representations associate a high dimensional realvector to ...
read it

Evolutionary Approaches to Optimization Problems in Chimera Topologies
Chimera graphs define the topology of one of the first commercially avai...
read it

Computing factorized approximations of Paretofronts using mNMlandscapes and Boltzmann distributions
NMlandscapes have been recently introduced as a class of tunable rugged...
read it

MOEA/DGM: Using probabilistic graphical models in MOEA/D for solving combinatorial optimization problems
Evolutionary algorithms based on modeling the statistical dependencies (...
read it
Roberto Santana
is this you? claim profile